def model(inputs, is_training):
"""Creation of the model graph."""
if use_resnetd_stem:
inputs = conv2d_fixed_padding(
inputs=inputs, filters=32, kernel_size=3, strides=2,
data_format=data_format, name="init_conv_0")
inputs = norm_activation(
inputs, is_training, data_format=data_format,
layer=norm_act_layer, bn_momentum=bn_momentum,
name="init_norm_0")
inputs = conv2d_fixed_padding(
inputs=inputs, filters=32, kernel_size=3, strides=1,
data_format=data_format, name="init_conv_1")
inputs = norm_activation(
inputs, is_training, data_format=data_format,
layer=norm_act_layer, bn_momentum=bn_momentum,
name="init_norm_1")
inputs = conv2d_fixed_padding(
inputs=inputs, filters=64, kernel_size=3, strides=1,
data_format=data_format, name="init_conv_2")
else:
inputs = conv2d_fixed_padding(
inputs=inputs, filters=64, kernel_size=7, strides=2,
data_format=data_format, name="init_conv_0")
inputs = tf.identity(inputs, 'initial_conv')
if not pre_activation:
inputs = norm_activation(inputs, is_training, data_format=data_format,
layer=norm_act_layer, bn_momentum=bn_momentum,
name="init_norm_2")
if not skip_stem_max_pool:
if replace_stem_max_pool:
inputs = conv2d_fixed_padding(
inputs=inputs, filters=64,
kernel_size=3, strides=2, data_format=data_format,
name="init_conv_3")
inputs = norm_activation(
inputs, is_training, data_format=data_format,
bn_momentum=bn_momentum, name="init_norm_3")
else:
inputs = tf.layers.max_pooling2d(
inputs=inputs, pool_size=3, strides=2, padding='SAME',
data_format=data_format)
inputs = tf.identity(inputs, 'initial_max_pool')
custom_block_group = functools.partial(
block_group,
data_format=data_format,
dropblock_size=dropblock_size,
pre_activation=pre_activation,
norm_act_layer=norm_act_layer,
se_ratio=se_ratio,
resnetd_shortcut=resnetd_shortcut,
bn_momentum=bn_momentum)
num_layers = len(layers) + 1
stride_c2 = 2 if skip_stem_max_pool else 1
# Multiscale feature extractions
inputs = multiscale(
inputs=inputs,
data_format=data_format,
scales=scales,
custom_block_group=custom_block_group,
filters=64,
block_fn=block_fn,
layer=layers[0],
stride_c2=stride_c2,
is_training=is_training,
name='block_group1',
scope_name='multiscale1',
dropblock_keep_prob=dropblock_keep_probs[0],
drop_connect_rate=resnet_layers.get_drop_connect_rate(
drop_connect_rate, 2, num_layers))
inputs = multiscale(
inputs=inputs,
data_format=data_format,
scales=scales,
custom_block_group=custom_block_group,
filters=128,
block_fn=block_fn,
layer=layers[1],
stride_c2=stride_c2,
is_training=is_training,
name='block_group2',
scope_name='multiscale2',
dropblock_keep_prob=dropblock_keep_probs[1],
drop_connect_rate=resnet_layers.get_drop_connect_rate(
drop_connect_rate, 3, num_layers))
inputs = multiscale(
inputs=inputs,
data_format=data_format,
scales=scales,
custom_block_group=custom_block_group,
filters=256,
block_fn=block_fn,
layer=layers[2],
stride_c2=stride_c2,
is_training=is_training,
name='block_group3',
scope_name='multiscale3',
dropblock_keep_prob=dropblock_keep_probs[2],
drop_connect_rate=resnet_layers.get_drop_connect_rate(
drop_connect_rate, 4, num_layers))
inputs = multiscale(
inputs=inputs,
data_format=data_format,
scales=scales,
custom_block_group=custom_block_group,
filters=512,
block_fn=block_fn,
layer=layers[3],
stride_c2=stride_c2,
is_training=is_training,
name='block_group4',
scope_name='multiscale4',
dropblock_keep_prob=dropblock_keep_probs[3],
use_pool=False,
drop_connect_rate=resnet_layers.get_drop_connect_rate(
drop_connect_rate, 5, num_layers))
if pre_activation:
inputs = norm_activation(inputs, is_training, data_format=data_format,
layer=norm_act_layer, bn_momentum=bn_momentum)
