def __init__(self, model_path=INCEPTION_V2_PATH, image_size=299):
cache_dir = os.sep.join(model_path.split(os.sep)[:-1])
get_file(fname=model_path.split(os.sep)[-1],
cache_dir=cache_dir,
cache_subdir='',
origin=INCEPTION_V2_URL,
untar=True)
self._get_session()
self.checkpoint_file = model_path
self.image_size = image_size
self._get_inception_preprocessing(inception_size=224)
self.arg_scope = inception.inception_v2_arg_scope()
with slim.arg_scope(self.arg_scope):
self.logits, self.end_points = inception.inception_v2(
self.scaled_input_tensor,
is_training=False,
num_classes=1001,
reuse=False)
end_point = list(self.end_points.values())[-3]
kernel_size = end_point.get_shape().as_list()[-2]
with variable_scope.variable_scope('InceptionV2/Logits',
reuse=True):
embedding = layers_lib.avg_pool2d(end_point,
kernel_size,
padding='VALID',
scope='AvgPool_1a_%dx%d' %
(kernel_size, kernel_size))
self.end_points['PreLogits'] = embedding
self._restore()
def avg_pool2d(inputs,
kernel_size=2,
stride=2,
padding='SAME',
explicit_padding=True,
scope=None,
outputs_collections=None):
"""
SAME PADDING equally
:param inputs: [N, H, W, C]
:param kernel_size: kernel size
:param stride: pooling stride
:param padding: padding mode
:param scope: var_scope & operation name
:param outputs_collections: add result to some collection
:return:
"""
kernel_size = [kernel_size, kernel_size
] if type(kernel_size) is int else kernel_size
stride = [stride, stride] if type(stride) is int else stride
if padding == 'SAME' and explicit_padding:
inputs = same_padding(inputs, kernel_size, [1, 1])
padding = 'VALID'
pool = layers_lib.avg_pool2d(inputs,
kernel_size,
stride=stride,
padding=padding,
data_format='NHWC',
outputs_collections=outputs_collections,
scope=scope)
return pool
def avg_pool2d(inputs,
kernel_size=2,
stride=2,
padding='SAME',
scope=None,
outputs_collections=None):
"""
SAME PADDING equally
:param inputs: [N, H, W, C]
:param kernel_size: kernel size
:param stride: pooling stride
:param padding: padding mode
:param scope: var_scope & operation name
:param outputs_collections: add result to some collection
:return:
"""
if padding == 'SAME':
inputs = same_padding(inputs, [kernel_size, kernel_size], [1, 1])
pool = layers_lib.avg_pool2d(inputs,
kernel_size,
stride=stride,
padding='VALID',
data_format='NHWC',
outputs_collections=outputs_collections,
scope=scope)
return pool
def inception_v1(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.8,
prediction_fn=layers_lib.softmax,
spatial_squeeze=True,
reuse=None,
scope='InceptionV1'):
"""Defines the Inception V1 architecture.
This architecture is defined in:
Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed,
Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich.
http://arxiv.org/pdf/1409.4842v1.pdf.
The default image size used to train this network is 224x224.
Args:
inputs: a tensor of size [batch_size, height, width, channels].
num_classes: number of predicted classes.
is_training: whether is training or not.
dropout_keep_prob: the percentage of activation values that are retained.
prediction_fn: a function to get predictions out of logits.
spatial_squeeze: if True, logits is of shape is [B, C], if false logits is
of shape [B, 1, 1, C], where B is batch_size and C is number of classes.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
scope: Optional variable_scope.
Returns:
logits: the pre-softmax activations, a tensor of size
[batch_size, num_classes]
end_points: a dictionary from components of the network to the corresponding
activation.
"""
# Final pooling and prediction
with variable_scope.variable_scope(
scope, 'InceptionV1', [inputs, num_classes], reuse=reuse) as scope:
with arg_scope(
[layers_lib.batch_norm, layers_lib.dropout], is_training=is_training):
net, end_points = inception_v1_base(inputs, scope=scope)
with variable_scope.variable_scope('Logits'):
net = layers_lib.avg_pool2d(
net, [7, 7], stride=1, scope='MaxPool_0a_7x7')
net = layers_lib.dropout(net, dropout_keep_prob, scope='Dropout_0b')
logits = layers.conv2d(
net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='Conv2d_0c_1x1')
if spatial_squeeze:
logits = array_ops.squeeze(logits, [1, 2], name='SpatialSqueeze')
end_points['Logits'] = logits
end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
return logits, end_points
def inception():
image = tf.placeholder(tf.float32, [None, 224, 224, 3], 'image')
with slim.arg_scope(inception_arg_scope(is_training=False)):
with variable_scope.variable_scope(
'InceptionV1', 'InceptionV1', [image, 1000], reuse=None) as scope:
with arg_scope(
[layers_lib.batch_norm, layers_lib.dropout], is_training=False):
net, end_points = inception_v1_base(image, scope=scope)
with variable_scope.variable_scope('Logits'):
net_conv = layers_lib.avg_pool2d(
net, [7, 7], stride=1, scope='MaxPool_0a_7x7')
print(net_conv.shape)
return net_conv, image
def inception_2d_fields(img,
fields,
num_classes=30,
is_training=True,
dropout_keep_prob=0.6,
prediction_fn=layers_lib.softmax,
spatial_squeeze=True,
reuse=None,
scope='InceptionV1_Fields'
):
with arg_scope([layers.conv2d, layers_lib.fully_connected],
weights_initializer=tf.contrib.layers.xavier_initializer(),
biases_initializer=tf.constant_initializer(0.2),
weights_regularizer=regularizers.l2_regularizer(0.0002),
biases_regularizer=regularizers.l2_regularizer(0.0002)):
net, end_points = inception_2d.inception_v1_base(img, scope=scope, final_endpoint='Mixed_4b')
with variable_scope.variable_scope('Logits'):
net = layers_lib.avg_pool2d(net, [5, 5], stride=3, scope='AvgPool_0a_5x5')
net = layers.conv2d(inputs=net, num_outputs=128, kernel_size=1)
net = tf.reshape(net, [-1, 1, 1, 4 * 4 * 128])
net = array_ops.squeeze(net,[1,2],name='Squeeze4Fields')
net = tf.concat([net,fields],axis=1)
net = layers.fully_connected(inputs=net, num_outputs=1024)
net = layers_lib.dropout(net, dropout_keep_prob, scope='Dropout_0b')
logits = layers.fully_connected(inputs=net,
num_outputs=num_classes,
activation_fn=None,
weights_initializer=tf.contrib.layers.xavier_initializer(),
biases_initializer=tf.constant_initializer(0.0),
weights_regularizer=regularizers.l2_regularizer(0.0002),
biases_regularizer=regularizers.l2_regularizer(0.0002),
scope='InnerProduct')
# logits = layers.conv2d(
# net,
# num_classes, [1, 1],
# activation_fn=None,
# normalizer_fn=None,
# scope='Conv2d_0c_1x1')
if spatial_squeeze:
logits = array_ops.squeeze(logits, [1, 2], name='SpatialSqueeze')
end_points['Logits'] = logits
end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
return logits, end_points
def inception_v3(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.8,
min_depth=16,
depth_multiplier=1.0,
prediction_fn=layers_lib.softmax,
spatial_squeeze=True,
reuse=None,
scope='InceptionV3'):
"""Inception model from http://arxiv.org/abs/1512.00567.
"Rethinking the Inception Architecture for Computer Vision"
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens,
Zbigniew Wojna.
With the default arguments this method constructs the exact model defined in
the paper. However, one can experiment with variations of the inception_v3
network by changing arguments dropout_keep_prob, min_depth and
depth_multiplier.
The default image size used to train this network is 299x299.
Args:
inputs: a tensor of size [batch_size, height, width, channels].
num_classes: number of predicted classes.
is_training: whether is training or not.
dropout_keep_prob: the percentage of activation values that are retained.
min_depth: Minimum depth value (number of channels) for all convolution ops.
Enforced when depth_multiplier < 1, and not an active constraint when
depth_multiplier >= 1.
depth_multiplier: Float multiplier for the depth (number of channels)
for all convolution ops. The value must be greater than zero. Typical
usage will be to set this value in (0, 1) to reduce the number of
parameters or computation cost of the model.
prediction_fn: a function to get predictions out of logits.
spatial_squeeze: if True, logits is of shape is [B, C], if false logits is
of shape [B, 1, 1, C], where B is batch_size and C is number of classes.
To use this parameter, the input images must be smaller
than 300x300 pixels, in which case the output logit layer
does not contain spatial information and can be removed.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
scope: Optional variable_scope.
Returns:
logits: the pre-softmax activations, a tensor of size
[batch_size, num_classes]
end_points: a dictionary from components of the network to the corresponding
activation.
Raises:
ValueError: if 'depth_multiplier' is less than or equal to zero.
"""
if depth_multiplier <= 0:
raise ValueError('depth_multiplier is not greater than zero.')
depth = lambda d: max(int(d * depth_multiplier), min_depth)
with variable_scope.variable_scope(
scope, 'InceptionV3', [inputs, num_classes], reuse=reuse) as scope:
with arg_scope(
[layers_lib.batch_norm, layers_lib.dropout], is_training=is_training):
net, end_points = inception_v3_base(
inputs,
scope=scope,
min_depth=min_depth,
depth_multiplier=depth_multiplier)
# Auxiliary Head logits
with arg_scope(
[layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d],
stride=1,
padding='SAME'):
aux_logits = end_points['Mixed_6e']
with variable_scope.variable_scope('AuxLogits'):
aux_logits = layers_lib.avg_pool2d(
aux_logits, [5, 5],
stride=3,
padding='VALID',
scope='AvgPool_1a_5x5')
aux_logits = layers.conv2d(
aux_logits, depth(128), [1, 1], scope='Conv2d_1b_1x1')
# Shape of feature map before the final layer.
kernel_size = _reduced_kernel_size_for_small_input(aux_logits, [5, 5])
aux_logits = layers.conv2d(
aux_logits,
depth(768),
kernel_size,
weights_initializer=trunc_normal(0.01),
padding='VALID',
scope='Conv2d_2a_{}x{}'.format(*kernel_size))
aux_logits = layers.conv2d(
aux_logits,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
weights_initializer=trunc_normal(0.001),
scope='Conv2d_2b_1x1')
if spatial_squeeze:
aux_logits = array_ops.squeeze(
aux_logits, [1, 2], name='SpatialSqueeze')
end_points['AuxLogits'] = aux_logits
# Final pooling and prediction
with variable_scope.variable_scope('Logits'):
kernel_size = _reduced_kernel_size_for_small_input(net, [8, 8])
net = layers_lib.avg_pool2d(
net,
kernel_size,
padding='VALID',
scope='AvgPool_1a_{}x{}'.format(*kernel_size))
# 1 x 1 x 2048
net = layers_lib.dropout(
net, keep_prob=dropout_keep_prob, scope='Dropout_1b')
end_points['PreLogits'] = net
# 2048
logits = layers.conv2d(
net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='Conv2d_1c_1x1')
if spatial_squeeze:
logits = array_ops.squeeze(logits, [1, 2], name='SpatialSqueeze')
# 1000
end_points['Logits'] = logits
end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
return logits, end_points
def inception_v3_base(inputs,
final_endpoint='Mixed_7c',
min_depth=16,
depth_multiplier=1.0,
scope=None):
"""Inception model from http://arxiv.org/abs/1512.00567.
Constructs an Inception v3 network from inputs to the given final endpoint.
This method can construct the network up to the final inception block
Mixed_7c.
Note that the names of the layers in the paper do not correspond to the names
of the endpoints registered by this function although they build the same
network.
Here is a mapping from the old_names to the new names:
Old name | New name
=======================================
conv0 | Conv2d_1a_3x3
conv1 | Conv2d_2a_3x3
conv2 | Conv2d_2b_3x3
pool1 | MaxPool_3a_3x3
conv3 | Conv2d_3b_1x1
conv4 | Conv2d_4a_3x3
pool2 | MaxPool_5a_3x3
mixed_35x35x256a | Mixed_5b
mixed_35x35x288a | Mixed_5c
mixed_35x35x288b | Mixed_5d
mixed_17x17x768a | Mixed_6a
mixed_17x17x768b | Mixed_6b
mixed_17x17x768c | Mixed_6c
mixed_17x17x768d | Mixed_6d
mixed_17x17x768e | Mixed_6e
mixed_8x8x1280a | Mixed_7a
mixed_8x8x2048a | Mixed_7b
mixed_8x8x2048b | Mixed_7c
Args:
inputs: a tensor of size [batch_size, height, width, channels].
final_endpoint: specifies the endpoint to construct the network up to. It
can be one of ['Conv2d_1a_3x3', 'Conv2d_2a_3x3', 'Conv2d_2b_3x3',
'MaxPool_3a_3x3', 'Conv2d_3b_1x1', 'Conv2d_4a_3x3', 'MaxPool_5a_3x3',
'Mixed_5b', 'Mixed_5c', 'Mixed_5d', 'Mixed_6a', 'Mixed_6b', 'Mixed_6c',
'Mixed_6d', 'Mixed_6e', 'Mixed_7a', 'Mixed_7b', 'Mixed_7c'].
min_depth: Minimum depth value (number of channels) for all convolution ops.
Enforced when depth_multiplier < 1, and not an active constraint when
depth_multiplier >= 1.
depth_multiplier: Float multiplier for the depth (number of channels)
for all convolution ops. The value must be greater than zero. Typical
usage will be to set this value in (0, 1) to reduce the number of
parameters or computation cost of the model.
scope: Optional variable_scope.
Returns:
tensor_out: output tensor corresponding to the final_endpoint.
end_points: a set of activations for external use, for example summaries or
losses.
Raises:
ValueError: if final_endpoint is not set to one of the predefined values,
or depth_multiplier <= 0
"""
# end_points will collect relevant activations for external use, for example
# summaries or losses.
end_points = {}
if depth_multiplier <= 0:
raise ValueError('depth_multiplier is not greater than zero.')
depth = lambda d: max(int(d * depth_multiplier), min_depth)
with variable_scope.variable_scope(scope, 'InceptionV3', [inputs]):
with arg_scope(
[layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d],
stride=1,
padding='VALID'):
# 299 x 299 x 3
end_point = 'Conv2d_1a_3x3'
net = layers.conv2d(inputs, depth(32), [3, 3], stride=2, scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 149 x 149 x 32
end_point = 'Conv2d_2a_3x3'
net = layers.conv2d(net, depth(32), [3, 3], scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 147 x 147 x 32
end_point = 'Conv2d_2b_3x3'
net = layers.conv2d(
net, depth(64), [3, 3], padding='SAME', scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 147 x 147 x 64
end_point = 'MaxPool_3a_3x3'
net = layers_lib.max_pool2d(net, [3, 3], stride=2, scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 73 x 73 x 64
end_point = 'Conv2d_3b_1x1'
net = layers.conv2d(net, depth(80), [1, 1], scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 73 x 73 x 80.
end_point = 'Conv2d_4a_3x3'
net = layers.conv2d(net, depth(192), [3, 3], scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 71 x 71 x 192.
end_point = 'MaxPool_5a_3x3'
net = layers_lib.max_pool2d(net, [3, 3], stride=2, scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 35 x 35 x 192.
