mirror of
https://github.com/wassname/keras-contrib.git
synced 2026-06-27 16:10:11 +08:00
Improve name scope and add CIFAR model
This commit is contained in:
Somshubra Majumdar
@@ -38,7 +38,6 @@ from keras.applications.inception_v3 import preprocess_input
|
||||
from keras.applications.imagenet_utils import decode_predictions
|
||||
from keras import backend as K
|
||||
|
||||
|
||||
_BN_DECAY = 0.9997
|
||||
_BN_EPSILON = 1e-3
|
||||
|
||||
@@ -171,10 +170,10 @@ def NASNet(input_shape=None,
|
||||
img_input = input_tensor
|
||||
|
||||
assert penultimate_filters % 24 == 0, "`penultimate_filters` needs to be divisible " \
|
||||
"by 6 * (2^N)."
|
||||
"by 6 * (2^N)."
|
||||
|
||||
channel_dim = 1 if K.image_data_format() == 'channels_first' else -1
|
||||
filters = penultimate_filters // 24
|
||||
filters = penultimate_filters // 24
|
||||
|
||||
x = Conv2D(stem_filters, (3, 3), strides=(2, 2), padding='valid', use_bias=False, name='stem_conv1',
|
||||
kernel_initializer='he_normal')(img_input)
|
||||
@@ -199,22 +198,22 @@ def NASNet(input_shape=None,
|
||||
img_dim = 2 if K.image_data_format() == 'channels_first' else -2
|
||||
|
||||
with K.name_scope('auxilary_branch'):
|
||||
auxilary_x = Activation('relu')(x)
|
||||
auxilary_x = AveragePooling2D((5, 5), strides=(3, 3), padding='valid', name='aux_pool')(auxilary_x)
|
||||
auxilary_x = Conv2D(128, (1, 1), padding='same', use_bias=False, name='aux_conv_projection',
|
||||
kernel_initializer='he_normal')(auxilary_x)
|
||||
auxilary_x = BatchNormalization(axis=channel_dim, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
|
||||
name='aux_bn_projection')(auxilary_x)
|
||||
auxilary_x = Activation('relu')(auxilary_x)
|
||||
auxilary_x = Activation('relu')(x)
|
||||
auxilary_x = AveragePooling2D((5, 5), strides=(3, 3), padding='valid', name='aux_pool')(auxilary_x)
|
||||
auxilary_x = Conv2D(128, (1, 1), padding='same', use_bias=False, name='aux_conv_projection',
|
||||
kernel_initializer='he_normal')(auxilary_x)
|
||||
auxilary_x = BatchNormalization(axis=channel_dim, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
|
||||
name='aux_bn_projection')(auxilary_x)
|
||||
auxilary_x = Activation('relu')(auxilary_x)
|
||||
|
||||
auxilary_x = Conv2D(768, auxilary_x._keras_shape[img_dim], padding='valid', use_bias=False,
|
||||
kernel_initializer='he_normal', name='aux_conv_reduction')(auxilary_x)
|
||||
auxilary_x = BatchNormalization(axis=channel_dim, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
|
||||
name='aux_bn_reduction')(auxilary_x)
|
||||
auxilary_x = Activation('relu')(auxilary_x)
|
||||
auxilary_x = Conv2D(768, auxilary_x._keras_shape[img_dim], padding='valid', use_bias=False,
|
||||
kernel_initializer='he_normal', name='aux_conv_reduction')(auxilary_x)
|
||||
auxilary_x = BatchNormalization(axis=channel_dim, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
|
||||
name='aux_bn_reduction')(auxilary_x)
|
||||
auxilary_x = Activation('relu')(auxilary_x)
|
||||
|
||||
auxilary_x = GlobalAveragePooling2D()(auxilary_x)
|
||||
auxilary_x = Dense(classes, activation='softmax')(auxilary_x)
|
||||
auxilary_x = GlobalAveragePooling2D()(auxilary_x)
|
||||
auxilary_x = Dense(classes, activation='softmax')(auxilary_x)
|
||||
|
||||
x, p0 = _reduction_A(x, p, filters * filters_multiplier ** 2, id='reduce_%d' % (2 * nb_blocks))
|
||||
|
||||
@@ -456,7 +455,7 @@ def NASNetCIFAR(input_shape=None,
|
||||
"""
|
||||
return NASNet(input_shape,
|
||||
penultimate_filters=768,
|
||||
nb_blocks=2,
|
||||
nb_blocks=6,
|
||||
stem_filters=96,