# The activation is 7x7 so this is a global average pool.
# TODO(huangyp): reduce_mean will be faster.
if data_format == 'channels_last':
# pool_size = (inputs.shape[1], inputs.shape[2])
reduction_indices = [1, 2]
else:
# pool_size = (inputs.shape[2], inputs.shape[3])
reduction_indices = [2, 3]
inputs = tf.reduce_mean(inputs, reduction_indices=reduction_indices)
# inputs = tf.layers.average_pooling2d(
# inputs=inputs, pool_size=pool_size, strides=1, padding='VALID',
# data_format=data_format)
inputs = tf.identity(inputs, 'final_avg_pool')
inputs = tf.reshape(
inputs, [-1, 2048 if block_fn is bottleneck_block else 512])
if dropout_rate is not None:
tf.logging.info('using dropout')
inputs = tf.layers.dropout(
inputs, rate=dropout_rate, training=is_training)
tf.logging.info('Predense shape: {}'.format(inputs.shape))
inputs = tf.layers.dense(
inputs=inputs,
units=num_classes,
kernel_initializer=tf.random_normal_initializer(stddev=.01))
inputs = tf.identity(inputs, 'final_dense')
return inputs
def model(inputs, is_training):
"""Creation of the model graph."""
inputs = conv2d_fixed_padding(inputs=inputs,
filters=64,
kernel_size=7,
strides=1,
data_format=data_format)
inputs = tf.identity(inputs, 'initial_conv')
if not pre_activation:
inputs = norm_activation(inputs,
is_training,
data_format=data_format,
layer=norm_act_layer,
bn_momentum=bn_momentum)
inputs = tf.layers.max_pooling2d(inputs=inputs,
pool_size=3,
strides=2,
padding='SAME',
data_format=data_format)
inputs = tf.identity(inputs, 'initial_max_pool')
custom_block_group = functools.partial(
block_group,
data_format=data_format,
dropblock_size=dropblock_size,
pre_activation=pre_activation,
norm_act_layer=norm_act_layer,
se_ratio=se_ratio,
resnetd_shortcut=resnetd_shortcut,
bn_momentum=bn_momentum)
num_layers = len(layers) + 1
stride_c2 = 1 # if skip_stem_max_pool else 1
## Block 1
inputs = scale_invariance(
inputs=inputs,
scales=scales,
is_training=is_training,
block_fn=block_fn,
layers=layers[0],
name='block_group1',
filters=64,
drop_connect_rate=resnet_layers.get_drop_connect_rate(
drop_connect_rate, 2, num_layers),
dropblock_keep_probs=dropblock_keep_probs[0],
stride_c2=stride_c2,
custom_block_group=custom_block_group,
data_format=data_format)
inputs = tf.layers.max_pooling3d(inputs=inputs,
pool_size=(scales, 2, 2),
strides=(scales, 2, 2),
padding='SAME',
data_format=data_format)
inputs = tf.squeeze(inputs, 1) # Squeeze the last dim
## Block 2
inputs = scale_invariance(
inputs=inputs,
scales=scales,
is_training=is_training,
block_fn=block_fn,
layers=layers[1],
name='block_group2',
filters=128,
drop_connect_rate=resnet_layers.get_drop_connect_rate(
drop_connect_rate, 3, num_layers),
dropblock_keep_probs=dropblock_keep_probs[1],
stride_c2=stride_c2,
custom_block_group=custom_block_group,
data_format=data_format)
inputs = tf.layers.max_pooling3d(inputs=inputs,
pool_size=(scales, 2, 2),
strides=(scales, 2, 2),
padding='SAME',
data_format=data_format)
inputs = tf.squeeze(inputs, 1) # Squeeze the last dim
## Block 3
inputs = scale_invariance(
inputs=inputs,
scales=scales,
is_training=is_training,
block_fn=block_fn,
layers=layers[2],
name='block_group3',
filters=256,
drop_connect_rate=resnet_layers.get_drop_connect_rate(
drop_connect_rate, 4, num_layers),
dropblock_keep_probs=dropblock_keep_probs[2],
stride_c2=stride_c2,
custom_block_group=custom_block_group,
data_format=data_format)
inputs = tf.layers.max_pooling3d(inputs=inputs,
pool_size=(scales, 2, 2),
strides=(scales, 2, 2),
padding='SAME',
data_format=data_format)
inputs = tf.squeeze(inputs, 1) # Squeeze the last dim
## Block 4
inputs = scale_invariance(
inputs=inputs,
scales=scales,
is_training=is_training,
block_fn=block_fn,
layers=layers[3],
name='block_group4',
filters=512,
drop_connect_rate=resnet_layers.get_drop_connect_rate(
drop_connect_rate, 5, num_layers),
dropblock_keep_probs=dropblock_keep_probs[3],
stride_c2=stride_c2,
custom_block_group=custom_block_group,
data_format=data_format)
inputs = tf.layers.max_pooling3d(inputs=inputs,
pool_size=(scales, 2, 2),
strides=(scales, 2, 2),
padding='SAME',
data_format=data_format)
inputs = tf.squeeze(inputs, 1) # Squeeze the last dim
if pre_activation:
inputs = norm_activation(inputs,
is_training,
data_format=data_format,
layer=norm_act_layer,
bn_momentum=bn_momentum)