# Inception blocks
with arg_scope(
[layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d],
stride=1,
padding='SAME'):
# mixed: 35 x 35 x 256.
end_point = 'Mixed_5b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, depth(48), [1, 1], scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(64), [5, 5], scope='Conv2d_0b_5x5')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(96), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3, depth(32), [1, 1], scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_1: 35 x 35 x 288.
end_point = 'Mixed_5c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, depth(48), [1, 1], scope='Conv2d_0b_1x1')
branch_1 = layers.conv2d(
branch_1, depth(64), [5, 5], scope='Conv_1_0c_5x5')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(96), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3, depth(64), [1, 1], scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_2: 35 x 35 x 288.
end_point = 'Mixed_5d'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, depth(48), [1, 1], scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(64), [5, 5], scope='Conv2d_0b_5x5')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(96), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3, depth(64), [1, 1], scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_3: 17 x 17 x 768.
end_point = 'Mixed_6a'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net,
depth(384), [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_1a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(96), [3, 3], scope='Conv2d_0b_3x3')
branch_1 = layers.conv2d(
branch_1,
depth(96), [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_1a_1x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(
net, [3, 3], stride=2, padding='VALID', scope='MaxPool_1a_3x3')
net = array_ops.concat([branch_0, branch_1, branch_2], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed4: 17 x 17 x 768.
end_point = 'Mixed_6b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, depth(128), [1, 1], scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(128), [1, 7], scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(
branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net, depth(128), [1, 1], scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(128), [7, 1], scope='Conv2d_0b_7x1')
branch_2 = layers.conv2d(
branch_2, depth(128), [1, 7], scope='Conv2d_0c_1x7')
branch_2 = layers.conv2d(
branch_2, depth(128), [7, 1], scope='Conv2d_0d_7x1')
branch_2 = layers.conv2d(
branch_2, depth(192), [1, 7], scope='Conv2d_0e_1x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3, depth(192), [1, 1], scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_5: 17 x 17 x 768.
end_point = 'Mixed_6c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, depth(160), [1, 1], scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(160), [1, 7], scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(
branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net, depth(160), [1, 1], scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(160), [7, 1], scope='Conv2d_0b_7x1')
branch_2 = layers.conv2d(
branch_2, depth(160), [1, 7], scope='Conv2d_0c_1x7')
branch_2 = layers.conv2d(
branch_2, depth(160), [7, 1], scope='Conv2d_0d_7x1')
branch_2 = layers.conv2d(
branch_2, depth(192), [1, 7], scope='Conv2d_0e_1x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3, depth(192), [1, 1], scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_6: 17 x 17 x 768.
end_point = 'Mixed_6d'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, depth(160), [1, 1], scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(160), [1, 7], scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(
branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net, depth(160), [1, 1], scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(160), [7, 1], scope='Conv2d_0b_7x1')
branch_2 = layers.conv2d(
branch_2, depth(160), [1, 7], scope='Conv2d_0c_1x7')
branch_2 = layers.conv2d(
branch_2, depth(160), [7, 1], scope='Conv2d_0d_7x1')
branch_2 = layers.conv2d(
branch_2, depth(192), [1, 7], scope='Conv2d_0e_1x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3, depth(192), [1, 1], scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_7: 17 x 17 x 768.
end_point = 'Mixed_6e'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(192), [1, 7], scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(
branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(192), [7, 1], scope='Conv2d_0b_7x1')
branch_2 = layers.conv2d(
branch_2, depth(192), [1, 7], scope='Conv2d_0c_1x7')
branch_2 = layers.conv2d(
branch_2, depth(192), [7, 1], scope='Conv2d_0d_7x1')
branch_2 = layers.conv2d(
branch_2, depth(192), [1, 7], scope='Conv2d_0e_1x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3, depth(192), [1, 1], scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_8: 8 x 8 x 1280.
end_point = 'Mixed_7a'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
branch_0 = layers.conv2d(
branch_0,
depth(320), [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_1a_3x3')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(192), [1, 7], scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(
branch_1, depth(192), [7, 1], scope='Conv2d_0c_7x1')
branch_1 = layers.conv2d(
branch_1,
depth(192), [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_1a_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(
net, [3, 3], stride=2, padding='VALID', scope='MaxPool_1a_3x3')
net = array_ops.concat([branch_0, branch_1, branch_2], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_9: 8 x 8 x 2048.
end_point = 'Mixed_7b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(320), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, depth(384), [1, 1], scope='Conv2d_0a_1x1')
branch_1 = array_ops.concat(
[
layers.conv2d(
branch_1, depth(384), [1, 3], scope='Conv2d_0b_1x3'),
layers.conv2d(
branch_1, depth(384), [3, 1], scope='Conv2d_0b_3x1')
],
3)
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net, depth(448), [1, 1], scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(384), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = array_ops.concat(
[
layers.conv2d(
branch_2, depth(384), [1, 3], scope='Conv2d_0c_1x3'),
layers.conv2d(
branch_2, depth(384), [3, 1], scope='Conv2d_0d_3x1')
],
3)
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3, depth(192), [1, 1], scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_10: 8 x 8 x 2048.
end_point = 'Mixed_7c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(320), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, depth(384), [1, 1], scope='Conv2d_0a_1x1')
branch_1 = array_ops.concat(
[
layers.conv2d(
branch_1, depth(384), [1, 3], scope='Conv2d_0b_1x3'),
layers.conv2d(
branch_1, depth(384), [3, 1], scope='Conv2d_0c_3x1')
],
3)
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net, depth(448), [1, 1], scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(384), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = array_ops.concat(
[
layers.conv2d(
branch_2, depth(384), [1, 3], scope='Conv2d_0c_1x3'),
layers.conv2d(
branch_2, depth(384), [3, 1], scope='Conv2d_0d_3x1')
],
3)
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3, depth(192), [1, 1], scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
raise ValueError('Unknown final endpoint %s' % final_endpoint)
def get_loss(self,
net_model,
masks,
batch_size=None,
return_segmentation_net=True,
return_decision_net=True,
output_resolution_reduction=8):
"""Adds all losses for the model.
Note the final loss is not returned. Instead, the list of losses are collected
by slim.losses. The losses are accumulated in tower_loss() and summed to
calculate the total loss.
Args:
logits: List of logits from inference(). Each entry is a 2-D float Tensor.
labels: Labels from distorted_inputs or inputs(). 1-D tensor
of shape [batch_size]
batch_size: integer
"""
if not batch_size:
raise Exception("Missing batch_size")
net, decision_net, endpoints = net_model
if output_resolution_reduction > 1:
mask_blur_kernel = [
output_resolution_reduction * 2 + 1,
output_resolution_reduction * 2 + 1
]
masks = layers_lib.avg_pool2d(
masks,
mask_blur_kernel,
stride=output_resolution_reduction,
padding='SAME',
scope='pool_mask',
outputs_collections='tower_0/_end_points')
if self.use_corss_entropy_seg_net is False:
masks = tf.greater(masks, tf.constant(0.5))
predictions = net
tf.summary.image('prediction', predictions)
l1 = None
l2 = None
if return_segmentation_net:
if self.positive_weight > 1:
pos_pixels = tf.less(tf.constant(0.0), masks)
neg_pixels = tf.greater_equal(tf.constant(0.0), masks)
num_pos_pixels = tf.cast(tf.count_nonzero(pos_pixels),
dtype=tf.float32)
num_neg_pixels = tf.cast(tf.count_nonzero(neg_pixels),
dtype=tf.float32)
pos_pixels = tf.cast(pos_pixels, dtype=tf.float32)
neg_pixels = tf.cast(neg_pixels, dtype=tf.float32)
positive_weight = tf.cond(
num_pos_pixels > tf.constant(0, dtype=tf.float32),
lambda: tf.multiply(
tf.div(num_neg_pixels, num_pos_pixels),
tf.constant(self.positive_weight, dtype=tf.float32)),
lambda: tf.constant(self.positive_weight, dtype=tf.float32
))
positive_weight = tf.reshape(positive_weight, [1])
# weight positive samples more !!
weights = tf.add(neg_pixels,
tf.multiply(pos_pixels, positive_weight))
# noramlize weights so that the sum of weights is always equal to the num of elements
N = tf.constant(weights.shape[1]._value *
weights.shape[2]._value,
dtype=tf.float32)
factor = tf.reduce_sum(weights, axis=[1, 2])
factor = tf.divide(N, factor)
weights = tf.multiply(weights,
tf.reshape(factor, [-1, 1, 1, 1]))
if self.use_corss_entropy_seg_net is False:
l1 = tf.losses.mean_squared_error(masks,
predictions,
weights=weights)
else:
l1 = tf.losses.sigmoid_cross_entropy(
logits=predictions,
multi_class_labels=masks,
weights=weights
) # NOTE: weights were added but not tested yet !!
else:
if self.use_corss_entropy_seg_net is False:
l1 = tf.losses.mean_squared_error(masks, predictions)
else:
l1 = tf.losses.sigmoid_cross_entropy(
logits=predictions, multi_class_labels=masks)
if return_decision_net:
with tf.name_scope('decision'):
masks = tf.cast(masks, tf.float32)
label = tf.minimum(tf.reduce_sum(masks, [1, 2, 3]),
tf.constant(1.0))
if len(decision_net.shape) == 2:
decision_net = tf.squeeze(decision_net, [1])
elif len(decision_net.shape) == 4:
decision_net = tf.squeeze(decision_net, [1, 2, 3])
else:
raise Exception(
"Only 2 or 4 dimensional output expected for decision_net"
)
decision_net = tf.reshape(decision_net, [-1, 1])
label = tf.reshape(label, [-1, 1])
l2 = tf.losses.sigmoid_cross_entropy(
logits=decision_net,
multi_class_labels=label,
weights=self.decision_positive_weight)
return [l1, l2]
def inception_v2(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.8,
min_depth=16,
depth_multiplier=1.0,
prediction_fn=layers_lib.softmax,
spatial_squeeze=True,
reuse=None,
scope='InceptionV2'):
"""Inception v2 model for classification.
Constructs an Inception v2 network for classification as described in
http://arxiv.org/abs/1502.03167.
The default image size used to train this network is 224x224.
Args:
inputs: a tensor of shape [batch_size, height, width, channels].
num_classes: number of predicted classes.
is_training: whether is training or not.
dropout_keep_prob: the percentage of activation values that are retained.
min_depth: Minimum depth value (number of channels) for all convolution ops.
Enforced when depth_multiplier < 1, and not an active constraint when
depth_multiplier >= 1.
depth_multiplier: Float multiplier for the depth (number of channels)
for all convolution ops. The value must be greater than zero. Typical
usage will be to set this value in (0, 1) to reduce the number of
parameters or computation cost of the model.
prediction_fn: a function to get predictions out of logits.
spatial_squeeze: if True, logits is of shape is [B, C], if false logits is
of shape [B, 1, 1, C], where B is batch_size and C is number of classes.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
scope: Optional variable_scope.
Returns:
logits: the pre-softmax activations, a tensor of size
[batch_size, num_classes]
end_points: a dictionary from components of the network to the corresponding
activation.
Raises:
ValueError: if final_endpoint is not set to one of the predefined values,
or depth_multiplier <= 0
"""
if depth_multiplier <= 0:
raise ValueError('depth_multiplier is not greater than zero.')
# Final pooling and prediction
with variable_scope.variable_scope(
scope, 'InceptionV2', [inputs, num_classes], reuse=reuse) as scope:
with arg_scope(
[layers_lib.batch_norm, layers_lib.dropout], is_training=is_training):
net, end_points = inception_v2_base(
inputs,
scope=scope,
min_depth=min_depth,
depth_multiplier=depth_multiplier)
with variable_scope.variable_scope('Logits'):
kernel_size = _reduced_kernel_size_for_small_input(net, [7, 7])
net = layers_lib.avg_pool2d(
net,
kernel_size,
padding='VALID',
scope='AvgPool_1a_{}x{}'.format(*kernel_size))
# 1 x 1 x 1024
net = layers_lib.dropout(
net, keep_prob=dropout_keep_prob, scope='Dropout_1b')
logits = layers.conv2d(
net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='Conv2d_1c_1x1')
if spatial_squeeze:
logits = array_ops.squeeze(logits, [1, 2], name='SpatialSqueeze')
end_points['Logits'] = logits
end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
return logits, end_points
def inception_v3_base(inputs,
final_endpoint='Mixed_7c',
min_depth=16,
depth_multiplier=1.0,
scope=None):
"""Inception model from http://arxiv.org/abs/1512.00567.
Constructs an Inception v3 network from inputs to the given final endpoint.
This method can construct the network up to the final inception block
Mixed_7c.
Note that the names of the layers in the paper do not correspond to the names
of the endpoints registered by this function although they build the same
network.
Here is a mapping from the old_names to the new names:
Old name | New name
=======================================
conv0 | Conv2d_1a_3x3
conv1 | Conv2d_2a_3x3
conv2 | Conv2d_2b_3x3
pool1 | MaxPool_3a_3x3
conv3 | Conv2d_3b_1x1
conv4 | Conv2d_4a_3x3
pool2 | MaxPool_5a_3x3
mixed_35x35x256a | Mixed_5b
mixed_35x35x288a | Mixed_5c
mixed_35x35x288b | Mixed_5d
mixed_17x17x768a | Mixed_6a
mixed_17x17x768b | Mixed_6b
mixed_17x17x768c | Mixed_6c
mixed_17x17x768d | Mixed_6d
mixed_17x17x768e | Mixed_6e
mixed_8x8x1280a | Mixed_7a
mixed_8x8x2048a | Mixed_7b
mixed_8x8x2048b | Mixed_7c
Args:
inputs: a tensor of size [batch_size, height, width, channels].
final_endpoint: specifies the endpoint to construct the network up to. It
can be one of ['Conv2d_1a_3x3', 'Conv2d_2a_3x3', 'Conv2d_2b_3x3',
'MaxPool_3a_3x3', 'Conv2d_3b_1x1', 'Conv2d_4a_3x3', 'MaxPool_5a_3x3',
'Mixed_5b', 'Mixed_5c', 'Mixed_5d', 'Mixed_6a', 'Mixed_6b', 'Mixed_6c',
'Mixed_6d', 'Mixed_6e', 'Mixed_7a', 'Mixed_7b', 'Mixed_7c'].
min_depth: Minimum depth value (number of channels) for all convolution ops.
Enforced when depth_multiplier < 1, and not an active constraint when
depth_multiplier >= 1.
depth_multiplier: Float multiplier for the depth (number of channels)
for all convolution ops. The value must be greater than zero. Typical
usage will be to set this value in (0, 1) to reduce the number of
parameters or computation cost of the model.
scope: Optional variable_scope.
Returns:
tensor_out: output tensor corresponding to the final_endpoint.
end_points: a set of activations for external use, for example summaries or
losses.
Raises:
ValueError: if final_endpoint is not set to one of the predefined values,
or depth_multiplier <= 0
"""
# end_points will collect relevant activations for external use, for example
# summaries or losses.
end_points = {}
if depth_multiplier <= 0:
raise ValueError('depth_multiplier is not greater than zero.')
depth = lambda d: max(int(d * depth_multiplier), min_depth)
with variable_scope.variable_scope(scope, 'InceptionV3', [inputs]):
with arg_scope(
[layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d],
stride=1,
padding='VALID'):
# 299 x 299 x 3
end_point = 'Conv2d_1a_3x3'
net = layers.conv2d(inputs,
depth(32), [3, 3],
stride=2,
scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 149 x 149 x 32
end_point = 'Conv2d_2a_3x3'
net = layers.conv2d(net, depth(32), [3, 3], scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 147 x 147 x 32
end_point = 'Conv2d_2b_3x3'
net = layers.conv2d(net,
depth(64), [3, 3],
padding='SAME',
scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 147 x 147 x 64
end_point = 'MaxPool_3a_3x3'
net = layers_lib.max_pool2d(net, [3, 3], stride=2, scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 73 x 73 x 64
end_point = 'Conv2d_3b_1x1'
net = layers.conv2d(net, depth(80), [1, 1], scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 73 x 73 x 80.
end_point = 'Conv2d_4a_3x3'
net = layers.conv2d(net, depth(192), [3, 3], scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 71 x 71 x 192.
end_point = 'MaxPool_5a_3x3'
net = layers_lib.max_pool2d(net, [3, 3], stride=2, scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 35 x 35 x 192.