|
||||
skip_reduction=True,
|
||||
use_auxilary_branch=use_auxilary_branch,
|
||||
@@ -518,32 +517,32 @@ def _adjust_block(p, ip, filters, id=None):
|
||||
img_dim = 2 if K.image_data_format() == 'channels_first' else -2
|
||||
|
||||
with K.name_scope('adjust_block'):
|
||||
if p is None:
|
||||
p = ip
|
||||
if p is None:
|
||||
p = ip
|
||||
|
||||
elif p._keras_shape[img_dim] != ip._keras_shape[img_dim]:
|
||||
with K.name_scope('adjust_reduction_block_%s' % id):
|
||||
p = Activation('relu', name='adjust_relu_1_%s' % id)(p)
|
||||
elif p._keras_shape[img_dim] != ip._keras_shape[img_dim]:
|
||||
with K.name_scope('adjust_reduction_block_%s' % id):
|
||||
p = Activation('relu', name='adjust_relu_1_%s' % id)(p)
|
||||
|
||||
p1 = AveragePooling2D((1, 1), strides=(2, 2), padding='valid', name='adjust_avg_pool_1_%s' % id)(p)
|
||||
p1 = Conv2D(filters // 2, (1, 1), padding='same', use_bias=False,
|
||||
name='adjust_conv_1_%s' % id, kernel_initializer='he_normal')(p1)
|
||||
p1 = AveragePooling2D((1, 1), strides=(2, 2), padding='valid', name='adjust_avg_pool_1_%s' % id)(p)
|
||||
p1 = Conv2D(filters // 2, (1, 1), padding='same', use_bias=False,
|
||||
name='adjust_conv_1_%s' % id, kernel_initializer='he_normal')(p1)
|
||||
|
||||
p2 = AveragePooling2D((1, 1), strides=(2, 2), padding='valid', name='adjust_avg_pool_2_%s' % id)(p)
|
||||
p2 = Conv2D(filters // 2, (1, 1), padding='same', use_bias=False,
|
||||
name='adjust_conv_2_%s' % id, kernel_initializer='he_normal')(p2)
|
||||
p2 = AveragePooling2D((1, 1), strides=(2, 2), padding='valid', name='adjust_avg_pool_2_%s' % id)(p)
|
||||
p2 = Conv2D(filters // 2, (1, 1), padding='same', use_bias=False,
|
||||
name='adjust_conv_2_%s' % id, kernel_initializer='he_normal')(p2)
|
||||
|
||||
p = concatenate([p1, p2], axis=channel_dim)
|
||||
p = BatchNormalization(axis=channel_dim, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
|
||||
name='adjust_bn_%s' % id)(p)
|
||||
p = concatenate([p1, p2], axis=channel_dim)
|
||||
p = BatchNormalization(axis=channel_dim, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
|
||||
name='adjust_bn_%s' % id)(p)
|
||||
|
||||
elif p._keras_shape[channel_dim] != filters:
|
||||
with K.name_scope('adjust_projection_block_%s' % id):
|
||||
p = Activation('relu')(p)
|
||||
p = Conv2D(filters, (1, 1), strides=(1, 1), padding='same', name='adjust_conv_projection_%s' % id,
|
||||
use_bias=False, kernel_initializer='he_normal')(p)
|
||||
p = BatchNormalization(axis=channel_dim, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
|
||||
name='adjust_bn_%s' % id)(p)
|
||||
elif p._keras_shape[channel_dim] != filters:
|
||||
with K.name_scope('adjust_projection_block_%s' % id):
|
||||
p = Activation('relu')(p)
|
||||
p = Conv2D(filters, (1, 1), strides=(1, 1), padding='same', name='adjust_conv_projection_%s' % id,
|
||||
use_bias=False, kernel_initializer='he_normal')(p)
|
||||
p = BatchNormalization(axis=channel_dim, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
|
||||
name='adjust_bn_%s' % id)(p)
|
||||
return p
|
||||
|
||||
|
||||
@@ -562,38 +561,38 @@ def _normal_A(ip, p, filters, id=None):
|
||||
channel_dim = 1 if K.image_data_format() == 'channels_first' else -1
|
||||
|
||||
with K.name_scope('normal_A_block_%s' % id):
|
||||
p = _adjust_block(p, ip, filters, id)
|
||||
p = _adjust_block(p, ip, filters, id)
|
||||
|
||||
h = Activation('relu')(ip)
|
||||
h = Conv2D(filters, (1, 1), strides=(1, 1), padding='same', name='normal_conv_1_%s' % id,
|
||||
use_bias=False, kernel_initializer='he_normal')(h)