# The activation is 7x7 so this is a global average pool.
# TODO(huangyp): reduce_mean will be faster.
if data_format == 'channels_last':
pool_size = (inputs.shape[1], inputs.shape[2])
else:
pool_size = (inputs.shape[2], inputs.shape[3])
inputs = tf.layers.average_pooling2d(inputs=inputs,
pool_size=pool_size,
strides=1,
padding='VALID',
data_format=data_format)
inputs = tf.identity(inputs, 'final_avg_pool')
inputs = tf.reshape(
inputs, [-1, 2048 if block_fn is bottleneck_block else 512])
if dropout_rate is not None:
tf.logging.info('using dropout')
inputs = tf.layers.dropout(inputs,
rate=dropout_rate,
training=is_training)
inputs = tf.layers.dense(
inputs=inputs,
units=num_classes,
kernel_initializer=tf.random_normal_initializer(stddev=.01))
inputs = tf.identity(inputs, 'final_dense')
return inputs
def model(inputs, is_training):
"""Creation of the model graph."""
#####
## Dont use dilation on the first conv/pool. Use it everywhere else.
#####
inputs = conv2d_fixed_padding(inputs=inputs,
filters=64,
kernel_size=7,
strides=1,
data_format=data_format)
inputs = tf.identity(inputs, 'initial_conv')
if not pre_activation:
inputs = norm_activation(inputs,
is_training,
data_format=data_format,
layer=norm_act_layer,
bn_momentum=bn_momentum)
inputs = tf.layers.max_pooling2d(inputs=inputs,
pool_size=3,
strides=2,
padding='SAME',
data_format=data_format)
inputs = tf.identity(inputs, 'initial_max_pool')
#####
custom_block_group = functools.partial(
block_group,
data_format=data_format,
dropblock_size=dropblock_size,
pre_activation=pre_activation,
norm_act_layer=norm_act_layer,
se_ratio=se_ratio,
resnetd_shortcut=resnetd_shortcut,
bn_momentum=bn_momentum)
num_layers = len(layers) + 1
stride_c2 = 1 # if skip_stem_max_pool else 1
## Block S1/C1
c1 = tf.identity(inputs)
inputs = scale_invariance(
inputs=c1,
scales=scales,
is_training=is_training,
block_fn=block_fn,
layers=layers[0],
name='block_group1',
filters=64,
drop_connect_rate=resnet_layers.get_drop_connect_rate(
drop_connect_rate, 2, num_layers),
dropblock_keep_probs=dropblock_keep_probs[0],
stride_c2=stride_c2,
custom_block_group=custom_block_group,
data_format=data_format)
inputs = tf.layers.max_pooling3d(inputs=inputs,
pool_size=(scales, 2, 2),
strides=(scales, 1, 1),
padding='SAME',
data_format=data_format)
inputs = tf.squeeze(inputs, 1) # Squeeze the last dim
## Block S2b
c2b = scale_invariance(
inputs=c1,
scales=scales,
is_training=is_training,
block_fn=block_fn,
layers=layers[0],
name='block_groups2b',
filters=128,
drop_connect_rate=resnet_layers.get_drop_connect_rate(
drop_connect_rate, 2, num_layers),
dropblock_keep_probs=dropblock_keep_probs[0],
stride_c2=stride_c2,
custom_block_group=custom_block_group,
data_format=data_format)
c2b = tf.layers.max_pooling3d(inputs=c2b,
pool_size=(scales, 2, 2),
strides=(scales, 1, 1),
padding='SAME',
data_format=data_format)
c2b = tf.squeeze(c2b, 1) # Squeeze the last dim
## Block S2/C2
inputs = scale_invariance(
inputs=inputs,
scales=scales,
is_training=is_training,
block_fn=block_fn,
layers=layers[1],
