def lenet(images, num_classes=10, is_training=False,
dropout_keep_prob=0.5,
prediction_fn=slim.softmax,
scope='LeNet'):
"""Creates a variant of the LeNet model.
Note that since the output is a set of 'logits', the values fall in the
interval of (-infinity, infinity). Consequently, to convert the outputs to a
probability distribution over the characters, one will need to convert them
using the softmax function:
logits = lenet.lenet(images, is_training=False)
probabilities = tf.nn.softmax(logits)
predictions = tf.argmax(logits, 1)
Args:
images: A batch of `Tensors` of size [batch_size, height, width, channels].
num_classes: the number of classes in the dataset. If 0 or None, the logits
layer is omitted and the input features to the logits layer are returned
instead.
is_training: specifies whether or not we're currently training the model.
This variable will determine the behaviour of the dropout layer.
dropout_keep_prob: the percentage of activation values that are retained.
prediction_fn: a function to get predictions out of logits.
scope: Optional variable_scope.
Returns:
net: a 2D Tensor with the logits (pre-softmax activations) if num_classes
is a non-zero integer, or the inon-dropped-out nput to the logits layer
if num_classes is 0 or None.
end_points: a dictionary from components of the network to the corresponding
activation.
"""
end_points = {}
with tf.variable_scope(scope, 'LeNet', [images]):
net = end_points['conv1'] = slim.conv2d(images, 32, [5, 5], scope='conv1')
net = end_points['pool1'] = slim.max_pool2d(net, [2, 2], 2, scope='pool1')
net = end_points['conv2'] = slim.conv2d(net, 64, [5, 5], scope='conv2')
net = end_points['pool2'] = slim.max_pool2d(net, [2, 2], 2, scope='pool2')
net = slim.flatten(net)
end_points['Flatten'] = net
net = end_points['fc3'] = slim.fully_connected(net, 1024, scope='fc3')
if not num_classes:
return net, end_points
net = end_points['dropout3'] = slim.dropout(
net, dropout_keep_prob, is_training=is_training, scope='dropout3')
logits = end_points['Logits'] = slim.fully_connected(
net, num_classes, activation_fn=None, scope='fc4')
end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
return logits, end_points
def create_network(self):
# feature extractor - convolutions
net = slim.convolution(self.input_tensor, 96, [7, 7], 2, padding='VALID', scope='conv1',
activation_fn=tf.nn.relu)
net = tf.nn.lrn(net, depth_radius=5, bias=2, alpha=1e-4*5, beta=0.75)
net = slim.pool(net, [3, 3], 'MAX', stride=2, padding='VALID', scope='pool1')
# net = self.Squeeze_excitation_layer(net, 96, 4, layer_name = 'SE_1')
net = slim.convolution(net, 256, [5, 5], 2, padding='VALID', scope='conv2',
activation_fn=tf.nn.relu)
net = tf.nn.lrn(net, depth_radius=5, bias=2, alpha=1e-4*5, beta=0.75)
net = slim.pool(net, [3, 3], 'MAX', stride=2, padding='VALID', scope='pool2')
# net = self.Squeeze_excitation_layer(net, 256, 4, layer_name = 'SE_2')
net = slim.convolution(net, 512, [3, 3], 1, padding='VALID', scope='conv3',
activation_fn=tf.nn.relu)
# net = self.Squeeze_excitation_layer(net, 512, 4, layer_name = 'SE_3')
self.layer_feat = net
# fc layers
net = slim.convolution(net, 512, [3, 3], 1, padding='VALID', scope='fc4',
activation_fn=tf.nn.relu)
# net = self.Squeeze_excitation_layer(net, 512, 4, layer_name = 'SE_4')
net = slim.dropout(net, keep_prob=0.5, is_training=self.is_training, scope='dropout')
net = tf.concat([net, self.action_history_tensor], axis=-1)
net = slim.convolution(net, 512, [1, 1], 1, padding='VALID', scope='fc5',
activation_fn=tf.nn.relu)
net = slim.dropout(net, keep_prob=0.5, is_training=self.is_training, scope='dropout_x16')
# auxilaries
out_actions = slim.convolution(net, 11, [1, 1], 1, padding='VALID', scope='fc6_1', activation_fn=None)
out_scores = slim.convolution(net, 2, [1, 1], 1, padding='VALID', scope='fc6_2', activation_fn=None)
self.out_actions = flatten_convolution(out_actions)
self.out_scores = flatten_convolution(out_scores)
self.layer_actions = tf.nn.softmax(out_actions)
self.layer_scores = tf.nn.softmax(out_scores)
def BNLF(inputs, is_training=True, scope='deep_regression', n_frames=5):
with tf.variable_scope(scope, 'deep_regression', [inputs]):
end_points = {}
with slim.arg_scope([slim.fully_connected],
activation_fn=tf.nn.leaky_relu,
weights_regularizer=slim.l1_regularizer(2e-6)):