|
||||
h = BatchNormalization(axis=channel_dim, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
|
||||
name='normal_bn_1_%s' % id)(h)
|
||||
h = Activation('relu')(ip)
|
||||
h = Conv2D(filters, (1, 1), strides=(1, 1), padding='same', name='normal_conv_1_%s' % id,
|
||||
use_bias=False, kernel_initializer='he_normal')(h)
|
||||
h = BatchNormalization(axis=channel_dim, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
|
||||
name='normal_bn_1_%s' % id)(h)
|
||||
|
||||
with K.name_scope('block_1'):
|
||||
x1 = _separable_conv_block(h, filters, id='normal_left1_%s' % id)
|
||||
x1 = add([x1, h], name='normal_add_1_%s' % id)
|
||||
with K.name_scope('block_1'):
|
||||
x1 = _separable_conv_block(h, filters, id='normal_left1_%s' % id)
|
||||
x1 = add([x1, h], name='normal_add_1_%s' % id)
|
||||
|
||||
with K.name_scope('block_2'):
|
||||
x2_1 = _separable_conv_block(p, filters, id='normal_left2_%s' % id)
|
||||
x2_2 = _separable_conv_block(h, filters, kernel_size=(5, 5), id='normal_right2_%s' % id)
|
||||
x2 = add([x2_1, x2_2], name='normal_add_2_%s' % id)
|
||||
with K.name_scope('block_2'):
|
||||
x2_1 = _separable_conv_block(p, filters, id='normal_left2_%s' % id)
|
||||
x2_2 = _separable_conv_block(h, filters, kernel_size=(5, 5), id='normal_right2_%s' % id)
|
||||
x2 = add([x2_1, x2_2], name='normal_add_2_%s' % id)
|
||||
|
||||
with K.name_scope('block_3'):
|
||||
x3 = AveragePooling2D((3, 3), strides=(1, 1), padding='same', name='normal_left3_%s' % (id))(h)
|
||||
x3 = add([x3, p], name='normal_add_3_%s' % id)
|
||||
with K.name_scope('block_3'):
|
||||
x3 = AveragePooling2D((3, 3), strides=(1, 1), padding='same', name='normal_left3_%s' % (id))(h)
|
||||
x3 = add([x3, p], name='normal_add_3_%s' % id)
|
||||
|
||||
with K.name_scope('block_4'):
|
||||
x4_1 = AveragePooling2D((3, 3), strides=(1, 1), padding='same', name='normal_left4_%s' % (id))(p)
|
||||
x4_2 = AveragePooling2D((3, 3), strides=(1, 1), padding='same', name='normal_right4_%s' % (id))(p)
|
||||
x4 = add([x4_1, x4_2], name='normal_add_4_%s' % id)
|
||||
with K.name_scope('block_4'):
|
||||
x4_1 = AveragePooling2D((3, 3), strides=(1, 1), padding='same', name='normal_left4_%s' % (id))(p)
|
||||
x4_2 = AveragePooling2D((3, 3), strides=(1, 1), padding='same', name='normal_right4_%s' % (id))(p)
|
||||
x4 = add([x4_1, x4_2], name='normal_add_4_%s' % id)
|
||||
|
||||
with K.name_scope('block_5'):
|
||||
x5_1 = _separable_conv_block(p, filters, (5, 5), id='normal_left5_%s' % id)
|
||||
x5_2 = _separable_conv_block(p, filters, (3, 3), id='normal_right5_%s' % id)
|
||||
x5 = add([x5_1, x5_2], name='normal_add_5_%s' % id)
|
||||
with K.name_scope('block_5'):
|
||||
x5_1 = _separable_conv_block(p, filters, (5, 5), id='normal_left5_%s' % id)
|
||||
x5_2 = _separable_conv_block(p, filters, (3, 3), id='normal_right5_%s' % id)
|
||||
x5 = add([x5_1, x5_2], name='normal_add_5_%s' % id)
|
||||
|
||||
x = concatenate([p, x2, x5, x3, x4, x1], axis=channel_dim, name='normal_concat_%s' % id)
|
||||
x = concatenate([p, x2, x5, x3, x4, x1], axis=channel_dim, name='normal_concat_%s' % id)
|
||||
return x, ip
|
||||
|
||||
|
||||
@@ -613,36 +612,36 @@ def _reduction_A(ip, p, filters, id=None):
|
||||
channel_dim = 1 if K.image_data_format() == 'channels_first' else -1
|
||||
|
||||
with K.name_scope('reduction_A_block_%s' % id):
|
||||
p = _adjust_block(p, ip, filters, id)
|
||||
p = _adjust_block(p, ip, filters, id)
|
||||
|
||||
h = Activation('relu')(ip)
|
||||
h = Conv2D(filters, (1, 1), strides=(1, 1), padding='same', name='reduction_conv_1_%s' % id,