# Inception blocks
with arg_scope(
[layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d],
stride=1,
padding='SAME'):
# mixed: 35 x 35 x 256.
end_point = 'Mixed_5b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(64), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(48), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(64), [5, 5],
scope='Conv2d_0b_5x5')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(64), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(96), [3, 3],
scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(branch_2,
depth(96), [3, 3],
scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(32), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat_v2(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_1: 35 x 35 x 288.
end_point = 'Mixed_5c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(64), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(48), [1, 1],
scope='Conv2d_0b_1x1')
branch_1 = layers.conv2d(branch_1,
depth(64), [5, 5],
scope='Conv_1_0c_5x5')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(64), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(96), [3, 3],
scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(branch_2,
depth(96), [3, 3],
scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(64), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat_v2(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_2: 35 x 35 x 288.
end_point = 'Mixed_5d'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(64), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(48), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(64), [5, 5],
scope='Conv2d_0b_5x5')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(64), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(96), [3, 3],
scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(branch_2,
depth(96), [3, 3],
scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(64), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat_v2(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_3: 17 x 17 x 768.
end_point = 'Mixed_6a'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(384), [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_1a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(64), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(96), [3, 3],
scope='Conv2d_0b_3x3')
branch_1 = layers.conv2d(branch_1,
depth(96), [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_1a_1x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(net, [3, 3],
stride=2,
padding='VALID',
scope='MaxPool_1a_3x3')
net = array_ops.concat_v2([branch_0, branch_1, branch_2], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed4: 17 x 17 x 768.
end_point = 'Mixed_6b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(128), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(128), [1, 7],
scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(branch_1,
depth(192), [7, 1],
scope='Conv2d_0c_7x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(128), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(128), [7, 1],
scope='Conv2d_0b_7x1')
branch_2 = layers.conv2d(branch_2,
depth(128), [1, 7],
scope='Conv2d_0c_1x7')
branch_2 = layers.conv2d(branch_2,
depth(128), [7, 1],
scope='Conv2d_0d_7x1')
branch_2 = layers.conv2d(branch_2,
depth(192), [1, 7],
scope='Conv2d_0e_1x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(192), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat_v2(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_5: 17 x 17 x 768.
end_point = 'Mixed_6c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(160), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(160), [1, 7],
scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(branch_1,
depth(192), [7, 1],
scope='Conv2d_0c_7x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(160), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(160), [7, 1],
scope='Conv2d_0b_7x1')
branch_2 = layers.conv2d(branch_2,
depth(160), [1, 7],
scope='Conv2d_0c_1x7')
branch_2 = layers.conv2d(branch_2,
depth(160), [7, 1],
scope='Conv2d_0d_7x1')
branch_2 = layers.conv2d(branch_2,
depth(192), [1, 7],
scope='Conv2d_0e_1x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(192), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat_v2(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_6: 17 x 17 x 768.
end_point = 'Mixed_6d'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(160), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(160), [1, 7],
scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(branch_1,
depth(192), [7, 1],
scope='Conv2d_0c_7x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(160), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(160), [7, 1],
scope='Conv2d_0b_7x1')
branch_2 = layers.conv2d(branch_2,
depth(160), [1, 7],
scope='Conv2d_0c_1x7')
branch_2 = layers.conv2d(branch_2,
depth(160), [7, 1],
scope='Conv2d_0d_7x1')
branch_2 = layers.conv2d(branch_2,
depth(192), [1, 7],
scope='Conv2d_0e_1x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(192), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat_v2(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_7: 17 x 17 x 768.
end_point = 'Mixed_6e'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(192), [1, 7],
scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(branch_1,
depth(192), [7, 1],
scope='Conv2d_0c_7x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(192), [7, 1],
scope='Conv2d_0b_7x1')
branch_2 = layers.conv2d(branch_2,
depth(192), [1, 7],
scope='Conv2d_0c_1x7')
branch_2 = layers.conv2d(branch_2,
depth(192), [7, 1],
scope='Conv2d_0d_7x1')
branch_2 = layers.conv2d(branch_2,
depth(192), [1, 7],
scope='Conv2d_0e_1x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(192), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat_v2(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_8: 8 x 8 x 1280.
end_point = 'Mixed_7a'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
branch_0 = layers.conv2d(branch_0,
depth(320), [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_1a_3x3')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(192), [1, 7],
scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(branch_1,
depth(192), [7, 1],
scope='Conv2d_0c_7x1')
branch_1 = layers.conv2d(branch_1,
depth(192), [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_1a_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(net, [3, 3],
stride=2,
padding='VALID',
scope='MaxPool_1a_3x3')
net = array_ops.concat_v2([branch_0, branch_1, branch_2], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_9: 8 x 8 x 2048.
end_point = 'Mixed_7b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(320), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(384), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = array_ops.concat_v2([
layers.conv2d(branch_1,
depth(384), [1, 3],
scope='Conv2d_0b_1x3'),
layers.conv2d(branch_1,
depth(384), [3, 1],
scope='Conv2d_0b_3x1')
], 3)
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(448), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(384), [3, 3],
scope='Conv2d_0b_3x3')
branch_2 = array_ops.concat_v2([
layers.conv2d(branch_2,
depth(384), [1, 3],
scope='Conv2d_0c_1x3'),
layers.conv2d(branch_2,
depth(384), [3, 1],
scope='Conv2d_0d_3x1')
], 3)
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(192), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat_v2(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_10: 8 x 8 x 2048.
end_point = 'Mixed_7c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(320), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(384), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = array_ops.concat_v2([
layers.conv2d(branch_1,
depth(384), [1, 3],
scope='Conv2d_0b_1x3'),
layers.conv2d(branch_1,
depth(384), [3, 1],
scope='Conv2d_0c_3x1')
], 3)
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(448), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(384), [3, 3],
scope='Conv2d_0b_3x3')
branch_2 = array_ops.concat_v2([
layers.conv2d(branch_2,
depth(384), [1, 3],
scope='Conv2d_0c_1x3'),
layers.conv2d(branch_2,
depth(384), [3, 1],
scope='Conv2d_0d_3x1')
], 3)
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(192), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat_v2(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
raise ValueError('Unknown final endpoint %s' % final_endpoint)
def ldnet_v1(inputs,
num_classes=3,
dropout_keep_prob=0.5,
spatial_squeeze=True,
scope="ldnet",
use_deform_conv=True,
print_current_tensor=False):
"""
ldnet architecture:
input: 32*32*3
input depth kenal stride padding
conv0： net = conv(input, 32, [3, 3], 1, "same")
--> 32*32*32
conv1: net = conv(net, 32, [3, 3], 1, "same")
--> 32*32*32
conv2： net = conv(net, 64, [3, 3], 1, "same")
--> 32*32*64
maxpool1: net = pool(net, [3, 3], 1, "same")
--> 32*32*64
conv3: net = conv(net, 192, [3, 3], 1, "same")
--> 32*32*192
maxpool2: net = pool(net, [3, 3], 1, "same")
--> 32*32*192
ldnet blocks:
mixed_1: 32 x 32 x 320 Feature extraction module
mixed_2: 32 x 32 x 320 Feature extraction module
mixed_res1: 32 x 32 x 320 Feature extraction module
mixed_3: 16 x 16 x 640 Dimension reduction module
mixed_4: 16 x 16 x 640 Feature extraction module
mixed_res2: 16 x 16 x 640 Feature extraction module
mixed_5: 8 x 8 x 1280 Dimension reduction module
mixed_6: 8 x 8 x 1280 Feature extraction module
mixed_res3: 8 x 8 x 1280 Feature extraction module
Final pooling and prediction -> 3
:param inputs: the size of imputs is [batch_num, width, height, channel].
:param num_classes: num of classes predicted.
:param dropout_keep_prob: dropout probability.
:param spatial_squeeze: whether or not squeeze.
:param scope: optional scope.
:param use_deform_conv: whether to use deform conv.
:param print_current_tensor: whether or not print current tenser shape, name and type.
:return:
logits: [batch_size, num_classes]
"""
# end_points will collect relevant activations for the computation
# of shortcuts.
end_points = []
with variable_scope.variable_scope(scope, "ldnet_v1", [inputs]):
with arg_scope([layers.conv2d, layers_lib.max_pool2d],
kernel_size=[3, 3],
stride=1,
padding='SAME'):
# input: 32 * 32 * 3
net = inputs
end_point = "conv0"
# if use_deform_conv:
# net = ConvOffset2D(3, name='conv0_offset')(net) # net offset
net = layers.conv2d(net, 32, scope=end_point)
if print_current_tensor:
print(net)
# --> 32 * 32 * 32
end_point = "conv1"
if use_deform_conv:
net = ConvOffset2D(32, name='conv1_offset')(net) # net offset
net = layers.conv2d(net, 32, scope=end_point)
if print_current_tensor: print(net)
# --> 32 * 32 * 32
end_point = "conv2"
if use_deform_conv:
net = ConvOffset2D(32, name='conv2_offset')(net) # net offset
net = layers.conv2d(net, 64, scope=end_point)
if print_current_tensor: print(net)
# --> 32 * 32 * 64
end_point = "maxpool0"
net = layers_lib.max_pool2d(net,
kernel_size=[2, 2],
scope=end_point)
if print_current_tensor: print(net)
# --> 32 * 32 * 64
end_point = 'conv3'
if use_deform_conv:
net = ConvOffset2D(64, name='conv3_offset')(net) # net offset
net = layers.conv2d(net, 192, scope=end_point)
if print_current_tensor: print(net)
# end_points.append(net)
# --> 32 * 32 * 192
end_point = 'maxpool1'
net = layers_lib.max_pool2d(net,
kernel_size=[2, 2],
scope=end_point)
if print_current_tensor: print(net)
# net.alias = end_point
# end_points.append(net)
# --> 32 * 32 * 192
# ldnet blocks
with arg_scope(
[layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d],
stride=1,
padding='SAME'):
# mixed_1: 32 x 32 x 320 Feature extraction module
end_point = 'mixed_1'
with variable_scope.variable_scope(end_point):
net = _feature_extraction_residual(net,
first_layer_depth=48,
second_layer_depth=64,
last_layer_depth=96,
scope='feature_extraction')
end_points.append(net)
if print_current_tensor: print(net, len(end_points))
# mixed_2: 32 x 32 x 320 Feature extraction module
end_point = 'mixed_2'
with variable_scope.variable_scope(end_point):
net = _feature_extraction_residual(
net,
first_layer_depth=48,
second_layer_depth=64,
last_layer_depth=96,
scope='feature_extraction_residual')
end_points.append(net)
if print_current_tensor: print(net, len(end_points))
# mixed_res1: 32 x 32 x 320 Feature extraction module
end_point = 'mixed_res1'
with variable_scope.variable_scope(end_point):
net = _feature_extraction_residual(
net,
first_layer_depth=48,
second_layer_depth=64,
last_layer_depth=96,
scope='feature_extraction_residual')
net_linear = layers.conv2d(net,
int(net.shape[3]), [1, 1],
activation_fn=None,
scope='net_linear_projection')
shortcuts = _shortcuts_addition(net.shape,
end_points[-1],
end_points[-2],
scope="shortcuts_addition")
net = nn_ops.relu(net_linear + shortcuts)
end_points.append(net)
if print_current_tensor: print(net, len(end_points))
# mixed_3: 16 x 16 x 640 Dimension reduction module
end_point = "mixed_3"
with variable_scope.variable_scope(end_point):
net = _dimension_reduction(net,
branch_0_depth=224,
branch_1_depth=96,
scope='dimension_reduction')
end_points.append(net)
if print_current_tensor: print(net, len(end_points))
# mixed_4: 16 x 16 x 640 Feature extraction module
end_point = "mixed_4"
with variable_scope.variable_scope(end_point):
net = _feature_extraction_residual(
net,
first_layer_depth=48 * 2,
second_layer_depth=64 * 2,
last_layer_depth=96 * 2,
scope='feature_extraction_residual')
end_points.append(net)
if print_current_tensor: print(net, len(end_points))
# mixed_res2: 16 x 16 x 640 Feature extraction module
end_point = "mixed_res2"
with variable_scope.variable_scope(end_point):
net = _feature_extraction_residual(
net,
first_layer_depth=48 * 2,
second_layer_depth=64 * 2,
last_layer_depth=96 * 2,
scope='feature_extraction_residual')
net_linear = layers.conv2d(net,
int(net.shape[3]), [1, 1],
activation_fn=None,
scope='net_linear_projection')
shortcuts = _shortcuts_addition(net.shape,
end_points[-1],
end_points[-2],
scope="shortcuts_addition")
net = nn_ops.relu(net_linear + shortcuts)
end_points.append(net)
if print_current_tensor: print(net, len(end_points))
# mixed_5: 8 x 8 x 1280 Dimension reduction module
end_point = "mixed_5"
with variable_scope.variable_scope(end_point):
net = _dimension_reduction(net,
branch_0_depth=224 * 2,
branch_1_depth=96 * 2,
scope='dimension_reduction')
end_points.append(net)
if print_current_tensor: print(net, len(end_points))
# mixed_6: 8 x 8 x 1280 Feature extraction module
end_point = "mixed_6"
with variable_scope.variable_scope(end_point):
net = _feature_extraction_residual(
net,
first_layer_depth=48 * 4,
second_layer_depth=64 * 4,
last_layer_depth=96 * 4,
scope='feature_extraction_residual')
end_points.append(net)
if print_current_tensor: print(net, len(end_points))
# mixed_res3: 8 x 8 x 1280 Feature extraction module
end_point = "mixed_res3"
with variable_scope.variable_scope(end_point):
net = _feature_extraction_residual(
net,
first_layer_depth=48 * 4,
second_layer_depth=64 * 4,
last_layer_depth=96 * 4,
scope='feature_extraction_residual')
net_linear = layers.conv2d(net,
int(net.shape[3]), [1, 1],
activation_fn=None,
scope='net_linear_projection')
shortcuts = _shortcuts_addition(net.shape,
end_points[-1],
end_points[-2],
scope="shortcuts_addition")
net = nn_ops.relu(net_linear + shortcuts)
end_points.append(net)
if print_current_tensor: print(net, len(end_points))
# Final pooling and prediction
with variable_scope.variable_scope('Logits'):
with arg_scope([layers.conv2d],
normalizer_fn=None,
normalizer_params=None):
net = layers.conv2d(net,
int(net.shape[3]), [3, 3],
stride=2,
scope='conv2d_1a_3x3')
# 4 x 4 x 1280
net = layers_lib.avg_pool2d(net, [4, 4],
padding='VALID',
scope='AvgPool_1b_4x4')
# 1 x 1 x 1280
# net = layers.conv2d(net, 640, [1, 1], scope='Conv2d_0c_1x1')
# local1
with variable_scope.variable_scope('local1') as scope:
# Move everything into depth so we can perform a single matrix multiply.
reshape = tf.reshape(net, [-1, 1280])
weights = _variable_with_weight_decay('weights',
shape=[1280, 640],
stddev=0.04,
wd=0.0001)
biases = _variable_on_cpu('biases', [640],
tf.constant_initializer(0.1))
net = tf.nn.relu(tf.matmul(reshape, weights) + biases,
name=scope.name)
# 1 x 1 x 640
net = layers_lib.dropout(net,
keep_prob=dropout_keep_prob,
scope='Dropout_0c')
# net = layers.conv2d(net, 320, [1, 1], scope='Conv2d_0d_1x1')
# local2
with variable_scope.variable_scope('local2') as scope:
weights = _variable_with_weight_decay('weights',
shape=[640, 320],
stddev=0.04,
wd=0.0001)
biases = _variable_on_cpu('biases', [320],
tf.constant_initializer(0.1))
net = tf.nn.relu(tf.matmul(net, weights) + biases,
name=scope.name)
# 1 x 1 x 320
net = layers_lib.dropout(net,
keep_prob=dropout_keep_prob,
scope='Dropout_0d')
net = tf.expand_dims(net, 1)
net = tf.expand_dims(net, 1)
logits = layers.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='Conv2d_0e_1x1')
# 1 x 1 x 3
if spatial_squeeze:
logits = array_ops.squeeze(logits, [1, 2],
name='SpatialSqueeze')
# 3
return logits
def inception_v3(inputs,
num_classes=12,
is_training=True,
dropout_keep_prob=0.8,
prediction_fn=layers_lib.softmax,
reuse=None,
hparam_string=None,
global_pool=True,
scope='InceptionV3'):
"""Inception model from http://arxiv.org/abs/1512.00567.
"Rethinking the Inception Architecture for Computer Vision"
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens,
Zbigniew Wojna.
With the default arguments this method constructs the exact model defined in
the paper. However, one can experiment with variations of the inception_v3
network by changing arguments dropout_keep_prob, min_depth and
depth_multiplier.
The default image size used to train this network is 299x299.
Args:
inputs: a tensor of size [batch_size, height, width, channels].
num_classes: number of predicted classes.
is_training: whether is training or not.
dropout_keep_prob: the percentage of activation values that are retained.
min_depth: Minimum depth value (number of channels) for all convolution ops.