# Use frame indices later in network.
input2 = inputs[:,-n_frames:]
net = slim.fully_connected(inputs, 256, scope='fc1')
end_points['fc1'] = net
net = slim.dropout(net, 0.8, is_training=is_training)
net = tf.concat((net,input2),axis=1)
net = slim.fully_connected(net, 128, scope='fc2')
end_points['fc2'] = net
net = slim.dropout(net, 0.8, is_training=is_training)
net = tf.concat((net,input2),axis=1)
net = slim.fully_connected(net, 64, scope='fc3')
end_points['fc3'] = net
net = slim.dropout(net, 0.8, is_training=is_training)
net = tf.concat((net,input2),axis=1)
net = slim.fully_connected(net, 32, scope='fc4')
end_points['fc4'] = net
predictions = slim.fully_connected(net, 1, activation_fn=None,
scope='prediction', normalizer_fn=None)
end_points['out'] = predictions
return predictions, end_points
def mobilenet_v1(inputs,
num_classes=1000,
dropout_keep_prob=0.999,
is_training=True,
min_depth=8,
depth_multiplier=1.0,
conv_defs=None,
prediction_fn=tf.contrib.layers.softmax,
spatial_squeeze=True,
reuse=None,
scope='MobilenetV1',
global_pool=False):
"""Mobilenet v1 model for classification.
Args:
inputs: a tensor of shape [batch_size, height, width, channels].
num_classes: number of predicted classes. If 0 or None, the logits layer
is omitted and the input features to the logits layer (before dropout)
are returned instead.
dropout_keep_prob: the percentage of activation values that are retained.
is_training: whether is training or not.
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.
conv_defs: A list of ConvDef namedtuples specifying the net architecture.
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.
global_pool: Optional boolean flag to control the avgpooling before the
logits layer. If false or unset, pooling is done with a fixed window
that reduces default-sized inputs to 1x1, while larger inputs lead to
larger outputs. If true, any input size is pooled down to 1x1.
Returns:
net: a 2D Tensor with the logits (pre-softmax activations) if num_classes
is a non-zero integer, or the non-dropped-out input to the logits layer
if num_classes is 0 or None.
end_points: a dictionary from components of the network to the corresponding
activation.
Raises:
ValueError: Input rank is invalid.
"""
input_shape = inputs.get_shape().as_list()
if len(input_shape) != 4:
raise ValueError('Invalid input tensor rank, expected 4, was: %d' %
len(input_shape))
with tf.variable_scope(scope, 'MobilenetV1', [inputs],
reuse=reuse) as scope:
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
net, end_points = mobilenet_v1_base(
inputs,
scope=scope,
min_depth=min_depth,
depth_multiplier=depth_multiplier,
conv_defs=conv_defs)
with tf.variable_scope('Logits'):
if global_pool:
# Global average pooling.
net = tf.reduce_mean(net, [1, 2],
keep_dims=True,
name='global_pool')
end_points['global_pool'] = net
else:
# Pooling with a fixed kernel size.
kernel_size = _reduced_kernel_size_for_small_input(
net, [7, 7])
net = slim.avg_pool2d(net,
kernel_size,
padding='VALID',
scope='AvgPool_1a')
end_points['AvgPool_1a'] = net
if not num_classes:
return net, end_points
# 1 x 1 x 1024
net = slim.dropout(net,
keep_prob=dropout_keep_prob,
scope='Dropout_1b')
logits = slim.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='Conv2d_1c_1x1')
if spatial_squeeze:
logits = tf.squeeze(logits, [1, 2], name='SpatialSqueeze')
end_points['Logits'] = logits
if prediction_fn:
end_points['Predictions'] = prediction_fn(logits,
scope='Predictions')
return logits, end_points
def alexnet_v2(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.5,
spatial_squeeze=True,
scope='alexnet_v2',
global_pool=False):
"""AlexNet version 2.
Described in: http://arxiv.org/pdf/1404.5997v2.pdf
Parameters from:
github.com/akrizhevsky/cuda-convnet2/blob/master/layers/
layers-imagenet-1gpu.cfg
Note: All the fully_connected layers have been transformed to conv2d layers.
To use in classification mode, resize input to 224x224 or set
global_pool=True. To use in fully convolutional mode, set
spatial_squeeze to false.