|
||||
use_bias=False, kernel_initializer='he_normal')(h)
|
||||
h = BatchNormalization(axis=channel_dim, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
|
||||
name='reduction_bn_1_%s' % id)(h)
|
||||
h = Activation('relu')(ip)
|
||||
h = Conv2D(filters, (1, 1), strides=(1, 1), padding='same', name='reduction_conv_1_%s' % id,
|
||||
use_bias=False, kernel_initializer='he_normal')(h)
|
||||
h = BatchNormalization(axis=channel_dim, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
|
||||
name='reduction_bn_1_%s' % id)(h)
|
||||
|
||||
with K.name_scope('block_1'):
|
||||
x1_1 = _separable_conv_block(p, filters, (7, 7), strides=(2, 2), id='reduction_left1_%s' % id)
|
||||
x1_2 = _separable_conv_block(h, filters, (5, 5), strides=(2, 2), id='reduction_right1_%s' % id)
|
||||
x1 = add([x1_1, x1_2], name='reduction_add_1_%s' % id)
|
||||
with K.name_scope('block_1'):
|
||||
x1_1 = _separable_conv_block(p, filters, (7, 7), strides=(2, 2), id='reduction_left1_%s' % id)
|
||||
x1_2 = _separable_conv_block(h, filters, (5, 5), strides=(2, 2), id='reduction_right1_%s' % id)
|
||||
x1 = add([x1_1, x1_2], name='reduction_add_1_%s' % id)
|
||||
|
||||
with K.name_scope('block_2'):
|
||||
x2_1 = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='reduction_left2_%s' % id)(h)
|
||||
x2_2 = _separable_conv_block(p, filters, (7, 7), strides=(2, 2), id='reduction_right2_%s' % id)
|
||||
x2 = add([x2_1, x2_2], name='reduction_add_2_%s' % id)
|
||||
with K.name_scope('block_2'):
|
||||
x2_1 = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='reduction_left2_%s' % id)(h)
|
||||
x2_2 = _separable_conv_block(p, filters, (7, 7), strides=(2, 2), id='reduction_right2_%s' % id)
|
||||
x2 = add([x2_1, x2_2], name='reduction_add_2_%s' % id)
|
||||
|
||||
with K.name_scope('block_3'):
|
||||
x3_1 = AveragePooling2D((3, 3), strides=(2, 2), padding='same', name='reduction_left3_%s' % id)(h)
|
||||
x3_2 = _separable_conv_block(p, filters, (5, 5), strides=(2, 2), id='reduction_right3_%s' % id)
|
||||
x3 = add([x3_1, x3_2], name='reduction_add3_%s' % id)
|
||||
with K.name_scope('block_3'):
|
||||
x3_1 = AveragePooling2D((3, 3), strides=(2, 2), padding='same', name='reduction_left3_%s' % id)(h)
|
||||
x3_2 = _separable_conv_block(p, filters, (5, 5), strides=(2, 2), id='reduction_right3_%s' % id)
|
||||
x3 = add([x3_1, x3_2], name='reduction_add3_%s' % id)
|
||||
|
||||
with K.name_scope('block_4'):
|
||||
x4_1 = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='reduction_left4_%s' % id)(h)
|
||||
x4_2 = _separable_conv_block(x1, filters, (3, 3), id='reduction_right4_%s' % id)
|
||||
x4 = add([x4_1, x4_2], name='reduction_add4_%s' % id)
|
||||
with K.name_scope('block_4'):
|
||||
x4_1 = MaxPooling2D((3, 3), strides=(2, 2), padding='same', name='reduction_left4_%s' % id)(h)
|
||||
x4_2 = _separable_conv_block(x1, filters, (3, 3), id='reduction_right4_%s' % id)
|
||||
x4 = add([x4_1, x4_2], name='reduction_add4_%s' % id)
|
||||
|
||||
with K.name_scope('block_5'):
|
||||
x5 = AveragePooling2D((3, 3), strides=(1, 1), padding='same', name='reduction_left5_%s' % id)(x1)
|
||||
with K.name_scope('block_5'):
|
||||
x5 = AveragePooling2D((3, 3), strides=(1, 1), padding='same', name='reduction_left5_%s' % id)(x1)
|
||||
|
||||
x = concatenate([x2, x3, x5, x4], axis=channel_dim, name='reduction_concat_%s' % id)
|
||||
return x, ip
|
||||
x = concatenate([x2, x3, x5, x4], axis=channel_dim, name='reduction_concat_%s' % id)
|
||||
return x, ip
|
||||
|
||||
Reference in New Issue
Block a user