Enforced when depth_multiplier < 1, and not an active constraint when
depth_multiplier >= 1.
depth_multiplier: Float multiplier for the depth (number of channels)
for all convolution ops. The value must be greater than zero. Typical
usage will be to set this value in (0, 1) to reduce the number of
parameters or computation cost of the model.
prediction_fn: a function to get predictions out of logits.
spatial_squeeze: if True, logits is of shape is [B, C], if false logits is
of shape [B, 1, 1, C], where B is batch_size and C is number of classes.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
scope: Optional variable_scope.
Returns:
logits: the pre-softmax activations, a tensor of size
[batch_size, num_classes]
end_points: a dictionary from components of the network to the corresponding
activation.
Raises:
ValueError: if 'depth_multiplier' is less than or equal to zero.
"""
hparams = create_hparams(hparam_string=hparam_string)
if hparams.depth_multiplier <= 0:
raise ValueError('depth_multiplier is not greater than zero.')
depth = lambda d: max(int(d * hparams.depth_multiplier), hparams.min_depth)
with variable_scope.variable_scope(scope,
'InceptionV3', [inputs, num_classes],
reuse=reuse) as scope:
with arg_scope([layers_lib.batch_norm, layers_lib.dropout],
is_training=is_training):
net, end_points = inception_v3_base(inputs,
scope=scope,
**hparams.values())
# Final pooling and prediction
with variable_scope.variable_scope('Logits'):
if global_pool:
# Global average pooling.
net_avg = math_ops.reduce_mean(net, [1, 2],
keep_dims=True,
name='global_avg_pool')
net_max = math_ops.reduce_max(net, [1, 2],
keep_dims=True,
name='global_max_pool')
net = array_ops.concat([net_avg, net_max], -1)
else:
kernel_size = _reduced_kernel_size_for_small_input(
net, [8, 8])
net = layers_lib.avg_pool2d(
net,
kernel_size,
padding='VALID',
scope='AvgPool_1a_{}x{}'.format(*kernel_size))
# 1 x 1 x 2048
net = layers_lib.dropout(net,
keep_prob=dropout_keep_prob,
scope='Dropout_1b')
end_points['PreLogits'] = net
# 2048
logits = layers.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='Conv2d_1c_1x1')
logits = layers_core.dense(array_ops.squeeze(
logits, [1, 2], name='SpatialSqueeze'),
num_classes,
name='logits')
end_points['Logits'] = logits
end_points['Predictions'] = prediction_fn(logits,
scope='Predictions')
return logits, end_points
def vgg_19_style_transfer(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.5,
spatial_squeeze=True,
scope='vgg_19'):
"""Oxford Net VGG 19-Layers version E Example.
Note: All the fully_connected layers have been transformed to conv2d layers.
To use in classification mode, resize input to 224x224.
Args:
inputs: a tensor of size [batch_size, height, width, channels].
num_classes: number of predicted classes.
is_training: whether or not the model is being trained.
dropout_keep_prob: the probability that activations are kept in the dropout
layers during training.
spatial_squeeze: whether or not should squeeze the spatial dimensions of the
outputs. Useful to remove unnecessary dimensions for classification.
scope: Optional scope for the variables.
Returns:
the last op containing the log predictions and end_points dict.
"""
with variable_scope.variable_scope(scope, 'vgg_19', [inputs]) as sc:
end_points_collection = sc.name + '_end_points'
# Collect outputs for conv2d, fully_connected and max_pool2d.
with arg_scope(
[layers.conv2d, layers_lib.fully_connected, layers_lib.max_pool2d],
outputs_collections=end_points_collection):
net = layers_lib.repeat(inputs,
2,
layers.conv2d,
64, [3, 3],
scope='conv1')
net = layers_lib.avg_pool2d(net, [2, 2], scope='pool1')
net = layers_lib.repeat(net,
2,
layers.conv2d,
128, [3, 3],
scope='conv2')
net = layers_lib.avg_pool2d(net, [2, 2], scope='pool2')
net = layers_lib.repeat(net,
4,
layers.conv2d,
256, [3, 3],
scope='conv3')
net = layers_lib.avg_pool2d(net, [2, 2], scope='pool3')
net = layers_lib.repeat(net,
4,
layers.conv2d,
512, [3, 3],
scope='conv4')
net = layers_lib.avg_pool2d(net, [2, 2], scope='pool4')
net = layers_lib.repeat(net,
4,
layers.conv2d,
512, [3, 3],
scope='conv5')
net = layers_lib.avg_pool2d(net, [2, 2], scope='pool5')
# Use conv2d instead of fully_connected layers.
net = layers.conv2d(net,
4096, [7, 7],
padding='VALID',
scope='fc6')
net = layers_lib.dropout(net,
dropout_keep_prob,
is_training=is_training,
scope='dropout6')
net = layers.conv2d(net, 4096, [1, 1], scope='fc7')
net = layers_lib.dropout(net,
dropout_keep_prob,
is_training=is_training,
scope='dropout7')
net = layers.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='fc8')
# Convert end_points_collection into a end_point dict.
end_points = utils.convert_collection_to_dict(
end_points_collection)
if spatial_squeeze:
net = array_ops.squeeze(net, [1, 2], name='fc8/squeezed')
end_points[sc.name + '/fc8'] = net
return net, end_points
def _feature_extraction_residual(net,
first_layer_depth=48,
second_layer_depth=64,
last_layer_depth=96,
use_deform_conv=False,
scope='feature_extraction_residual'):
"""
Feature extraction module of ldnet-v1.
:param net: the net input.
:param first_layer_depth: first layer depth.
:param second_layer_depth: second layer depth.
:param last_layer_depth: last layer depth.
:param scope: optional scope.
:return:
the size of returned net: [batch_size, height, width, channel], which
channel = (second_layer_depth + last_layer_depth) * 2
"""
with variable_scope.variable_scope(scope):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
first_layer_depth, [1, 1],
scope='Conv2d_0a_1x1')
if use_deform_conv:
branch_0 = ConvOffset2D(first_layer_depth,
name='conv3_offset')(
branch_0) # net offset
branch_0 = layers.conv2d(branch_0,
second_layer_depth, [3, 3],
scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
first_layer_depth, [1, 1],
scope='Conv2d_0a_1x1')
if use_deform_conv:
branch_1 = ConvOffset2D(first_layer_depth,
name='conv3_offset')(
branch_1) # net offset
branch_1 = layers.conv2d(branch_1,
second_layer_depth, [5, 5],
scope='Conv2d_0b_5x5')
if use_deform_conv:
branch_1 = ConvOffset2D(second_layer_depth,
name='conv3_offset')(
branch_1) # net offset
branch_1 = layers.conv2d(branch_1,
last_layer_depth, [5, 5],
scope='Conv2d_0c_5x5')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
first_layer_depth, [1, 1],
scope='Conv2d_0a_1x1')
if use_deform_conv:
branch_2 = ConvOffset2D(first_layer_depth,
name='conv3_offset')(
branch_2) # net offset
branch_2 = layers.conv2d(branch_2,
second_layer_depth, [7, 7],
scope='Conv2d_0b_7x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [5, 5],
scope='AvgPool_0a_5x5')
branch_3 = layers.conv2d(branch_3,
last_layer_depth, [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
return net
def inception_v2(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.8,
min_depth=16,
depth_multiplier=1.0,
prediction_fn=layers_lib.softmax,
spatial_squeeze=True,
reuse=None,
scope='InceptionV2'):
"""Inception v2 model for classification.
Constructs an Inception v2 network for classification as described in
http://arxiv.org/abs/1502.03167.
The recommended image size used to train this network is 224x224. For image
sizes that differ substantially, it is recommended to use inception_v2_base()
and connect custom final layers to the output.
Args:
inputs: a tensor of shape [batch_size, height, width, channels].
num_classes: number of predicted classes.
is_training: whether is training or not.
dropout_keep_prob: the percentage of activation values that are retained.
min_depth: Minimum depth value (number of channels) for all convolution ops.
Enforced when depth_multiplier < 1, and not an active constraint when
depth_multiplier >= 1.
depth_multiplier: Float multiplier for the depth (number of channels)
for all convolution ops. The value must be greater than zero. Typical
usage will be to set this value in (0, 1) to reduce the number of
parameters or computation cost of the model.
prediction_fn: a function to get predictions out of logits.
spatial_squeeze: if True, logits is of shape [B, C], if false logits is
of shape [B, 1, 1, C], where B is batch_size and C is number of classes.
Note that input image sizes other than 224x224 might lead to different
spatial dimensions, and hence cannot be squeezed. In this event,
it is best to set spatial_squeeze as False, and perform a reduce_mean
over the resulting spatial dimensions with sizes exceeding 1.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
scope: Optional variable_scope.
Returns:
logits: the pre-softmax activations, a tensor of size
[batch_size, num_classes]
end_points: a dictionary from components of the network to the corresponding
activation.
Raises:
ValueError: if depth_multiplier <= 0.
"""
if depth_multiplier <= 0:
raise ValueError('depth_multiplier is not greater than zero.')
# Final pooling and prediction
with variable_scope.variable_scope(
scope, 'InceptionV2', [inputs, num_classes], reuse=reuse) as scope:
with arg_scope(
[layers_lib.batch_norm, layers_lib.dropout], is_training=is_training):
net, end_points = inception_v2_base(
inputs,
scope=scope,
min_depth=min_depth,
depth_multiplier=depth_multiplier)
with variable_scope.variable_scope('Logits'):
kernel_size = _reduced_kernel_size_for_small_input(net, [7, 7])
net = layers_lib.avg_pool2d(
net,
kernel_size,
padding='VALID',
scope='AvgPool_1a_{}x{}'.format(*kernel_size))
# 1 x 1 x 1024
net = layers_lib.dropout(
net, keep_prob=dropout_keep_prob, scope='Dropout_1b')
logits = layers.conv2d(
net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='Conv2d_1c_1x1')
if spatial_squeeze:
logits = array_ops.squeeze(logits, [1, 2], name='SpatialSqueeze')
end_points['Logits'] = logits
end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
return logits, end_points
def inception_v2_base(inputs,
final_endpoint='Mixed_5c',
min_depth=16,
depth_multiplier=1.0,
scope=None):
"""Inception v2 (6a2).
Constructs an Inception v2 network from inputs to the given final endpoint.
This method can construct the network up to the layer inception(5b) as
described in http://arxiv.org/abs/1502.03167.
Args:
inputs: a tensor of shape [batch_size, height, width, channels].
final_endpoint: specifies the endpoint to construct the network up to. It
can be one of ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1',
'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c', 'Mixed_4a',
'Mixed_4b', 'Mixed_4c', 'Mixed_4d', 'Mixed_4e', 'Mixed_5a', 'Mixed_5b',
'Mixed_5c'].
min_depth: Minimum depth value (number of channels) for all convolution ops.
Enforced when depth_multiplier < 1, and not an active constraint when
depth_multiplier >= 1.
depth_multiplier: Float multiplier for the depth (number of channels)
for all convolution ops. The value must be greater than zero. Typical
usage will be to set this value in (0, 1) to reduce the number of
parameters or computation cost of the model.
scope: Optional variable_scope.
Returns:
tensor_out: output tensor corresponding to the final_endpoint.
end_points: a set of activations for external use, for example summaries or
losses.
Raises:
ValueError: if final_endpoint is not set to one of the predefined values,
or depth_multiplier <= 0
"""
# end_points will collect relevant activations for external use, for example
# summaries or losses.
end_points = {}
# Used to find thinned depths for each layer.
if depth_multiplier <= 0:
raise ValueError('depth_multiplier is not greater than zero.')
depth = lambda d: max(int(d * depth_multiplier), min_depth)
with variable_scope.variable_scope(scope, 'InceptionV2', [inputs]):
with arg_scope(
[
layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d,
layers.separable_conv2d
],
stride=1,
padding='SAME'):
# Note that sizes in the comments below assume an input spatial size of
# 224x224, however, the inputs can be of any size greater 32x32.
# 224 x 224 x 3
end_point = 'Conv2d_1a_7x7'
# depthwise_multiplier here is different from depth_multiplier.
# depthwise_multiplier determines the output channels of the initial
# depthwise conv (see docs for tf.nn.separable_conv2d), while
# depth_multiplier controls the # channels of the subsequent 1x1
# convolution. Must have
# in_channels * depthwise_multipler <= out_channels
# so that the separable convolution is not overparameterized.
depthwise_multiplier = min(int(depth(64) / 3), 8)
net = layers.separable_conv2d(
inputs,
depth(64), [7, 7],
depth_multiplier=depthwise_multiplier,
stride=2,
weights_initializer=trunc_normal(1.0),
scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 112 x 112 x 64
end_point = 'MaxPool_2a_3x3'
net = layers_lib.max_pool2d(net, [3, 3], scope=end_point, stride=2)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 56 x 56 x 64
end_point = 'Conv2d_2b_1x1'
net = layers.conv2d(
net,
depth(64), [1, 1],
scope=end_point,
weights_initializer=trunc_normal(0.1))
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 56 x 56 x 64
end_point = 'Conv2d_2c_3x3'
net = layers.conv2d(net, depth(192), [3, 3], scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 56 x 56 x 192
end_point = 'MaxPool_3a_3x3'
net = layers_lib.max_pool2d(net, [3, 3], scope=end_point, stride=2)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 28 x 28 x 192
# Inception module.
end_point = 'Mixed_3b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(64), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(64), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(64), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(96), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(32), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 28 x 28 x 256
end_point = 'Mixed_3c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(64), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(96), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(64), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(96), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(64), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 28 x 28 x 320
end_point = 'Mixed_4a'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_0 = layers.conv2d(
branch_0, depth(160), [3, 3], stride=2, scope='Conv2d_1a_3x3')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(64), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(96), [3, 3], scope='Conv2d_0b_3x3')
branch_1 = layers.conv2d(
branch_1, depth(96), [3, 3], stride=2, scope='Conv2d_1a_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(
net, [3, 3], stride=2, scope='MaxPool_1a_3x3')
net = array_ops.concat([branch_0, branch_1, branch_2], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 14 x 14 x 576
end_point = 'Mixed_4b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(224), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(64), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(96), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(96), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(128), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(128), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 14 x 14 x 576
end_point = 'Mixed_4c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(96), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(128), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(96), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(128), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(128), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 14 x 14 x 576
end_point = 'Mixed_4d'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(160), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(160), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(160), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(160), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(96), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 14 x 14 x 576
end_point = 'Mixed_4e'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(96), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(192), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(160), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(192), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(192), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(96), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 14 x 14 x 576
end_point = 'Mixed_5a'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_0 = layers.conv2d(
branch_0, depth(192), [3, 3], stride=2, scope='Conv2d_1a_3x3')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(192), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(256), [3, 3], scope='Conv2d_0b_3x3')
branch_1 = layers.conv2d(
branch_1, depth(256), [3, 3], stride=2, scope='Conv2d_1a_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(
net, [3, 3], stride=2, scope='MaxPool_1a_3x3')
net = array_ops.concat([branch_0, branch_1, branch_2], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 7 x 7 x 1024
end_point = 'Mixed_5b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(352), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(192), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(320), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(160), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(224), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(224), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 7 x 7 x 1024
end_point = 'Mixed_5c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(352), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(192), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(320), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(192), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(224), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(224), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
raise ValueError('Unknown final endpoint %s' % final_endpoint)
def inception_g(inputs,
num_classes = 5,
dropout_keep_prob = 0.8,
prediction_fn = layers_lib.softmax,
scope='InceptionG'
):
end_points = {}
# conv2d
with arg_scope(
[layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d],
stride=1,
padding='VALID'):
# 48 x 48 x 1
end_point = 'Conv2d_1a_3x3'
net = layers.conv2d(inputs, 32, [3, 3], stride=2, scope=end_point)
end_points[end_point] = net
# 23 x 23 x 32
end_point = 'Conv2d_2a_3x3'
net = layers.conv2d(net, 64, [3, 3], scope=end_point)
end_points[end_point] = net
# 21 x 21 x 64
end_point = 'MaxPool_3a_3x3'
net = layers_lib.max_pool2d(net, [3, 3], stride=2, scope=end_point)
end_points[end_point] = net
# 10 x 10 x 64
end_point = 'Conv2d_3b_1x1'
net = layers.conv2d(net, 80, [1, 1], scope=end_point)
end_points[end_point] = net
# 8 x 8 x 80
end_point = 'Conv2d_4a_3x3'
net = layers.conv2d(net, 128, [3, 3], scope=end_point)
end_points[end_point] = net
# Inception blocks
with arg_scope(
[layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d],
stride=1,
padding='SAME'):
# 8 x 8 x 144
end_point = 'Mixed_5a'
branch_0 = layers.conv2d(
net, 64, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
net, 48, [1, 1], scope='Conv2d_1a_1x1')
branch_1 = layers.conv2d(
branch_1, 64, [5, 5], scope='Conv2d_1b_5x5')
branch_2 = layers.conv2d(
net, 64, [1, 1], scope='Conv2d_2a_1x1')
branch_2 = layers.conv2d(
branch_2, 96, [3, 3], scope='Conv2d_2b_3x3')
branch_2 = layers.conv2d(
branch_2, 96, [3, 3], scope='Conv2d_2c_3x3')
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_3a_3x3')
branch_3 = layers.conv2d(
branch_3, 64, [1, 1], scope='Conv2d_3c_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points[end_point] = net
# aver pooling and softmax
net = layers_lib.avg_pool2d(
net,
[8,8],
padding='VALID',
scope='AvgPool_0a_7x7')
net = layers_lib.dropout(
net, keep_prob=dropout_keep_prob, scope='Dropout_1b')
end_points['PreLogits'] = net
logits = layers.conv2d(
net,
num_classes, # num classes
[1, 1],
activation_fn=None,
normalizer_fn=None,
scope='Conv2d_1c_1x1')
logits = array_ops.squeeze(logits, [1, 2], name='SpatialSqueeze')
end_points['Logits'] = logits
end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
return logits, end_points
def inception_v3_branch(net,
end_points,
num_classes,
deformable,
attention_option,
dropout_keep_prob=0.8,
final_endpoint='Logits',
min_depth=16,
depth_multiplier=1.0,
spatial_squeeze=True,
scope=None):
if depth_multiplier <= 0:
raise ValueError('depth_multiplier is not greater than zero.')