The LRN layers have been removed and change the initializers from
random_normal_initializer to xavier_initializer.
Args:
inputs: a tensor of size [batch_size, height, width, channels].
num_classes: the number of predicted classes. If 0 or None, the logits layer
is omitted and the input features to the logits layer are returned instead.
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
logits. Useful to remove unnecessary dimensions for classification.
scope: Optional scope for the variables.
global_pool: Optional boolean flag. If True, the input to the classification
layer is avgpooled to size 1x1, for any input size. (This is not part
of the original AlexNet.)
Returns:
net: the output of the logits layer (if num_classes is a non-zero integer),
or the non-dropped-out input to the logits layer (if num_classes is 0
or None).
end_points: a dict of tensors with intermediate activations.
"""
with tf.variable_scope(scope, 'alexnet_v2', [inputs]) as sc:
end_points_collection = sc.original_name_scope + '_end_points'
# Collect outputs for conv2d, fully_connected and max_pool2d.
with slim.arg_scope([slim.conv2d, slim.fully_connected, slim.max_pool2d],
outputs_collections=[end_points_collection]):
net = slim.conv2d(inputs, 64, [11, 11], 4, padding='VALID',
scope='conv1')
net = slim.max_pool2d(net, [3, 3], 2, scope='pool1')
net = slim.conv2d(net, 192, [5, 5], scope='conv2')
net = slim.max_pool2d(net, [3, 3], 2, scope='pool2')
net = slim.conv2d(net, 384, [3, 3], scope='conv3')
net = slim.conv2d(net, 384, [3, 3], scope='conv4')
net = slim.conv2d(net, 256, [3, 3], scope='conv5')
net = slim.max_pool2d(net, [3, 3], 2, scope='pool5')
# Use conv2d instead of fully_connected layers.
with slim.arg_scope([slim.conv2d],
weights_initializer=trunc_normal(0.005),
biases_initializer=tf.constant_initializer(0.1)):
net = slim.conv2d(net, 4096, [5, 5], padding='VALID',
scope='fc6')
net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
scope='dropout6')
net = slim.conv2d(net, 4096, [1, 1], scope='fc7')
# Convert end_points_collection into a end_point dict.
end_points = slim.utils.convert_collection_to_dict(
end_points_collection)
if global_pool:
net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool')
end_points['global_pool'] = net
if num_classes:
net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
scope='dropout7')
net = slim.conv2d(net, num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
biases_initializer=tf.zeros_initializer(),
scope='fc8')
if spatial_squeeze:
net = tf.squeeze(net, [1, 2], name='fc8/squeezed')
end_points[sc.name + '/fc8'] = net
return net, end_points
def inception_v2(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.8,
min_depth=16,
depth_multiplier=1.0,
prediction_fn=slim.softmax,
spatial_squeeze=True,
reuse=None,
scope='InceptionV2',
global_pool=False):
"""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. If 0 or None, the logits layer
is omitted and the input features to the logits layer (before dropout)
are returned instead.
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.
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.
global_pool: Optional boolean flag to control the avgpooling before the
logits layer. If false or unset, pooling is done with a fixed window
that reduces default-sized inputs to 1x1, while larger inputs lead to
larger outputs. If true, any input size is pooled down to 1x1.
Returns:
net: a Tensor with the logits (pre-softmax activations) if num_classes
is a non-zero integer, or the non-dropped-out input to the logits layer
if num_classes is 0 or None.
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 tf.variable_scope(scope, 'InceptionV2', [inputs], reuse=reuse) as scope:
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
net, end_points = inception_v2_base(
inputs, scope=scope, min_depth=min_depth,
depth_multiplier=depth_multiplier)
with tf.variable_scope('Logits'):
if global_pool:
# Global average pooling.
net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool')
end_points['global_pool'] = net
else:
# Pooling with a fixed kernel size.
kernel_size = _reduced_kernel_size_for_small_input(net, [7, 7])
net = slim.avg_pool2d(net, kernel_size, padding='VALID',
scope='AvgPool_1a_{}x{}'.format(*kernel_size))
end_points['AvgPool_1a'] = net
if not num_classes:
return net, end_points
# 1 x 1 x 1024
net = slim.dropout(net, keep_prob=dropout_keep_prob, scope='Dropout_1b')
logits = slim.conv2d(net, num_classes, [1, 1], activation_fn=None,
normalizer_fn=None, scope='Conv2d_1c_1x1')
if spatial_squeeze:
logits = tf.squeeze(logits, [1, 2], name='SpatialSqueeze')
end_points['Logits'] = logits
end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
return logits, end_points
def vgg_a(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.5,
spatial_squeeze=True,
scope='vgg_a',
fc_conv_padding='VALID',
global_pool=False):
"""Oxford Net VGG 11-Layers version A 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. If 0 or None, the logits layer is
omitted and the input features to the logits layer are returned instead.