name='block_group2',
filters=128,
drop_connect_rate=resnet_layers.get_drop_connect_rate(
drop_connect_rate, 3, num_layers),
dropblock_keep_probs=dropblock_keep_probs[1],
stride_c2=stride_c2,
custom_block_group=custom_block_group,
data_format=data_format)
inputs = tf.layers.max_pooling3d(inputs=inputs,
pool_size=(scales, 2, 2),
strides=(scales, 1, 1),
padding='SAME',
data_format=data_format)
inputs = tf.squeeze(inputs, 1) # Squeeze the last dim
c2 = tf.identity(inputs)
## Block S3/C3
inputs = scale_invariance(
inputs=inputs,
scales=scales,
is_training=is_training,
block_fn=block_fn,
layers=layers[2],
name='block_group3',
filters=256,
drop_connect_rate=resnet_layers.get_drop_connect_rate(
drop_connect_rate, 4, num_layers),
dropblock_keep_probs=dropblock_keep_probs[2],
stride_c2=stride_c2,
custom_block_group=custom_block_group,
data_format=data_format)
inputs = tf.layers.max_pooling3d(inputs=inputs,
pool_size=(scales, 2, 2),
strides=(scales, 1, 1),
padding='SAME',
data_format=data_format)
inputs = tf.squeeze(inputs, 1) # Squeeze the last dim
# Prep C3 for merge
merge_size = c2b.get_shape().as_list()
inputs = tf.cast(inputs, tf.float32)
inputs = tf.image.resize(inputs,
merge_size[1:3],
align_corners=True,
method=RESIZE_METHOD)
inputs = tf.cast(inputs, c2b.dtype)
c2 = tf.cast(c2, tf.float32)
c2 = tf.image.resize(c2,
merge_size[1:3],
align_corners=True,
method=RESIZE_METHOD)
c2 = tf.cast(c2, c2b.dtype)
# Merge C2 and C2b with C3
inputs = tf.concat([inputs, c2, c2b], -1)
## Block S4/C4
inputs = scale_invariance(
inputs=inputs,
scales=scales,
is_training=is_training,
block_fn=block_fn,
layers=layers[3],
name='block_group4',
filters=512, # Inception-style merge for C2->S4
drop_connect_rate=resnet_layers.get_drop_connect_rate(
drop_connect_rate, 5, num_layers),
dropblock_keep_probs=dropblock_keep_probs[3],
stride_c2=stride_c2,
custom_block_group=custom_block_group,
data_format=data_format)
inputs = tf.layers.max_pooling3d(inputs=inputs,
pool_size=(scales, 2, 2),
strides=(scales, 1, 1),
padding='SAME',
data_format=data_format)
inputs = tf.squeeze(inputs, 1) # Squeeze the last dim
if pre_activation:
inputs = norm_activation(inputs,
is_training,
data_format=data_format,
layer=norm_act_layer,
bn_momentum=bn_momentum)
# The activation is 7x7 so this is a global average pool.
# TODO(huangyp): reduce_mean will be faster.
if data_format == 'channels_last':
pool_size = (inputs.shape[1], inputs.shape[2])
else:
pool_size = (inputs.shape[2], inputs.shape[3])
inputs = tf.layers.average_pooling2d(inputs=inputs,
pool_size=pool_size,
strides=1,
padding='VALID',
data_format=data_format)
inputs = tf.identity(inputs, 'final_avg_pool')
inputs = tf.reshape(
inputs, [-1, 2048 if block_fn is bottleneck_block else 512])
if dropout_rate is not None:
tf.logging.info('using dropout')
inputs = tf.layers.dropout(inputs,
rate=dropout_rate,
training=is_training)
inputs = tf.layers.dense(
inputs=inputs,
units=num_classes,
kernel_initializer=tf.random_normal_initializer(stddev=.01))
inputs = tf.identity(inputs, 'final_dense')
return inputs