depth = lambda d: max(int(d * depth_multiplier), min_depth)
with variable_scope.variable_scope(scope, 'InceptionV3',
[net, end_points]):
with arg_scope(
[layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d],
stride=1,
padding='SAME'):
# Deformable blocks
if deformable == '1':
end_point = 'Deformation'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Deform'):
net_feature = end_points['Conv2d_4a_3x3']
net_shape = net_feature.get_shape().as_list()
b = net_shape[0]
h = net_shape[1]
w = net_shape[2]
c = net_shape[3]
net_offset = layers.conv2d(end_points['Conv2d_3b_1x1'],
depth(2 * c), [3, 3],
padding='VALID',
scope=end_point + '_offset')
net = df._to_b_h_w_c(
df.tf_batch_map_offsets(
df._to_bc_h_w(net_feature, net_shape),
df._to_bc_h_w_2(net_offset, net_shape)), net_shape)
end_points[scope.name + '/' + end_point +
'_offset'] = net_offset
end_points[scope.name + '/' + end_point] = net
if end_point == final_endpoint:
return net, end_points
end_point = 'MaxPool_5a_3x3'
net = layers_lib.max_pool2d(net, [3, 3],
stride=2,
padding='VALID',
scope=end_point)
end_points[scope.name + '/' + end_point] = net
if end_point == final_endpoint:
return net, end_points
# 35 x 35 x 192.
# Attention blocks
if attention_option[0] == '1':
end_point = 'Attention_S'
with variable_scope.variable_scope(end_point):
map_shape = net.get_shape().as_list()
b = map_shape[0]
h = map_shape[1]
w = map_shape[2]
c = map_shape[3]
with variable_scope.variable_scope('Spatial'):
initial_map = layers.conv2d(net,
depth(c), [3, 3],
scope='Conv2d_4a_3x3')
attention_map = df._to_b_h_w_c(
tf.nn.softmax(df._to_bc_hw(initial_map,
map_shape)), map_shape)
net = net * attention_map
end_points[scope.name + '/' + end_point +
'_map'] = attention_map
end_points[scope.name + '/' + end_point] = net
if attention_option[1] == '1':
end_point = 'Attention_C'
with variable_scope.variable_scope(end_point):
map_shape = net.get_shape().as_list()
b = map_shape[0]
h = map_shape[1]
w = map_shape[2]
c = map_shape[3]
with variable_scope.variable_scope('Channel'):
initial_map = layers.conv2d(net,
depth(c), [3, 3],
scope='Conv2d_4a_3x3')
attention_map = tf.nn.softmax(
tf.reduce_mean(tf.reshape(initial_map,
[b * h * w, c]),
axis=0))
net = net * attention_map
end_points[scope.name + '/' + end_point +
'_map'] = attention_map
end_points[scope.name + '/' + end_point] = net
if attention_option[2] == '1':
end_point = 'Attention_S'
with variable_scope.variable_scope(end_point):
map_shape = net.get_shape().as_list()
b = map_shape[0]
h = map_shape[1]
w = map_shape[2]
c = map_shape[3]
with variable_scope.variable_scope('Spatial'):
initial_map = layers.conv2d(net,
depth(c), [3, 3],
scope='Conv2d_4a_3x3')
attention_map = df._to_b_h_w_c(
tf.nn.softmax(df.to_bc_hw(initial_map, map_shape)),
map_shape)
net = net * attention_map
end_points[scope.name + '/' + end_point +
'_map'] = attention_map
end_points[scope.name + '/' + end_point] = net
if attention_option[3] == '1':
end_point = 'Attention_M'
with variable_scope.variable_scope(end_point):
map_shape = net.get_shape().as_list()
b = map_shape[0]
h = map_shape[1]
w = map_shape[2]
c = map_shape[3]
with variable_scope.variable_scope('Modulation'):
initial_map = layers.conv2d(net,
depth(c), [3, 3],
scope='Conv2d_4a_3x3')
attention_map = tf.clip_by_value(initial_map, 0, 1)
net = net * attention_map
end_points[scope.name + '/' + end_point +
'_map'] = attention_map
end_points[scope.name + '/' + end_point] = net
# Inception blocks
# mixed: 35 x 35 x 256.
end_point = 'Mixed_5b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(64), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(48), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(64), [5, 5],
scope='Conv2d_0b_5x5')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(64), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(96), [3, 3],
scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(branch_2,
depth(96), [3, 3],
scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(32), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[scope.name + '/' + end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_1: 35 x 35 x 288.
end_point = 'Mixed_5c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(64), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(48), [1, 1],
scope='Conv2d_0b_1x1')
branch_1 = layers.conv2d(branch_1,
depth(64), [5, 5],
scope='Conv_1_0c_5x5')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(64), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(96), [3, 3],
scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(branch_2,
depth(96), [3, 3],
scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(64), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[scope.name + '/' + end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_2: 35 x 35 x 288.
end_point = 'Mixed_5d'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(64), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(48), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(64), [5, 5],
scope='Conv2d_0b_5x5')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(64), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(96), [3, 3],
scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(branch_2,
depth(96), [3, 3],
scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(64), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[scope.name + '/' + end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_3: 17 x 17 x 768.
end_point = 'Mixed_6a'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(384), [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_1a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(64), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(96), [3, 3],
scope='Conv2d_0b_3x3')
branch_1 = layers.conv2d(branch_1,
depth(96), [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_1a_1x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(net, [3, 3],
stride=2,
padding='VALID',
scope='MaxPool_1a_3x3')
net = array_ops.concat([branch_0, branch_1, branch_2], 3)
end_points[scope.name + '/' + end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed4: 17 x 17 x 768.
end_point = 'Mixed_6b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(128), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(128), [1, 7],
scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(branch_1,
depth(192), [7, 1],
scope='Conv2d_0c_7x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(128), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(128), [7, 1],
scope='Conv2d_0b_7x1')
branch_2 = layers.conv2d(branch_2,
depth(128), [1, 7],
scope='Conv2d_0c_1x7')
branch_2 = layers.conv2d(branch_2,
depth(128), [7, 1],
scope='Conv2d_0d_7x1')
branch_2 = layers.conv2d(branch_2,
depth(192), [1, 7],
scope='Conv2d_0e_1x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(192), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[scope.name + '/' + end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_5: 17 x 17 x 768.
end_point = 'Mixed_6c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(160), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(160), [1, 7],
scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(branch_1,
depth(192), [7, 1],
scope='Conv2d_0c_7x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(160), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(160), [7, 1],
scope='Conv2d_0b_7x1')
branch_2 = layers.conv2d(branch_2,
depth(160), [1, 7],
scope='Conv2d_0c_1x7')
branch_2 = layers.conv2d(branch_2,
depth(160), [7, 1],
scope='Conv2d_0d_7x1')
branch_2 = layers.conv2d(branch_2,
depth(192), [1, 7],
scope='Conv2d_0e_1x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(192), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[scope.name + '/' + end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_6: 17 x 17 x 768.
end_point = 'Mixed_6d'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(160), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(160), [1, 7],
scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(branch_1,
depth(192), [7, 1],
scope='Conv2d_0c_7x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(160), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(160), [7, 1],
scope='Conv2d_0b_7x1')
branch_2 = layers.conv2d(branch_2,
depth(160), [1, 7],
scope='Conv2d_0c_1x7')
branch_2 = layers.conv2d(branch_2,
depth(160), [7, 1],
scope='Conv2d_0d_7x1')
branch_2 = layers.conv2d(branch_2,
depth(192), [1, 7],
scope='Conv2d_0e_1x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(192), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[scope.name + '/' + end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_7: 17 x 17 x 768.
end_point = 'Mixed_6e'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(192), [1, 7],
scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(branch_1,
depth(192), [7, 1],
scope='Conv2d_0c_7x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(192), [7, 1],
scope='Conv2d_0b_7x1')
branch_2 = layers.conv2d(branch_2,
depth(192), [1, 7],
scope='Conv2d_0c_1x7')
branch_2 = layers.conv2d(branch_2,
depth(192), [7, 1],
scope='Conv2d_0d_7x1')
branch_2 = layers.conv2d(branch_2,
depth(192), [1, 7],
scope='Conv2d_0e_1x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(192), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[scope.name + '/' + end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_8: 8 x 8 x 1280.
end_point = 'Mixed_7a'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
branch_0 = layers.conv2d(branch_0,
depth(320), [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_1a_3x3')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(192), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(branch_1,
depth(192), [1, 7],
scope='Conv2d_0b_1x7')
branch_1 = layers.conv2d(branch_1,
depth(192), [7, 1],
scope='Conv2d_0c_7x1')
branch_1 = layers.conv2d(branch_1,
depth(192), [3, 3],
stride=2,
padding='VALID',
scope='Conv2d_1a_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(net, [3, 3],
stride=2,
padding='VALID',
scope='MaxPool_1a_3x3')
net = array_ops.concat([branch_0, branch_1, branch_2], 3)
end_points[scope.name + '/' + end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_9: 8 x 8 x 2048.
end_point = 'Mixed_7b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(320), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(384), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = array_ops.concat([
layers.conv2d(branch_1,
depth(384), [1, 3],
scope='Conv2d_0b_1x3'),
layers.conv2d(branch_1,
depth(384), [3, 1],
scope='Conv2d_0b_3x1')
], 3)
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(448), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(384), [3, 3],
scope='Conv2d_0b_3x3')
branch_2 = array_ops.concat([
layers.conv2d(branch_2,
depth(384), [1, 3],
scope='Conv2d_0c_1x3'),
layers.conv2d(branch_2,
depth(384), [3, 1],
scope='Conv2d_0d_3x1')
], 3)
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(192), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[scope.name + '/' + end_point] = net
if end_point == final_endpoint:
return net, end_points
# mixed_10: 8 x 8 x 2048.
end_point = 'Mixed_7c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net,
depth(320), [1, 1],
scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net,
depth(384), [1, 1],
scope='Conv2d_0a_1x1')
branch_1 = array_ops.concat([
layers.conv2d(branch_1,
depth(384), [1, 3],
scope='Conv2d_0b_1x3'),
layers.conv2d(branch_1,
depth(384), [3, 1],
scope='Conv2d_0c_3x1')
], 3)
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net,
depth(448), [1, 1],
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(branch_2,
depth(384), [3, 3],
scope='Conv2d_0b_3x3')
branch_2 = array_ops.concat([
layers.conv2d(branch_2,
depth(384), [1, 3],
scope='Conv2d_0c_1x3'),
layers.conv2d(branch_2,
depth(384), [3, 1],
scope='Conv2d_0d_3x1')
], 3)
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3,
depth(192), [1, 1],
scope='Conv2d_0b_1x1')
net = array_ops.concat(
[branch_0, branch_1, branch_2, branch_3], 3)
end_points[scope.name + '/' + end_point] = net
if end_point == final_endpoint:
return net, end_points
# Final pooling and prediction
end_point = 'Logits'
with variable_scope.variable_scope(end_point):
kernel_size = _reduced_kernel_size_for_small_input(net, [8, 8])
net = layers_lib.avg_pool2d(
net,
kernel_size,
padding='VALID',
scope='AvgPool_1a_{}x{}'.format(*kernel_size))
# 1 x 1 x 2048
net = layers_lib.dropout(net,
keep_prob=dropout_keep_prob,
scope='Dropout_1b')
# 2048
net = layers.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='Conv2d_1c_1x1')
if spatial_squeeze:
net = array_ops.squeeze(net, [1, 2], name='SpatialSqueeze')
end_points[scope.name + '/' + end_point] = net
if end_point == final_endpoint:
return net, end_points
raise ValueError('Unknown final endpoint %s' % final_endpoint)
def inception_v1(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.8,
prediction_fn=layers_lib.softmax,
spatial_squeeze=True,
reuse=None,
scope='InceptionV1',
use_5x5=None):
"""Defines the Inception V1 architecture.
This architecture is defined in:
Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed,
Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich.
http://arxiv.org/pdf/1409.4842v1.pdf.
The default image size used to train this network is 224x224.
Args:
inputs: a tensor of size [batch_size, height, width, channels].
num_classes: number of predicted classes.
is_training: whether is training or not.
dropout_keep_prob: the percentage of activation values that are retained.
prediction_fn: a function to get predictions out of logits.
spatial_squeeze: if True, logits is of shape is [B, C], if false logits is
of shape [B, 1, 1, C], where B is batch_size and C is number of classes.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
scope: Optional variable_scope.
use_5x5: If True, the inception filter sizes will be set to 5x5
as specified in Figure 2(b) of the paper. The default behavior is to continue
with 3x3 filter sizes.
Note: This invalidates all current checkpoints and the saved models will
be incompatible as well. The training would have to be done from the beginning.
Returns:
logits: the pre-softmax activations, a tensor of size
[batch_size, num_classes]
end_points: a dictionary from components of the network to the corresponding
activation.
"""
# Final pooling and prediction
with variable_scope.variable_scope(
scope, 'InceptionV1', [inputs, num_classes], reuse=reuse) as scope:
with arg_scope(
[layers_lib.batch_norm, layers_lib.dropout], is_training=is_training):
# If we want the same filters as in the original paper. The default is 3x3.
if use_5x5:
filter_size=[5, 5]
filter_size_str=str(filter_size[0])+'x'+str(filter_size[1])
net, end_points = inception_v1_base(inputs, scope=scope)
with variable_scope.variable_scope('Logits'):
net = layers_lib.avg_pool2d(
net, [7, 7], stride=1, scope='MaxPool_0a_7x7')
net = layers_lib.dropout(net, dropout_keep_prob, scope='Dropout_0b')
logits = layers.conv2d(
net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='Conv2d_0c_1x1')
if spatial_squeeze:
logits = array_ops.squeeze(logits, [1, 2], name='SpatialSqueeze')
end_points['Logits'] = logits
end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
return logits, end_points
def inception_v2_base(inputs,
final_endpoint='Mixed_5c',
min_depth=16,
depth_multiplier=1.0,
scope=None):
"""Inception v2 (6a2).
Constructs an Inception v2 network from inputs to the given final endpoint.
This method can construct the network up to the layer inception(5b) as
described in http://arxiv.org/abs/1502.03167.
Args:
inputs: a tensor of shape [batch_size, height, width, channels].
final_endpoint: specifies the endpoint to construct the network up to. It
can be one of ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1',
'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c', 'Mixed_4a',
'Mixed_4b', 'Mixed_4c', 'Mixed_4d', 'Mixed_4e', 'Mixed_5a', 'Mixed_5b',
'Mixed_5c'].
min_depth: Minimum depth value (number of channels) for all convolution ops.