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.
fc_conv_padding: the type of padding to use for the fully connected layer
that is implemented as a convolutional layer. Use 'SAME' padding if you
are applying the network in a fully convolutional manner and want to
get a prediction map downsampled by a factor of 32 as an output.
Otherwise, the output prediction map will be (input / 32) - 6 in case of
'VALID' padding.
global_pool: Optional boolean flag. If True, the input to the classification
layer is avgpooled to size 1x1, for any input size. (This is not part
of the original VGG architecture.)
Returns:
net: the output of the logits layer (if num_classes is a non-zero integer),
or the input to the logits layer (if num_classes is 0 or None).
end_points: a dict of tensors with intermediate activations.
"""
with tf.variable_scope(scope, 'vgg_a', [inputs]) as sc:
end_points_collection = sc.original_name_scope + '_end_points'
# Collect outputs for conv2d, fully_connected and max_pool2d.
with slim.arg_scope([slim.conv2d, slim.max_pool2d],
outputs_collections=end_points_collection):
net = slim.repeat(inputs,
1,
slim.conv2d,
64, [3, 3],
scope='conv1')
net = slim.max_pool2d(net, [2, 2], scope='pool1')
net = slim.repeat(net, 1, slim.conv2d, 128, [3, 3], scope='conv2')
net = slim.max_pool2d(net, [2, 2], scope='pool2')
net = slim.repeat(net, 2, slim.conv2d, 256, [3, 3], scope='conv3')
net = slim.max_pool2d(net, [2, 2], scope='pool3')
net = slim.repeat(net, 2, slim.conv2d, 512, [3, 3], scope='conv4')
net = slim.max_pool2d(net, [2, 2], scope='pool4')
net = slim.repeat(net, 2, slim.conv2d, 512, [3, 3], scope='conv5')
net = slim.max_pool2d(net, [2, 2], scope='pool5')
# Use conv2d instead of fully_connected layers.
net = slim.conv2d(net,
4096, [7, 7],
padding=fc_conv_padding,
scope='fc6')
net = slim.dropout(net,
dropout_keep_prob,
is_training=is_training,
scope='dropout6')
net = slim.conv2d(net, 4096, [1, 1], scope='fc7')
# Convert end_points_collection into a end_point dict.
end_points = slim.utils.convert_collection_to_dict(
end_points_collection)
if global_pool:
net = tf.reduce_mean(net, [1, 2],
keep_dims=True,
name='global_pool')
end_points['global_pool'] = net
if num_classes:
net = slim.dropout(net,
dropout_keep_prob,
is_training=is_training,
scope='dropout7')
net = slim.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='fc8')
if spatial_squeeze:
net = tf.squeeze(net, [1, 2], name='fc8/squeezed')
end_points[sc.name + '/fc8'] = net
return net, 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=slim.softmax,
spatial_squeeze=True,
reuse=None,
create_aux_logits=True,
scope='InceptionV3',
global_pool=False):
"""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. If 0 or None, the logits layer
is omitted and the input features to the logits layer (before dropout)
are returned instead.
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.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
create_aux_logits: Whether to create the auxiliary logits.
scope: Optional variable_scope.
global_pool: Optional boolean flag to control the avgpooling before the
logits layer. If false or unset, pooling is done with a fixed window
that reduces default-sized inputs to 1x1, while larger inputs lead to
larger outputs. If true, any input size is pooled down to 1x1.
Returns:
net: a Tensor with the logits (pre-softmax activations) if num_classes
is a non-zero integer, or the non-dropped-out input to the logits layer
if num_classes is 0 or None.
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 tf.variable_scope(scope, 'InceptionV3', [inputs], reuse=reuse) as scope:
with slim.arg_scope([slim.batch_norm, slim.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
if create_aux_logits and num_classes:
with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
stride=1, padding='SAME'):
aux_logits = end_points['Mixed_6e']
with tf.variable_scope('AuxLogits'):
aux_logits = slim.avg_pool2d(
aux_logits, [5, 5], stride=3, padding='VALID',
scope='AvgPool_1a_5x5')
aux_logits = slim.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 = slim.conv2d(
aux_logits, depth(768), kernel_size,
weights_initializer=trunc_normal(0.01),
padding='VALID', scope='Conv2d_2a_{}x{}'.format(*kernel_size))
aux_logits = slim.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 = tf.squeeze(aux_logits, [1, 2], name='SpatialSqueeze')
end_points['AuxLogits'] = aux_logits
# Final pooling and prediction
with tf.variable_scope('Logits'):
if global_pool:
# Global average pooling.
net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='GlobalPool')
end_points['global_pool'] = net
else:
# Pooling with a fixed kernel size.
kernel_size = _reduced_kernel_size_for_small_input(net, [8, 8])
net = slim.avg_pool2d(net, kernel_size, padding='VALID',
scope='AvgPool_1a_{}x{}'.format(*kernel_size))
end_points['AvgPool_1a'] = net
if not num_classes:
return net, end_points
# 1 x 1 x 2048
net = slim.dropout(net, keep_prob=dropout_keep_prob, scope='Dropout_1b')
end_points['PreLogits'] = net
# 2048
logits = slim.conv2d(net, num_classes, [1, 1], activation_fn=None,
normalizer_fn=None, scope='Conv2d_1c_1x1')
if spatial_squeeze:
logits = tf.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_resnet_v2(inputs,
num_classes=1001,
is_training=True,
dropout_keep_prob=0.8,
reuse=None,
scope='InceptionResnetV2',
create_aux_logits=True,
activation_fn=tf.nn.relu):
"""Creates the Inception Resnet V2 model.
Args:
inputs: a 4-D tensor of size [batch_size, height, width, 3].
Dimension batch_size may be undefined. If create_aux_logits is false,
also height and width may be undefined.
num_classes: number of predicted classes. If 0 or None, the logits layer
is omitted and the input features to the logits layer (before dropout)
are returned instead.
is_training: whether is training or not.
dropout_keep_prob: float, the fraction to keep before final layer.
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.
create_aux_logits: Whether to include the auxilliary logits.
activation_fn: Activation function for conv2d.
Returns:
net: the output of the logits layer (if num_classes is a non-zero integer),
or the non-dropped-out input to the logits layer (if num_classes is 0 or
None).
end_points: the set of end_points from the inception model.
"""
end_points = {}
with tf.variable_scope(scope, 'InceptionResnetV2', [inputs],
reuse=reuse) as scope:
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
net, end_points = inception_resnet_v2_base(
inputs, scope=scope, activation_fn=activation_fn)
if create_aux_logits and num_classes:
with tf.variable_scope('AuxLogits'):
aux = end_points['PreAuxLogits']
aux = slim.avg_pool2d(aux,
5,
stride=3,
padding='VALID',
scope='Conv2d_1a_3x3')
aux = slim.conv2d(aux, 128, 1, scope='Conv2d_1b_1x1')
aux = slim.conv2d(aux,
768,
aux.get_shape()[1:3],
padding='VALID',
scope='Conv2d_2a_5x5')
aux = slim.flatten(aux)
aux = slim.fully_connected(aux,
num_classes,
activation_fn=None,
scope='Logits')
end_points['AuxLogits'] = aux
with tf.variable_scope('Logits'):
# TODO(sguada,arnoegw): Consider adding a parameter global_pool which
# can be set to False to disable pooling here (as in resnet_*()).
kernel_size = net.get_shape()[1:3]
if kernel_size.is_fully_defined():
net = slim.avg_pool2d(net,
kernel_size,
padding='VALID',
scope='AvgPool_1a_8x8')
else:
net = tf.reduce_mean(net, [1, 2],
keep_dims=True,
name='global_pool')
end_points['global_pool'] = net
if not num_classes:
return net, end_points
net = slim.flatten(net)
net = slim.dropout(net,
dropout_keep_prob,
is_training=is_training,
scope='Dropout')
end_points['PreLogitsFlatten'] = net
logits = slim.fully_connected(net,
num_classes,
activation_fn=None,
scope='Logits')
end_points['Logits'] = logits
end_points['Predictions'] = tf.nn.softmax(logits,
name='Predictions')
return logits, end_points
def inception_v4(inputs,
num_classes=1001,
is_training=True,
dropout_keep_prob=0.8,
reuse=None,
scope='InceptionV4',
create_aux_logits=True):
"""Creates the Inception V4 model.
Args:
inputs: a 4-D tensor of size [batch_size, height, width, 3].
num_classes: number of predicted classes. If 0 or None, the logits layer
is omitted and the input features to the logits layer (before dropout)
are returned instead.
is_training: whether is training or not.
dropout_keep_prob: float, the fraction to keep before final layer.
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.
create_aux_logits: Whether to include the auxiliary logits.
