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 LogisticClassifier(inputs, labels, scope=None, reuse=None):
with tf.variable_scope(scope,
'LogisticClassifier', [inputs, labels],
reuse=reuse):
predictions = slim.fully_connected(inputs,
1,
activation_fn=tf.sigmoid,
scope='fully_connected')
slim.losses.log_loss(predictions, labels)
return predictions
def BatchNormClassifier(inputs, labels, scope=None, reuse=None):
with tf.variable_scope(scope,
'BatchNormClassifier', [inputs, labels],
reuse=reuse):
inputs = slim.batch_norm(inputs, decay=0.1, fused=True)
predictions = slim.fully_connected(inputs,
1,
activation_fn=tf.sigmoid,
scope='fully_connected')
slim.losses.log_loss(predictions, labels)
return predictions
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 _build_aux_head(net, end_points, num_classes, hparams, scope):
"""Auxiliary head used for all models across all datasets."""
with tf.variable_scope(scope):
aux_logits = tf.identity(net)
with tf.variable_scope('aux_logits'):
aux_logits = slim.avg_pool2d(aux_logits, [5, 5],
stride=3,
padding='VALID')
aux_logits = slim.conv2d(aux_logits, 128, [1, 1], scope='proj')
aux_logits = slim.batch_norm(aux_logits, scope='aux_bn0')
aux_logits = tf.nn.relu(aux_logits)
# Shape of feature map before the final layer.
shape = aux_logits.shape
if hparams.data_format == 'NHWC':
shape = shape[1:3]
else:
shape = shape[2:4]
aux_logits = slim.conv2d(aux_logits, 768, shape, padding='VALID')
aux_logits = slim.batch_norm(aux_logits, scope='aux_bn1')
aux_logits = tf.nn.relu(aux_logits)
aux_logits = tf.contrib.layers.flatten(aux_logits)
aux_logits = slim.fully_connected(aux_logits, num_classes)
end_points['AuxLogits'] = aux_logits
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 _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_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