Enforced when depth_multiplier < 1, and not an active constraint when
depth_multiplier >= 1.
depth_multiplier: Float multiplier for the depth (number of channels)
for all convolution ops. The value must be greater than zero. Typical
usage will be to set this value in (0, 1) to reduce the number of
parameters or computation cost of the model.
scope: Optional variable_scope.
Returns:
tensor_out: output tensor corresponding to the final_endpoint.
end_points: a set of activations for external use, for example summaries or
losses.
Raises:
ValueError: if final_endpoint is not set to one of the predefined values,
or depth_multiplier <= 0
"""
# end_points will collect relevant activations for external use, for example
# summaries or losses.
end_points = {}
# Used to find thinned depths for each layer.
if depth_multiplier <= 0:
raise ValueError('depth_multiplier is not greater than zero.')
depth = lambda d: max(int(d * depth_multiplier), min_depth)
with variable_scope.variable_scope(scope, 'InceptionV2', [inputs]):
with arg_scope(
[
layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d,
layers.separable_conv2d
],
stride=1,
padding='SAME'):
# Note that sizes in the comments below assume an input spatial size of
# 224x224, however, the inputs can be of any size greater 32x32.
# 224 x 224 x 3
end_point = 'Conv2d_1a_7x7'
# depthwise_multiplier here is different from depth_multiplier.
# depthwise_multiplier determines the output channels of the initial
# depthwise conv (see docs for tf.nn.separable_conv2d), while
# depth_multiplier controls the # channels of the subsequent 1x1
# convolution. Must have
# in_channels * depthwise_multipler <= out_channels
# so that the separable convolution is not overparameterized.
depthwise_multiplier = min(int(depth(64) / 3), 8)
net = layers.separable_conv2d(
inputs,
depth(64), [7, 7],
depth_multiplier=depthwise_multiplier,
stride=2,
weights_initializer=trunc_normal(1.0),
scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 112 x 112 x 64
end_point = 'MaxPool_2a_3x3'
net = layers_lib.max_pool2d(net, [3, 3], scope=end_point, stride=2)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 56 x 56 x 64
end_point = 'Conv2d_2b_1x1'
net = layers.conv2d(
net,
depth(64), [1, 1],
scope=end_point,
weights_initializer=trunc_normal(0.1))
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 56 x 56 x 64
end_point = 'Conv2d_2c_3x3'
net = layers.conv2d(net, depth(192), [3, 3], scope=end_point)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 56 x 56 x 192
end_point = 'MaxPool_3a_3x3'
net = layers_lib.max_pool2d(net, [3, 3], scope=end_point, stride=2)
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 28 x 28 x 192
# Inception module.
end_point = 'Mixed_3b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(64), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(64), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(64), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(96), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(32), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat(3, [branch_0, branch_1, branch_2, branch_3] )
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 28 x 28 x 256
end_point = 'Mixed_3c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(64), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(64), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(96), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(64), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(96), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(96), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(64), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat(3, [branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 28 x 28 x 320
end_point = 'Mixed_4a'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_0 = layers.conv2d(
branch_0, depth(160), [3, 3], stride=2, scope='Conv2d_1a_3x3')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(64), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(96), [3, 3], scope='Conv2d_0b_3x3')
branch_1 = layers.conv2d(
branch_1, depth(96), [3, 3], stride=2, scope='Conv2d_1a_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(
net, [3, 3], stride=2, scope='MaxPool_1a_3x3')
net = array_ops.concat(3, [branch_0, branch_1, branch_2])
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 14 x 14 x 576
end_point = 'Mixed_4b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(224), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(64), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(96), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(96), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(128), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(128), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat(3, [branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 14 x 14 x 576
end_point = 'Mixed_4c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(96), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(128), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(96), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(128), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(128), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat(3, [branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 14 x 14 x 576
end_point = 'Mixed_4d'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(160), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(160), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(160), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(160), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(96), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat(3, [branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 14 x 14 x 576
end_point = 'Mixed_4e'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(96), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(192), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(160), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(192), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(192), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(96), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat(3, [branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 14 x 14 x 576
end_point = 'Mixed_5a'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_0 = layers.conv2d(
branch_0, depth(192), [3, 3], stride=2, scope='Conv2d_1a_3x3')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(192), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(256), [3, 3], scope='Conv2d_0b_3x3')
branch_1 = layers.conv2d(
branch_1, depth(256), [3, 3], stride=2, scope='Conv2d_1a_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(
net, [3, 3], stride=2, scope='MaxPool_1a_3x3')
net = array_ops.concat(3, [branch_0, branch_1, branch_2])
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 7 x 7 x 1024
end_point = 'Mixed_5b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(352), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(192), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(320), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(160), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(224), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(224), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat(3, [branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
# 7 x 7 x 1024
end_point = 'Mixed_5c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, depth(352), [1, 1], scope='Conv2d_0a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net,
depth(192), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, depth(320), [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net,
depth(192), [1, 1],
weights_initializer=trunc_normal(0.09),
scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, depth(224), [3, 3], scope='Conv2d_0b_3x3')
branch_2 = layers.conv2d(
branch_2, depth(224), [3, 3], scope='Conv2d_0c_3x3')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
branch_3 = layers.conv2d(
branch_3,
depth(128), [1, 1],
weights_initializer=trunc_normal(0.1),
scope='Conv2d_0b_1x1')
net = array_ops.concat(3, [branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net
if end_point == final_endpoint:
return net, end_points
raise ValueError('Unknown final endpoint %s' % final_endpoint)
def model_fn(features, labels, mode, params):
"""
Based on https://github.com/tensorflow/tpu/blob/master/models/experimental/inception/inception_v2_tpu_model.py
:param features:
:param labels:
:param mode:
:param params:
:return:
"""
tf.summary.image('0_input', features, max_outputs=4)
training = mode == tf.estimator.ModeKeys.TRAIN
# 224 x 224 x 3
end_point = 'Conv2d_1a_7x7'
net = layers.conv2d(features, 64, [7, 7], stride=2, weights_initializer=trunc_normal(1.0), activation_fn=None, scope=end_point)
net = tf.layers.batch_normalization(net, training=training, name='{}_bn'.format(end_point))
net = tf.nn.relu(net, name='{}_act'.format(end_point))
tf.summary.image('1_{}'.format(end_point), net[:, :, :, 0:3], max_outputs=4)
# 112 x 112 x 64
end_point = 'MaxPool_2a_3x3'
net = layers_lib.max_pool2d(net, [3, 3], scope=end_point, stride=2, padding='SAME')
tf.summary.image('2_{}'.format(end_point), net[:, :, :, 0:3], max_outputs=4)
# 56 x 56 x 64
end_point = 'Conv2d_2b_1x1'
net = layers.conv2d(net, 64, [1, 1], activation_fn=None, scope=end_point, weights_initializer=trunc_normal(0.1))
net = tf.layers.batch_normalization(net, training=training, name='{}_bn'.format(end_point))
net = tf.nn.relu(net, name='{}_act'.format(end_point))
tf.summary.image('3_{}'.format(end_point), net[:, :, :, 0:3], max_outputs=4)
# 56 x 56 x 64
end_point = 'Conv2d_2c_3x3'
net = layers.conv2d(net, 192, [3, 3], activation_fn=None, scope=end_point)
net = tf.layers.batch_normalization(net, training=training, name='{}_bn'.format(end_point))
net = tf.nn.relu(net, name='{}_act'.format(end_point))
tf.summary.image('4_{}'.format(end_point), net[:, :, :, 0:3], max_outputs=4)
# 56 x 56 x 192
end_point = 'MaxPool_3a_3x3'
net = layers_lib.max_pool2d(net, [3, 3], scope=end_point, stride=2, padding='SAME')
tf.summary.image('5_{}'.format(end_point), net[:, :, :, 0:3], max_outputs=4)
# 28 x 28 x 192
# Inception module.
end_point = 'Mixed_3b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net, 64, [1, 1], activation_fn=None, scope='Conv2d_0a_1x1')
branch_0 = tf.layers.batch_normalization(branch_0, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_0 = tf.nn.relu(branch_0, name='{}_act'.format('Conv2d_0a_1x1'))
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net, 64, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0a_1x1'))
branch_1 = layers.conv2d(branch_1, 64, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0b_3x3'))
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net, 64, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0a_1x1'))
branch_2 = layers.conv2d(branch_2, 96, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0b_3x3'))
branch_2 = layers.conv2d(branch_2, 96, [3, 3], activation_fn=None, scope='Conv2d_0c_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0c_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0c_3x3'))
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], padding='SAME', stride=1, scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3, 32, [1, 1], weights_initializer=trunc_normal(0.1), activation_fn=None, scope='Conv2d_0b_1x1')
branch_3 = tf.layers.batch_normalization(branch_3, training=training, name='{}_bn'.format('Conv2d_0b_1x1'))
branch_3 = tf.nn.relu(branch_3, name='{}_act'.format('Conv2d_0b_1x1'))
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
# 28 x 28 x 256
end_point = 'Mixed_3c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net, 64, [1, 1], activation_fn=None, scope='Conv2d_0a_1x1')
branch_0 = tf.layers.batch_normalization(branch_0, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_0 = tf.nn.relu(branch_0, name='{}_act'.format('Conv2d_0a_1x1'))
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net, 64, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0a_1x1'))
branch_1 = layers.conv2d(branch_1, 96, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0b_3x3'))
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net, 64, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0a_1x1'))
branch_2 = layers.conv2d(branch_2, 96, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0b_3x3'))
branch_2 = layers.conv2d(branch_2, 96, [3, 3], activation_fn=None, scope='Conv2d_0c_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0c_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0c_3x3'))
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], padding='SAME', stride=1, scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3, 64, [1, 1], weights_initializer=trunc_normal(0.1), activation_fn=None, scope='Conv2d_0b_1x1')
branch_3 = tf.layers.batch_normalization(branch_3, training=training, name='{}_bn'.format('Conv2d_0b_1x1'))
branch_3 = tf.nn.relu(branch_3, name='{}_act'.format('Conv2d_0b_1x1'))
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
# 28 x 28 x 320
end_point = 'Mixed_4a'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net, 128, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_0 = tf.layers.batch_normalization(branch_0, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_0 = tf.nn.relu(branch_0, name='{}_act'.format('Conv2d_0a_1x1'))
branch_0 = layers.conv2d(branch_0, 160, [3, 3], stride=2, activation_fn=None, scope='Conv2d_1a_3x3')
branch_0 = tf.layers.batch_normalization(branch_0, training=training, name='{}_bn'.format('Conv2d_1a_3x3'))
branch_0 = tf.nn.relu(branch_0, name='{}_act'.format('Conv2d_1a_3x3'))
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net, 64, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0a_1x1'))
branch_1 = layers.conv2d(branch_1, 96, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0b_3x3'))
branch_1 = layers.conv2d(branch_1, 96, [3, 3], stride=2, activation_fn=None, scope='Conv2d_1a_3x3')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_1a_3x3'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_1a_3x3'))
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(net, [3, 3], stride=2, padding='SAME', scope='MaxPool_1a_3x3')
net = array_ops.concat([branch_0, branch_1, branch_2], 3)
# 14 x 14 x 576
end_point = 'Mixed_4b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net, 224, [1, 1], activation_fn=None, scope='Conv2d_0a_1x1')
branch_0 = tf.layers.batch_normalization(branch_0, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_0 = tf.nn.relu(branch_0, name='{}_act'.format('Conv2d_0a_1x1'))
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net, 64, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0a_1x1'))
branch_1 = layers.conv2d(branch_1, 96, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0b_3x3'))
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net, 96, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0a_1x1'))
branch_2 = layers.conv2d(branch_2, 128, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0b_3x3'))
branch_2 = layers.conv2d(branch_2, 128, [3, 3], activation_fn=None, scope='Conv2d_0c_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0c_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0c_3x3'))
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], padding='SAME', stride=1, scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3, 128, [1, 1], weights_initializer=trunc_normal(0.1), activation_fn=None, scope='Conv2d_0b_1x1')
branch_3 = tf.layers.batch_normalization(branch_3, training=training, name='{}_bn'.format('Conv2d_0b_1x1'))
branch_3 = tf.nn.relu(branch_3, name='{}_act'.format('Conv2d_0b_1x1'))
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
# 14 x 14 x 576
end_point = 'Mixed_4c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net, 192, [1, 1], activation_fn=None, scope='Conv2d_0a_1x1')
branch_0 = tf.layers.batch_normalization(branch_0, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_0 = tf.nn.relu(branch_0, name='{}_act'.format('Conv2d_0a_1x1'))
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net, 96, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0a_1x1'))
branch_1 = layers.conv2d(branch_1, 128, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0b_3x3'))
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net, 96, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0a_1x1'))
branch_2 = layers.conv2d(branch_2, 128, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0b_3x3'))
branch_2 = layers.conv2d(branch_2, 128, [3, 3], activation_fn=None, scope='Conv2d_0c_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0c_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0c_3x3'))
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], padding='SAME', stride=1, scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3, 128, [1, 1], weights_initializer=trunc_normal(0.1), activation_fn=None, scope='Conv2d_0b_1x1')
branch_3 = tf.layers.batch_normalization(branch_3, training=training, name='{}_bn'.format('Conv2d_0b_1x1'))
branch_3 = tf.nn.relu(branch_3, name='{}_act'.format('Conv2d_0b_1x1'))
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
# 14 x 14 x 576
end_point = 'Mixed_4d'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net, 160, [1, 1], activation_fn=None, scope='Conv2d_0a_1x1')
branch_0 = tf.layers.batch_normalization(branch_0, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_0 = tf.nn.relu(branch_0, name='{}_act'.format('Conv2d_0a_1x1'))
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net, 128, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0a_1x1'))
branch_1 = layers.conv2d(branch_1, 160, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0b_3x3'))