Returns:
net: a Tensor with the logits (pre-softmax activations) if num_classes
is a non-zero integer, or the non-dropped input to the logits layer
if num_classes is 0 or None.
end_points: the set of end_points from the inception model.
"""
end_points = {}
with tf.variable_scope(scope, 'InceptionV4', [inputs],
reuse=reuse) as scope:
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
net, end_points = inception_v4_base(inputs, scope=scope)
with slim.arg_scope(
[slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
stride=1,
padding='SAME'):
# Auxiliary Head logits
if create_aux_logits and num_classes:
with tf.variable_scope('AuxLogits'):
# 17 x 17 x 1024
aux_logits = end_points['Mixed_6h']
aux_logits = slim.avg_pool2d(aux_logits, [5, 5],
stride=3,
padding='VALID',
scope='AvgPool_1a_5x5')
aux_logits = slim.conv2d(aux_logits,
128, [1, 1],
scope='Conv2d_1b_1x1')
aux_logits = slim.conv2d(aux_logits,
768,
aux_logits.get_shape()[1:3],
padding='VALID',
scope='Conv2d_2a')
aux_logits = slim.flatten(aux_logits)
aux_logits = slim.fully_connected(aux_logits,
num_classes,
activation_fn=None,
scope='Aux_logits')
end_points['AuxLogits'] = aux_logits
# Final pooling and prediction
# TODO(sguada,arnoegw): Consider adding a parameter global_pool which
# can be set to False to disable pooling here (as in resnet_*()).
with tf.variable_scope('Logits'):
# 8 x 8 x 1536
kernel_size = net.get_shape()[1:3]
if kernel_size.is_fully_defined():
net = slim.avg_pool2d(net,
kernel_size,
padding='VALID',
scope='AvgPool_1a')
else:
net = tf.reduce_mean(net, [1, 2],
keep_dims=True,
name='global_pool')
end_points['global_pool'] = net
if not num_classes:
return net, end_points
# 1 x 1 x 1536
net = slim.dropout(net,
dropout_keep_prob,
scope='Dropout_1b')
net = slim.flatten(net, scope='PreLogitsFlatten')
end_points['PreLogitsFlatten'] = net
# 1536
logits = slim.fully_connected(net,
num_classes,
activation_fn=None,
scope='Logits')
end_points['Logits'] = logits
end_points['Predictions'] = tf.nn.softmax(
logits, name='Predictions')
return logits, end_points
def overfeat(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.5,
spatial_squeeze=True,
scope='overfeat',
global_pool=False):
"""Contains the model definition for the OverFeat network.
The definition for the network was obtained from:
OverFeat: Integrated Recognition, Localization and Detection using
Convolutional Networks
Pierre Sermanet, David Eigen, Xiang Zhang, Michael Mathieu, Rob Fergus and
Yann LeCun, 2014
http://arxiv.org/abs/1312.6229
Note: All the fully_connected layers have been transformed to conv2d layers.
To use in classification mode, resize input to 231x231. To use in fully
convolutional mode, set spatial_squeeze to false.
Args:
inputs: a tensor of size [batch_size, height, width, channels].
num_classes: number of predicted classes. If 0 or None, the logits layer is
omitted and the input features to the logits layer are returned instead.
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.
global_pool: Optional boolean flag. If True, the input to the classification
layer is avgpooled to size 1x1, for any input size. (This is not part
of the original OverFeat.)
Returns:
net: the output of the logits layer (if num_classes is a non-zero integer),
or the non-dropped-out input to the logits layer (if num_classes is 0 or
None).
end_points: a dict of tensors with intermediate activations.
"""
with tf.variable_scope(scope, 'overfeat', [inputs]) as sc:
end_points_collection = sc.original_name_scope + '_end_points'
# Collect outputs for conv2d, fully_connected and max_pool2d
with slim.arg_scope(
[slim.conv2d, slim.fully_connected, slim.max_pool2d],
outputs_collections=end_points_collection):
net = slim.conv2d(inputs,
64, [11, 11],
4,
padding='VALID',
scope='conv1')
net = slim.max_pool2d(net, [2, 2], scope='pool1')
net = slim.conv2d(net, 256, [5, 5], padding='VALID', scope='conv2')
net = slim.max_pool2d(net, [2, 2], scope='pool2')
net = slim.conv2d(net, 512, [3, 3], scope='conv3')
net = slim.conv2d(net, 1024, [3, 3], scope='conv4')
net = slim.conv2d(net, 1024, [3, 3], scope='conv5')
net = slim.max_pool2d(net, [2, 2], scope='pool5')