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net, 128, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0a_1x1'))
branch_2 = layers.conv2d(branch_2, 160, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0b_3x3'))
branch_2 = layers.conv2d(branch_2, 160, [3, 3], activation_fn=None, scope='Conv2d_0c_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0c_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0c_3x3'))
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], padding='SAME', stride=1, scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3, 96, [1, 1], weights_initializer=trunc_normal(0.1), activation_fn=None, scope='Conv2d_0b_1x1')
branch_3 = tf.layers.batch_normalization(branch_3, training=training, name='{}_bn'.format('Conv2d_0b_1x1'))
branch_3 = tf.nn.relu(branch_3, name='{}_act'.format('Conv2d_0b_1x1'))
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
# 14 x 14 x 576
end_point = 'Mixed_4e'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net, 96, [1, 1], activation_fn=None, scope='Conv2d_0a_1x1')
branch_0 = tf.layers.batch_normalization(branch_0, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_0 = tf.nn.relu(branch_0, name='{}_act'.format('Conv2d_0a_1x1'))
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net, 128, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0a_1x1'))
branch_1 = layers.conv2d(branch_1, 192, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0b_3x3'))
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net, 160, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0a_1x1'))
branch_2 = layers.conv2d(branch_2, 192, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0b_3x3'))
branch_2 = layers.conv2d(branch_2, 192, [3, 3], activation_fn=None, scope='Conv2d_0c_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0c_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0c_3x3'))
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], padding='SAME', stride=1, scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3, 96, [1, 1], weights_initializer=trunc_normal(0.1), activation_fn=None, scope='Conv2d_0b_1x1')
branch_3 = tf.layers.batch_normalization(branch_3, training=training, name='{}_bn'.format('Conv2d_0b_1x1'))
branch_3 = tf.nn.relu(branch_3, name='{}_act'.format('Conv2d_0b_1x1'))
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
# 14 x 14 x 576
end_point = 'Mixed_5a'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net, 128, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_0 = tf.layers.batch_normalization(branch_0, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_0 = tf.nn.relu(branch_0, name='{}_act'.format('Conv2d_0a_1x1'))
branch_0 = layers.conv2d(branch_0, 192, [3, 3], stride=2, activation_fn=None, scope='Conv2d_1a_3x3')
branch_0 = tf.layers.batch_normalization(branch_0, training=training, name='{}_bn'.format('Conv2d_1a_3x3'))
branch_0 = tf.nn.relu(branch_0, name='{}_act'.format('Conv2d_1a_3x3'))
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net, 192, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0a_1x1'))
branch_1 = layers.conv2d(branch_1, 256, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0b_3x3'))
branch_1 = layers.conv2d(branch_1, 256, [3, 3], stride=2, activation_fn=None, scope='Conv2d_1a_3x3')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_1a_3x3'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_1a_3x3'))
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(net, [3, 3], stride=2, padding='SAME', scope='MaxPool_1a_3x3')
net = array_ops.concat([branch_0, branch_1, branch_2], 3)
# 7 x 7 x 1024
end_point = 'Mixed_5b'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net, 352, [1, 1], activation_fn=None, scope='Conv2d_0a_1x1')
branch_0 = tf.layers.batch_normalization(branch_0, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_0 = tf.nn.relu(branch_0, name='{}_act'.format('Conv2d_0a_1x1'))
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net, 192, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0a_1x1'))
branch_1 = layers.conv2d(branch_1, 320, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0b_3x3'))
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net, 160, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0a_1x1'))
branch_2 = layers.conv2d(branch_2, 224, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0b_3x3'))
branch_2 = layers.conv2d(branch_2, 224, [3, 3], activation_fn=None, scope='Conv2d_0c_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0c_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0c_3x3'))
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3], padding='SAME', stride=1, scope='AvgPool_0a_3x3')
branch_3 = layers.conv2d(branch_3, 128, [1, 1], weights_initializer=trunc_normal(0.1), activation_fn=None, scope='Conv2d_0b_1x1')
branch_3 = tf.layers.batch_normalization(branch_3, training=training, name='{}_bn'.format('Conv2d_0b_1x1'))
branch_3 = tf.nn.relu(branch_3, name='{}_act'.format('Conv2d_0b_1x1'))
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
# 7 x 7 x 1024
end_point = 'Mixed_5c'
with variable_scope.variable_scope(end_point):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(net, 352, [1, 1], activation_fn=None, scope='Conv2d_0a_1x1')
branch_0 = tf.layers.batch_normalization(branch_0, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_0 = tf.nn.relu(branch_0, name='{}_act'.format('Conv2d_0a_1x1'))
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(net, 192, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0a_1x1'))
branch_1 = layers.conv2d(branch_1, 320, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_1 = tf.layers.batch_normalization(branch_1, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_1 = tf.nn.relu(branch_1, name='{}_act'.format('Conv2d_0b_3x3'))
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(net, 192, [1, 1], weights_initializer=trunc_normal(0.09), activation_fn=None, scope='Conv2d_0a_1x1')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0a_1x1'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0a_1x1'))
branch_2 = layers.conv2d(branch_2, 224, [3, 3], activation_fn=None, scope='Conv2d_0b_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0b_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0b_3x3'))
branch_2 = layers.conv2d(branch_2, 224, [3, 3], activation_fn=None, scope='Conv2d_0c_3x3')
branch_2 = tf.layers.batch_normalization(branch_2, training=training, name='{}_bn'.format('Conv2d_0c_3x3'))
branch_2 = tf.nn.relu(branch_2, name='{}_act'.format('Conv2d_0c_3x3'))
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.max_pool2d(net, [3, 3], padding='SAME', stride=1, scope='MaxPool_0a_3x3')
branch_3 = layers.conv2d(branch_3, 128, [1, 1], weights_initializer=trunc_normal(0.1), activation_fn=None, scope='Conv2d_0b_1x1')
branch_3 = tf.layers.batch_normalization(branch_3, training=training, name='{}_bn'.format('Conv2d_0b_1x1'))
branch_3 = tf.nn.relu(branch_3, name='{}_act'.format('Conv2d_0b_1x1'))
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
with variable_scope.variable_scope('Logits'):
kernel_size = util._reduced_kernel_size_for_small_input(net, [7, 7])
net = layers_lib.avg_pool2d(net, kernel_size, stride=1, padding='VALID', scope='AvgPool_1a_{}x{}'.format(*kernel_size))
# 1 x 1 x 1024
net = layers_lib.dropout(net, keep_prob=params['dropout_keep_prob'], scope='Dropout_1b')
logits = layers.conv2d(net, params['num_classes'], [1, 1], normalizer_fn=None, activation_fn=None, scope='Conv2d_1c_1x1')
if params['spatial_squeeze']:
logits = array_ops.squeeze(logits, [1, 2], name='SpatialSqueeze')
predictions = {
'argmax': tf.argmax(logits, axis=1, name='prediction_classes'),
'predictions': layers_lib.softmax(logits, scope='Predictions'),
}
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)
loss = tf.losses.sparse_softmax_cross_entropy(logits=logits, labels=labels)
tf.summary.scalar('loss', loss)
eval_metric_ops = {
'accuracy_val': tf.metrics.accuracy(labels=labels, predictions=predictions['argmax'])
}
if mode == tf.estimator.ModeKeys.EVAL:
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)
optimizer = tf.train.GradientDescentOptimizer(learning_rate=params['learning_rate'])
extra_update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(extra_update_ops):
train_op = optimizer.minimize(loss=loss, global_step=tf.train.get_global_step())
tf.summary.scalar('accuracy_train', eval_metric_ops['accuracy_val'][1])
tf.summary.histogram('labels', labels)
tf.summary.histogram('predictions', predictions['argmax'])
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)
def ldnet(inputs, num_classes=3, dropout_keep_prob=0.5, spatial_squeeze=True, scope="ldnet",
print_current_tensor=False):
"""
ldnet architecture:
input: 32*32*3
input depth kenal stride padding
conv0： net = conv(input, 32, [3, 3], 1, "same")
--> 32*32*32
conv1: net = conv(net, 32, [3, 3], 1, "same")
--> 32*32*32
conv2： net = conv(net, 64, [3, 3], 1, "same")
--> 32*32*64
maxpool1: net = pool(net, [3, 3], 1, "same")
--> 32*32*64
conv3: net = conv(net, 192, [3, 3], 1, "same")
--> 32*32*192
maxpool2: net = pool(net, [3, 3], 1, "same")
--> 32*32*192
ldnet blocks:
mixed_1: 32 x 32 x 320 Feature extraction module
mixed_2: 16 x 16 x 640 Dimension reduction module
mixed_3: 16 x 16 x 640 Feature extraction module
mixed_4: 8 x 8 x 1280 Dimension reduction module
mixed_5: 4 x 4 x 1280 Dimension reduction module
Final pooling and prediction -> 3
:param inputs: the size of imputs is [batch_num, width, height, channel].
:param num_classes: num of classes.
:param dropout_keep_prob:
:param spatial_squeeze:
:param scope:
:param print_current_tensor: whether print current tenser shape, name and type.
:return:
logits: [batch, num_classes]
"""
with variable_scope.variable_scope(scope, "ldnet", [inputs]):
with arg_scope(
[layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d],
kernel_size=[3, 3],
stride=1,
padding='SAME'):
# input: 32 * 32 * 3
net = layers.conv2d(inputs, 32, scope="conv0")
if print_current_tensor: print(net)
# --> 32 * 32 * 32
net = layers.conv2d(net, 32, scope="conv1")
if print_current_tensor: print(net)
# --> 32 * 32 * 32
net = layers.conv2d(net, 64, scope="conv2")
if print_current_tensor: print(net)
# --> 32 * 32 * 64
net = layers_lib.max_pool2d(net, kernel_size=[2, 2], scope="maxpool0")
if print_current_tensor: print(net)
# --> 32 * 32 * 64
net = layers.conv2d(net, 192, scope="conv3")
if print_current_tensor: print(net)
# --> 32 * 32 * 192
net = layers_lib.max_pool2d(net, kernel_size=[2, 2], scope="maxpool1")
if print_current_tensor: print(net)
# --> 32 * 32 * 192
# ldnet blocks
with arg_scope(
[layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d],
stride=1,
padding='SAME'):
# mixed_1: 32 x 32 x 320 Feature extraction module
with variable_scope.variable_scope("mixed_1"):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, 48, [1, 1], scope='Conv2d_0a_1x1')
branch_0 = layers.conv2d(
branch_0, 64, [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, 48, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, 64, [5, 5], scope='Conv2d_0b_5x5')
branch_1 = layers.conv2d(
branch_1, 96, [5, 5], scope='Conv2d_0c_5x5')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net, 48, [1, 1], scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, 64, [7, 7], scope='Conv2d_0b_7x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [5, 5], scope='AvgPool_0a_5x5')
branch_3 = layers.conv2d(
branch_3, 96, [1, 1], scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
if print_current_tensor: print(net)
# mixed_2: 16 x 16 x 640 Dimension reduction module
with variable_scope.variable_scope("mixed_2"):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net,
224, [3, 3],
stride=2,
scope='Conv2d_1a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, 64, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, 96, [3, 3], scope='Conv2d_0b_3x3')
branch_1 = layers.conv2d(
branch_1,
96, [3, 3],
stride=2,
scope='Conv2d_1a_1x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(
net, [3, 3], stride=2, scope='MaxPool_1a_3x3')
net = array_ops.concat([branch_0, branch_1, branch_2], 3)
if print_current_tensor: print(net)
# mixed_3: 16 x 16 x 640 Feature extraction module
with variable_scope.variable_scope("mixed_3"):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net, 96, [1, 1], scope='Conv2d_0a_1x1')
branch_0 = layers.conv2d(
branch_0, 128, [3, 3], scope='Conv2d_0b_3x3')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, 96, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, 128, [5, 5], scope='Conv2d_0b_5x5')
branch_1 = layers.conv2d(
branch_1, 192, [5, 5], scope='Conv2d_0c_5x5')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers.conv2d(
net, 96, [1, 1], scope='Conv2d_0a_1x1')
branch_2 = layers.conv2d(
branch_2, 128, [7, 7], scope='Conv2d_0b_7x7')
with variable_scope.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [5, 5], scope='AvgPool_0a_5x5')
branch_3 = layers.conv2d(
branch_3, 192, [1, 1], scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2, branch_3], 3)
if print_current_tensor: print(net)
# mixed_4: 8 x 8 x 1280 Dimension reduction module
with variable_scope.variable_scope("mixed_4"):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net,
448, [3, 3],
stride=2,
scope='Conv2d_1a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, 64, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, 96, [3, 3], scope='Conv2d_0b_3x3')
branch_1 = layers.conv2d(
branch_1,
192, [3, 3],
stride=2,
scope='Conv2d_1a_1x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(
net, [3, 3], stride=2, scope='MaxPool_1a_3x3')
net = array_ops.concat([branch_0, branch_1, branch_2], 3)
if print_current_tensor: print(net)
# mixed_5: 4 x 4 x 1280 Dimension reduction module
with variable_scope.variable_scope("mixed_5"):
with variable_scope.variable_scope('Branch_0'):
branch_0 = layers.conv2d(
net,
448, [3, 3],
stride=2,
scope='Conv2d_1a_1x1')
with variable_scope.variable_scope('Branch_1'):
branch_1 = layers.conv2d(
net, 64, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = layers.conv2d(
branch_1, 96, [3, 3], scope='Conv2d_0b_3x3')
branch_1 = layers.conv2d(
branch_1,
192, [3, 3],
stride=2,
scope='Conv2d_1a_1x1')
with variable_scope.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(
net, [3, 3], stride=2, scope='MaxPool_1a_3x3')
branch_2 = layers.conv2d(
branch_2, 640, [1, 1], scope='Conv2d_0b_1x1')
net = array_ops.concat([branch_0, branch_1, branch_2], 3)
if print_current_tensor: print(net)
# Final pooling and prediction
with variable_scope.variable_scope('Logits'):
net = layers_lib.avg_pool2d(
net,
[4, 4],
padding='VALID',
scope='AvgPool_1a_4x4')
# 1 x 1 x 1280
# net = layers.conv2d(net, 640, [1, 1], scope='Conv2d_0b_1x1')
# local1
with variable_scope.variable_scope('local1') as scope:
# Move everything into depth so we can perform a single matrix multiply.
reshape = tf.reshape(net, [-1, 1280])
weights = _variable_with_weight_decay('weights', shape=[1280, 640],
stddev=0.04, wd=0.0001)
biases = _variable_on_cpu('biases', [640], tf.constant_initializer(0.1))
net = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)
# 1 x 1 x 640
net = layers_lib.dropout(net, keep_prob=dropout_keep_prob, scope='Dropout_0c')
# net = layers.conv2d(net, 320, [1, 1], scope='Conv2d_0d_1x1')
# local2
with variable_scope.variable_scope('local2') as scope:
weights = _variable_with_weight_decay('weights', shape=[640, 320],
stddev=0.04, wd=0.0001)
biases = _variable_on_cpu('biases', [320], tf.constant_initializer(0.1))
net = tf.nn.relu(tf.matmul(net, weights) + biases, name=scope.name)
# 1 x 1 x 320
net = layers_lib.dropout(net, keep_prob=dropout_keep_prob, scope='Dropout_0e')
net = tf.expand_dims(net, 1)
net = tf.expand_dims(net, 1)
logits = layers.conv2d(
net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='Conv2d_0f_1x1')
# 1 x 1 x 3
if spatial_squeeze:
logits = array_ops.squeeze(logits, [1, 2], name='SpatialSqueeze')
# 3
return logits
def inception_v3(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.8,
min_depth=16,
depth_multiplier=1.0,
prediction_fn=layers_lib.softmax,
spatial_squeeze=True,
reuse=None,
scope='InceptionV3'):
"""Inception model from http://arxiv.org/abs/1512.00567.
"Rethinking the Inception Architecture for Computer Vision"
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens,
Zbigniew Wojna.
With the default arguments this method constructs the exact model defined in
the paper. However, one can experiment with variations of the inception_v3
network by changing arguments dropout_keep_prob, min_depth and
depth_multiplier.
The default image size used to train this network is 299x299.
Args:
inputs: a tensor of size [batch_size, height, width, channels].
num_classes: number of predicted classes.
is_training: whether is training or not.
dropout_keep_prob: the percentage of activation values that are retained.
min_depth: Minimum depth value (number of channels) for all convolution ops.
Enforced when depth_multiplier < 1, and not an active constraint when
depth_multiplier >= 1.
depth_multiplier: Float multiplier for the depth (number of channels)
for all convolution ops. The value must be greater than zero. Typical
usage will be to set this value in (0, 1) to reduce the number of
parameters or computation cost of the model.
prediction_fn: a function to get predictions out of logits.
spatial_squeeze: if True, logits is of shape is [B, C], if false logits is
of shape [B, 1, 1, C], where B is batch_size and C is number of classes.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
scope: Optional variable_scope.
Returns:
logits: the pre-softmax activations, a tensor of size
[batch_size, num_classes]
end_points: a dictionary from components of the network to the corresponding
activation.
Raises:
ValueError: if 'depth_multiplier' is less than or equal to zero.
"""
if depth_multiplier <= 0:
raise ValueError('depth_multiplier is not greater than zero.')
depth = lambda d: max(int(d * depth_multiplier), min_depth)
with variable_scope.variable_scope(scope,
'InceptionV3', [inputs, num_classes],
reuse=reuse) as scope:
with arg_scope([layers_lib.batch_norm, layers_lib.dropout],
is_training=is_training):
net, end_points = inception_v3_base(
inputs,
scope=scope,
min_depth=min_depth,
depth_multiplier=depth_multiplier)
# Auxiliary Head logits
with arg_scope(
[layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d],
stride=1,
padding='SAME'):
aux_logits = end_points['Mixed_6e']
with variable_scope.variable_scope('AuxLogits'):
aux_logits = layers_lib.avg_pool2d(aux_logits, [5, 5],
stride=3,
padding='VALID',
scope='AvgPool_1a_5x5')
aux_logits = layers.conv2d(aux_logits,
depth(128), [1, 1],
scope='Conv2d_1b_1x1')
# Shape of feature map before the final layer.
kernel_size = _reduced_kernel_size_for_small_input(
aux_logits, [5, 5])
aux_logits = layers.conv2d(
aux_logits,
depth(768),
kernel_size,
weights_initializer=trunc_normal(0.01),
padding='VALID',
scope='Conv2d_2a_{}x{}'.format(*kernel_size))
aux_logits = layers.conv2d(
aux_logits,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
weights_initializer=trunc_normal(0.001),
scope='Conv2d_2b_1x1')
if spatial_squeeze:
aux_logits = array_ops.squeeze(aux_logits, [1, 2],
name='SpatialSqueeze')
end_points['AuxLogits'] = aux_logits
# Final pooling and prediction
with variable_scope.variable_scope('Logits'):
kernel_size = _reduced_kernel_size_for_small_input(net, [8, 8])
net = layers_lib.avg_pool2d(
net,
kernel_size,
padding='VALID',
scope='AvgPool_1a_{}x{}'.format(*kernel_size))
# 1 x 1 x 2048
net = layers_lib.dropout(net,
keep_prob=dropout_keep_prob,
scope='Dropout_1b')
end_points['PreLogits'] = net
# 2048
logits = layers.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='Conv2d_1c_1x1')
if spatial_squeeze:
logits = array_ops.squeeze(logits, [1, 2],
name='SpatialSqueeze')
# 1000
end_points['Logits'] = logits
end_points['Predictions'] = prediction_fn(logits,
scope='Predictions')
return logits, end_points
def ops(self, input, scope=None, reuse=False):
self.scope = scope
sipconv2d = SIP_Conv2d()
sipconv2d.set_default(is_training=self.is_training)
if self.depth_multiplier <= 0:
raise ValueError('depth_multiplier is not greater than zero.')
depth = lambda d: max(int(d * self.depth_multiplier), self.min_depth)
with tf.variable_scope(scope, "Inception_v3", reuse=reuse):
sipconv2d.set_default(stride=1, padding="VALID")
#---------------------------------------
end_point = "Conv2d_p1_3x3"
# ---- ops
net = sipconv2d.ops(input,
depth(32), [3, 3],
stride=2,
scope=end_point)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Conv2d_p2_3x3"
# ---- ops
net = sipconv2d.ops(net, depth(32), [3, 3], scope=end_point)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Conv2d_p3_3x3"
# ---- ops
net = sipconv2d.ops(net,
depth(64), [3, 3],
padding="SAME",
scope=end_point)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "MaxPool_p4_3x3"
# ---- ops
net = layers_lib.max_pool2d(net, [3, 3], stride=2, scope=end_point)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Conv2d_p5_1x1"
# ---- ops
net = sipconv2d.ops(net, depth(80), [1, 1], scope=end_point)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Conv2d_p6_3x3"
# ---- ops
net = sipconv2d.ops(net, depth(192), [3, 3], scope=end_point)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "MaxPool_p7_3x3"
# ---- ops
net = layers_lib.max_pool2d(net, [3, 3], stride=2, scope=end_point)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Mixed_p8_a"
# ---- ops
sipconv2d.set_default(padding="SAME", stride=1)
with tf.variable_scope(end_point):
with tf.variable_scope('Branch_0'):
branch_0 = sipconv2d.ops(net,
depth(64), [1, 1],
scope="a_conv2d")
with tf.variable_scope('Branch_1'):
branch_1 = sipconv2d.ops(net,
depth(48), [1, 1],
scope="b_conv2d_1")
branch_1 = sipconv2d.ops(branch_1,
depth(64), [5, 5],
scope='b_conv2d_2')
with tf.variable_scope('Branch_2'):
branch_2 = sipconv2d.ops(net,
depth(64), [1, 1],
scope="c_conv2d_1")
branch_2 = sipconv2d.ops(branch_2,
depth(96), [3, 3],
scope="c_conv2d_2")
branch_2 = sipconv2d.ops(branch_2,
depth(96), [3, 3],
scope="c_conv2d_3")
with tf.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
stride=1,
padding="SAME",
scope='d_AvgPool')
branch_3 = sipconv2d.ops(branch_3,
depth(32), [1, 1],
scope='d_conv2d')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Mixed_p8_b"
# ---- ops
with tf.variable_scope(end_point):
with tf.variable_scope('Branch_0'):
branch_0 = sipconv2d.ops(net,
depth(64), [1, 1],
scope="a_conv2d")
with tf.variable_scope('Branch_1'):
branch_1 = sipconv2d.ops(net,
depth(48), [1, 1],
scope="b_conv2d_1")
branch_1 = sipconv2d.ops(branch_1,
depth(64), [5, 5],
scope='b_conv2d_2')
with tf.variable_scope('Branch_2'):
branch_2 = sipconv2d.ops(net,
depth(64), [1, 1],
scope="c_conv2d_1")
branch_2 = sipconv2d.ops(branch_2,
depth(96), [3, 3],
scope="c_conv2d_2")
branch_2 = sipconv2d.ops(branch_2,
depth(96), [3, 3],
scope="c_conv2d_3")
with tf.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
stride=1,
padding="SAME",
scope='d_AvgPool')
branch_3 = sipconv2d.ops(branch_3,
depth(64), [1, 1],
scope='d_conv2d')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Mixed_p8_c"
# ---- ops
with tf.variable_scope(end_point):
with tf.variable_scope('Branch_0'):
branch_0 = sipconv2d.ops(net,
depth(64), [1, 1],
scope="a_conv2d")
with tf.variable_scope('Branch_1'):
branch_1 = sipconv2d.ops(net,
depth(48), [1, 1],
scope="b_conv2d_1")
branch_1 = sipconv2d.ops(branch_1,
depth(64), [5, 5],
scope='b_conv2d_2')
with tf.variable_scope('Branch_2'):
branch_2 = sipconv2d.ops(net,
depth(64), [1, 1],
scope="c_conv2d_1")
branch_2 = sipconv2d.ops(branch_2,
depth(96), [3, 3],
scope="c_conv2d_2")
branch_2 = sipconv2d.ops(branch_2,
depth(96), [3, 3],
scope="c_conv2d_3")
with tf.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
stride=1,
padding="SAME",
scope='d_AvgPool')
branch_3 = sipconv2d.ops(branch_3,
depth(64), [1, 1],
scope='d_conv2d')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Mixed_p9_a"
# ---- ops
with tf.variable_scope(end_point):
with tf.variable_scope('Branch_0'):
branch_0 = sipconv2d.ops(net,
depth(384), [3, 3],
stride=2,
padding="VALID",
scope="a_conv2d")
with tf.variable_scope('Branch_1'):
branch_1 = sipconv2d.ops(net,
depth(64), [1, 1],
scope="b_conv2d_1")
branch_1 = sipconv2d.ops(branch_1,
depth(96), [3, 3],
scope='b_conv2d_2')
branch_1 = sipconv2d.ops(branch_1,
depth(96), [3, 3],
stride=2,
padding="VALID",
scope='b_conv2d_3')
with tf.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(net, [3, 3],
stride=2,
padding="VALID",
scope="c_Max_Pool")
net = tf.concat([branch_0, branch_1, branch_2], 3)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Mixed_p9_b"
# ---- ops
with tf.variable_scope(end_point):
with tf.variable_scope('Branch_0'):
branch_0 = sipconv2d.ops(net,
depth(192), [1, 1],
scope="a_conv2d")
with tf.variable_scope('Branch_1'):
branch_1 = sipconv2d.ops(net,
depth(128), [1, 1],
scope="b_conv2d_1")
branch_1 = sipconv2d.ops(branch_1,
depth(128), [1, 7],
scope='b_conv2d_2')
branch_1 = sipconv2d.ops(branch_1,
depth(192), [7, 1],
scope='b_conv2d_3')
with tf.variable_scope('Branch_2'):
branch_2 = sipconv2d.ops(net,
depth(128), [1, 1],
scope="c_conv2d_1")
branch_2 = sipconv2d.ops(branch_2,
depth(128), [7, 1],
scope="c_conv2d_2")
branch_2 = sipconv2d.ops(branch_2,
depth(128), [1, 7],
scope="c_conv2d_3")
branch_2 = sipconv2d.ops(branch_2,
depth(128), [7, 1],
scope="c_conv2d_4")
branch_2 = sipconv2d.ops(branch_2,
depth(192), [1, 7],
scope="c_conv2d_5")
with tf.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
stride=1,
padding="SAME",
scope='d_AvgPool')
branch_3 = sipconv2d.ops(branch_3,
depth(192), [1, 1],
scope='d_conv2d')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Mixed_p9_c"
# ---- ops
with tf.variable_scope(end_point):
with tf.variable_scope('Branch_0'):
branch_0 = sipconv2d.ops(net,
depth(192), [1, 1],
scope="a_conv2d")
with tf.variable_scope('Branch_1'):
branch_1 = sipconv2d.ops(net,
depth(160), [1, 1],
scope="b_conv2d_1")
branch_1 = sipconv2d.ops(branch_1,
depth(160), [1, 7],
scope='b_conv2d_2')
branch_1 = sipconv2d.ops(branch_1,
depth(192), [7, 1],
scope='b_conv2d_3')
with tf.variable_scope('Branch_2'):
branch_2 = sipconv2d.ops(net,
depth(160), [1, 1],
scope="c_conv2d_1")
branch_2 = sipconv2d.ops(branch_2,
depth(160), [7, 1],
scope="c_conv2d_2")
branch_2 = sipconv2d.ops(branch_2,
depth(160), [1, 7],
scope="c_conv2d_3")
branch_2 = sipconv2d.ops(branch_2,
depth(160), [7, 1],
scope="c_conv2d_4")
branch_2 = sipconv2d.ops(branch_2,
depth(192), [1, 7],
scope="c_conv2d_5")
with tf.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
stride=1,
padding="SAME",
scope='d_AvgPool')
branch_3 = sipconv2d.ops(branch_3,
depth(192), [1, 1],
scope='d_conv2d')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Mixed_p9_d"
# ---- ops
with tf.variable_scope(end_point):
with tf.variable_scope('Branch_0'):
branch_0 = sipconv2d.ops(net,
depth(192), [1, 1],
scope="a_conv2d")
with tf.variable_scope('Branch_1'):
branch_1 = sipconv2d.ops(net,
depth(160), [1, 1],
scope="b_conv2d_1")
branch_1 = sipconv2d.ops(branch_1,
depth(160), [1, 7],
scope='b_conv2d_2')
branch_1 = sipconv2d.ops(branch_1,
depth(192), [7, 1],
scope='b_conv2d_3')
with tf.variable_scope('Branch_2'):
branch_2 = sipconv2d.ops(net,
depth(160), [1, 1],
scope="c_conv2d_1")
branch_2 = sipconv2d.ops(branch_2,
depth(160), [7, 1],
scope="c_conv2d_2")
branch_2 = sipconv2d.ops(branch_2,
depth(160), [1, 7],
scope="c_conv2d_3")
branch_2 = sipconv2d.ops(branch_2,
depth(160), [7, 1],
scope="c_conv2d_4")
branch_2 = sipconv2d.ops(branch_2,
depth(192), [1, 7],
scope="c_conv2d_5")
with tf.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
stride=1,
padding="SAME",
scope='d_AvgPool')
branch_3 = sipconv2d.ops(branch_3,
depth(192), [1, 1],
scope='d_conv2d')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Mixed_p9_e"
# ---- ops
with tf.variable_scope(end_point):
with tf.variable_scope('Branch_0'):
branch_0 = sipconv2d.ops(net,
depth(192), [1, 1],
scope="a_conv2d")
with tf.variable_scope('Branch_1'):
branch_1 = sipconv2d.ops(net,
depth(192), [1, 1],
scope="b_conv2d_1")
branch_1 = sipconv2d.ops(branch_1,
depth(192), [1, 7],
scope='b_conv2d_2')
branch_1 = sipconv2d.ops(branch_1,
depth(192), [7, 1],
scope='b_conv2d_3')
with tf.variable_scope('Branch_2'):
branch_2 = sipconv2d.ops(net,
depth(192), [1, 1],
scope="c_conv2d_1")
branch_2 = sipconv2d.ops(branch_2,
depth(192), [7, 1],
scope="c_conv2d_2")
branch_2 = sipconv2d.ops(branch_2,
depth(192), [1, 7],
scope="c_conv2d_3")
branch_2 = sipconv2d.ops(branch_2,
depth(192), [7, 1],
scope="c_conv2d_4")
branch_2 = sipconv2d.ops(branch_2,
depth(192), [1, 7],
scope="c_conv2d_5")
with tf.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
stride=1,
padding="SAME",
scope='d_AvgPool')
branch_3 = sipconv2d.ops(branch_3,
depth(192), [1, 1],
scope='d_conv2d')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Mixed_p10_a"
# ---- ops
with tf.variable_scope(end_point):
with tf.variable_scope('Branch_0'):
branch_0 = sipconv2d.ops(net,
depth(192), [1, 1],
scope="a_conv2d_1")
branch_0 = sipconv2d.ops(branch_0,
depth(320), [3, 3],
stride=2,
padding="VALID",
scope="a_conv2d_2")
with tf.variable_scope('Branch_1'):
branch_1 = sipconv2d.ops(net,
depth(192), [1, 1],
scope="b_conv2d_1")
branch_1 = sipconv2d.ops(branch_1,
depth(192), [1, 7],
scope='b_conv2d_2')
branch_1 = sipconv2d.ops(branch_1,
depth(192), [7, 1],
scope='b_conv2d_3')
branch_1 = sipconv2d.ops(branch_1,
depth(192), [3, 3],
stride=2,
padding="VALID",
scope='b_conv2d_4')
with tf.variable_scope('Branch_2'):
branch_2 = layers_lib.max_pool2d(net, [3, 3],
stride=2,
padding="VALID",
scope="c_Max_Pool")
net = tf.concat([branch_0, branch_1, branch_2], 3)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Mixed_p10_b"
# ---- ops
with tf.variable_scope(end_point):
with tf.variable_scope('Branch_0'):
branch_0 = sipconv2d.ops(net,
depth(320), [1, 1],
scope="a_conv2d")
with tf.variable_scope('Branch_1'):
branch_1 = sipconv2d.ops(net,
depth(384), [1, 1],
scope="b_conv2d_1")
branch_1 = tf.concat([
sipconv2d.ops(
branch_1, depth(384), [1, 3], scope='b_conv2d_2'),
sipconv2d.ops(
branch_1, depth(384), [3, 1], scope='b_conv2d_3')
], 3)
with tf.variable_scope('Branch_2'):
branch_2 = sipconv2d.ops(net,
depth(448), [1, 1],
scope="c_conv2d_1")
branch_2 = sipconv2d.ops(branch_2,
depth(384), [3, 3],
scope="c_conv2d_2")
branch_2 = tf.concat([
sipconv2d.ops(
branch_2, depth(384), [1, 3], scope='c_conv2d_3'),
sipconv2d.ops(
branch_2, depth(384), [3, 1], scope='c_conv2d_4')
], 3)
with tf.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
stride=1,
padding="SAME",
scope='d_AvgPool')
branch_3 = sipconv2d.ops(branch_3,
depth(192), [1, 1],
scope='d_conv2d')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
# ---------------------------------------
end_point = "Mixed_p10_c"
# ---- ops
with tf.variable_scope(end_point):
with tf.variable_scope('Branch_0'):
branch_0 = sipconv2d.ops(net,
depth(320), [1, 1],
scope="a_conv2d")
with tf.variable_scope('Branch_1'):
branch_1 = sipconv2d.ops(net,
depth(384), [1, 1],
scope="b_conv2d_1")
branch_1 = tf.concat([
sipconv2d.ops(
branch_1, depth(384), [1, 3], scope='b_conv2d_2'),
sipconv2d.ops(
branch_1, depth(384), [3, 1], scope='b_conv2d_3')
], 3)
with tf.variable_scope('Branch_2'):
branch_2 = sipconv2d.ops(net,
depth(448), [1, 1],
scope="c_conv2d_1")
branch_2 = sipconv2d.ops(branch_2,
depth(384), [3, 3],
scope="c_conv2d_2")
branch_2 = tf.concat([
sipconv2d.ops(
branch_2, depth(384), [1, 3], scope='c_conv2d_3'),
sipconv2d.ops(
branch_2, depth(384), [3, 1], scope='c_conv2d_4')
], 3)
with tf.variable_scope('Branch_3'):
branch_3 = layers_lib.avg_pool2d(net, [3, 3],
stride=1,
padding="SAME",
scope='d_AvgPool')
branch_3 = sipconv2d.ops(branch_3,
depth(192), [1, 1],
scope='d_conv2d')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# ----
self.key_point[end_point] = net
if end_point == self.final_endpoint:
self.get_variables()
return net