# Use conv2d instead of fully_connected layers.
with slim.arg_scope(
[slim.conv2d],
weights_initializer=trunc_normal(0.005),
biases_initializer=tf.constant_initializer(0.1)):
net = slim.conv2d(net,
3072, [6, 6],
padding='VALID',
scope='fc6')
net = slim.dropout(net,
dropout_keep_prob,
is_training=is_training,
scope='dropout6')
net = slim.conv2d(net, 4096, [1, 1], scope='fc7')
# Convert end_points_collection into a end_point dict.
end_points = slim.utils.convert_collection_to_dict(
end_points_collection)
if global_pool:
net = tf.reduce_mean(net, [1, 2],
keep_dims=True,
name='global_pool')
end_points['global_pool'] = net
if num_classes:
net = slim.dropout(net,
dropout_keep_prob,
is_training=is_training,
scope='dropout7')
net = slim.conv2d(
net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
biases_initializer=tf.zeros_initializer(),
scope='fc8')
if spatial_squeeze:
net = tf.squeeze(net, [1, 2], name='fc8/squeezed')
end_points[sc.name + '/fc8'] = net
return net, end_points
def _build_nasnet_base(images,
normal_cell,
reduction_cell,
num_classes,
hparams,
is_training,
stem_type,
final_endpoint=None):
"""Constructs a NASNet image model."""
end_points = {}
def add_and_check_endpoint(endpoint_name, net):
end_points[endpoint_name] = net
return final_endpoint and (endpoint_name == final_endpoint)
# Find where to place the reduction cells or stride normal cells
reduction_indices = nasnet_utils.calc_reduction_layers(
hparams.num_cells, hparams.num_reduction_layers)
stem_cell = reduction_cell
if stem_type == 'imagenet':
stem = lambda: _imagenet_stem(images, hparams, stem_cell)
elif stem_type == 'cifar':
stem = lambda: _cifar_stem(images, hparams)
else:
raise ValueError('Unknown stem_type: ', stem_type)
net, cell_outputs = stem()
if add_and_check_endpoint('Stem', net): return net, end_points
# Setup for building in the auxiliary head.
aux_head_cell_idxes = []
if len(reduction_indices) >= 2:
aux_head_cell_idxes.append(reduction_indices[1] - 1)
# Run the cells
filter_scaling = 1.0
# true_cell_num accounts for the stem cells
true_cell_num = 2 if stem_type == 'imagenet' else 0
for cell_num in range(hparams.num_cells):
stride = 1
if hparams.skip_reduction_layer_input:
prev_layer = cell_outputs[-2]
if cell_num in reduction_indices:
filter_scaling *= hparams.filter_scaling_rate
net = reduction_cell(net,
scope='reduction_cell_{}'.format(
reduction_indices.index(cell_num)),
filter_scaling=filter_scaling,
stride=2,
prev_layer=cell_outputs[-2],
cell_num=true_cell_num)
if add_and_check_endpoint(
'Reduction_Cell_{}'.format(
reduction_indices.index(cell_num)), net):
return net, end_points
true_cell_num += 1
cell_outputs.append(net)
if not hparams.skip_reduction_layer_input:
prev_layer = cell_outputs[-2]
net = normal_cell(net,
scope='cell_{}'.format(cell_num),
filter_scaling=filter_scaling,
stride=stride,
prev_layer=prev_layer,
cell_num=true_cell_num)
if add_and_check_endpoint('Cell_{}'.format(cell_num), net):
return net, end_points
true_cell_num += 1
if (hparams.use_aux_head and cell_num in aux_head_cell_idxes
and num_classes and is_training):
aux_net = tf.nn.relu(net)
_build_aux_head(aux_net,
end_points,
num_classes,
hparams,
scope='aux_{}'.format(cell_num))
cell_outputs.append(net)
# Final softmax layer
with tf.variable_scope('final_layer'):
net = tf.nn.relu(net)
net = nasnet_utils.global_avg_pool(net)
if add_and_check_endpoint('global_pool', net) or num_classes is None:
return net, end_points
net = slim.dropout(net,
hparams.dense_dropout_keep_prob,
scope='dropout')
logits = slim.fully_connected(net, num_classes)
if add_and_check_endpoint('Logits', logits):
return net, end_points
predictions = tf.nn.softmax(logits, name='predictions')
if add_and_check_endpoint('Predictions', predictions):
return net, end_points
return logits, end_points
def inception_v1(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.8,
prediction_fn=slim.softmax,
spatial_squeeze=True,
reuse=None,
scope='InceptionV1',
global_pool=False):
"""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. If 0 or None, the logits layer
is omitted and the input features to the logits layer (before dropout)
are returned instead.
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 [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.
global_pool: Optional boolean flag to control the avgpooling before the
logits layer. If false or unset, pooling is done with a fixed window
that reduces default-sized inputs to 1x1, while larger inputs lead to
larger outputs. If true, any input size is pooled down to 1x1.
Returns:
net: a Tensor with the logits (pre-softmax activations) if num_classes
is a non-zero integer, or the non-dropped-out input to the logits layer
if num_classes is 0 or None.
end_points: a dictionary from components of the network to the corresponding
activation.
"""
# Final pooling and prediction
with tf.variable_scope(scope, 'InceptionV1', [inputs], reuse=reuse) as scope:
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
net, end_points = inception_v1_base(inputs, scope=scope)
with tf.variable_scope('Logits'):
if global_pool:
# Global average pooling.
net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool')
end_points['global_pool'] = net
else:
# Pooling with a fixed kernel size.
net = slim.avg_pool2d(net, [7, 7], stride=1, scope='AvgPool_0a_7x7')
end_points['AvgPool_0a_7x7'] = net
if not num_classes:
return net, end_points
net = slim.dropout(net, dropout_keep_prob, scope='Dropout_0b')
logits = slim.conv2d(net, num_classes, [1, 1], activation_fn=None,
normalizer_fn=None, scope='Conv2d_0c_1x1')
if spatial_squeeze:
logits = tf.squeeze(logits, [1, 2], name='SpatialSqueeze')
end_points['Logits'] = logits
end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
return logits, end_points
def inception_resnet_v1(inputs,
is_training=True,
dropout_keep_prob=0.8,
bottleneck_layer_size=128,
reuse=None,
scope='InceptionResnetV1'):
end_points = {}
with tf.compat.v1.variable_scope(scope,
'InceptionResnetV1', [inputs],
reuse=reuse):
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
with slim.arg_scope(
[slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
stride=1,
padding='SAME'):
# 149 x 149 x 32
net = slim.conv2d(inputs,
32,
3,
stride=2,
padding='VALID',
scope='Conv2d_1a_3x3')
end_points['Conv2d_1a_3x3'] = net
# 147 x 147 x 32
net = slim.conv2d(net,
32,
3,
padding='VALID',
scope='Conv2d_2a_3x3')
end_points['Conv2d_2a_3x3'] = net
# 147 x 147 x 64
net = slim.conv2d(net, 64, 3, scope='Conv2d_2b_3x3')
end_points['Conv2d_2b_3x3'] = net
# 73 x 73 x 64
net = slim.max_pool2d(net,
3,
stride=2,
padding='VALID',
scope='MaxPool_3a_3x3')
end_points['MaxPool_3a_3x3'] = net
# 73 x 73 x 80
net = slim.conv2d(net,
80,
1,
padding='VALID',
scope='Conv2d_3b_1x1')
end_points['Conv2d_3b_1x1'] = net
# 71 x 71 x 192
net = slim.conv2d(net,
192,
3,
padding='VALID',
scope='Conv2d_4a_3x3')
end_points['Conv2d_4a_3x3'] = net
# 35 x 35 x 256
net = slim.conv2d(net,
256,
3,
stride=2,
padding='VALID',
scope='Conv2d_4b_3x3')
end_points['Conv2d_4b_3x3'] = net
# 5 x Inception-resnet-A
net = slim.repeat(net, 5, block35, scale=0.17)
# Reduction-A
with tf.compat.v1.variable_scope('Mixed_6a'):
net = reduction_a(net, 192, 192, 256, 384)
end_points['Mixed_6a'] = net
# 10 x Inception-Resnet-B
net = slim.repeat(net, 10, block17, scale=0.10)
# Reduction-B
with tf.compat.v1.variable_scope('Mixed_7a'):
net = reduction_b(net)
end_points['Mixed_7a'] = net
# 5 x Inception-Resnet-C
net = slim.repeat(net, 5, block8, scale=0.20)
net = block8(net, activation_fn=None)
with tf.compat.v1.variable_scope('Logits'):
end_points['PrePool'] = net
# pylint: disable=no-member
net = slim.avg_pool2d(net,
net.get_shape()[1:3],
padding='VALID',
scope='AvgPool_1a_8x8')
net = slim.flatten(net)
net = slim.dropout(net,
dropout_keep_prob,
is_training=is_training,
scope='Dropout')
end_points['PreLogitsFlatten'] = net
net = slim.fully_connected(net,
bottleneck_layer_size,
activation_fn=None,
scope='Bottleneck',
reuse=False)
return net, end_points
