def InceptionV3(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation='softmax',
partition_layer='input'):
"""Instantiates the Inception v3 architecture.
Reference paper:
- [Rethinking the Inception Architecture for Computer Vision](
http://arxiv.org/abs/1512.00567) (CVPR 2016)
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in the `tf.keras.backend.image_data_format()`.
Caution: Be sure to properly pre-process your inputs to the application.
Please see `applications.inception_v3.preprocess_input` for an example.
Arguments:
include_top: Boolean, whether to include the fully-connected
layer at the top, as the last layer of the network. Default to `True`.
weights: One of `None` (random initialization),
`imagenet` (pre-training on ImageNet),
or the path to the weights file to be loaded. Default to `imagenet`.
input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model. `input_tensor` is useful for sharing
inputs between multiple different networks. Default to None.
input_shape: Optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(299, 299, 3)` (with `channels_last` data format)
or `(3, 299, 299)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 75.
E.g. `(150, 150, 3)` would be one valid value.
`input_shape` will be ignored if the `input_tensor` is provided.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` (default) means that the output of the model will be
the 4D tensor output of the last convolutional block.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional block, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified. Default to 1000.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
Returns:
A `keras.Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
ValueError: if `classifier_activation` is not `softmax` or `None` when
using a pretrained top layer.
"""
'''
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as `"imagenet"` with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=299,
min_size=75,
data_format=backend.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if backend.image_data_format() == 'channels_first':
channel_axis = 1
else:
channel_axis = 3
'''
channel_axis = 3
img_input = layers.Input(shape=input_shape, name="input_start")
flag = False
if partition_layer == 'input':
flag = True
x = img_input
x = conv2d_bn(x, 32, 3, 3, strides=(2, 2), padding='valid', name='1')
if flag or partition_layer == 'conv2d':
if partition_layer == 'conv2d':
x = img_input
flag = True
x = conv2d_bn(x, 32, 3, 3, padding='valid', name='2')
if flag or partition_layer == 'conv2d_1':
if partition_layer == 'conv2d_1':
x = img_input
flag = True
x = conv2d_bn(x, 64, 3, 3, name='3')
if flag or partition_layer == 'conv2d_2':
if partition_layer == 'conv2d_2':
x = img_input
flag = True
x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
if flag or partition_layer == 'max_pooling2d':
if partition_layer == 'max_pooling2d':
x = img_input
flag = True
x = conv2d_bn(x, 80, 1, 1, padding='valid', name='4')
if flag or partition_layer == 'conv2d_3':
if partition_layer == 'conv2d_3':
x = img_input
flag = True
x = conv2d_bn(x, 192, 3, 3, padding='valid', name='5')
if flag or partition_layer == 'conv2d_4':
if partition_layer == 'conv2d_4':
x = img_input
flag = True
x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
# mixed 0: 35 x 35 x 256
if flag or partition_layer == 'max_pooling2d_1':
# print("=====================partition_layer", partition_layer)
if partition_layer == 'max_pooling2d_1':
x = img_input
flag = True
branch1x1 = conv2d_bn(x, 64, 1, 1, name='6')
branch5x5 = conv2d_bn(x, 48, 1, 1, name='7')
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5, name='8')
branch3x3dbl = conv2d_bn(x, 64, 1, 1, name='9')
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3, name='10')
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3, name='11')
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 32, 1, 1, name='12')
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed0')
# mixed 1: 35 x 35 x 288
if flag or partition_layer == 'mixed0':
if partition_layer == 'mixed0':
x = img_input
flag = True
branch1x1 = conv2d_bn(x, 64, 1, 1, name='13')
branch5x5 = conv2d_bn(x, 48, 1, 1, name='14')
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5, name='15')
branch3x3dbl = conv2d_bn(x, 64, 1, 1, name='16')
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3, name='17')
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3, name='18')
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1, name='19')
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed1')
# mixed 2: 35 x 35 x 288
if flag or partition_layer == 'mixed1':
if partition_layer == 'mixed1':
x = img_input
flag = True
branch1x1 = conv2d_bn(x, 64, 1, 1, name='20')
branch5x5 = conv2d_bn(x, 48, 1, 1, name='21')
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5, name='22')
branch3x3dbl = conv2d_bn(x, 64, 1, 1, name='23')
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3, name='24')
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3, name='25')
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1, name='26')
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed2')
# mixed 3: 17 x 17 x 768
if flag or partition_layer == 'mixed2':
if partition_layer == 'mixed2':
x = img_input
flag = True
branch3x3 = conv2d_bn(x,
384,
3,
3,
strides=(2, 2),
padding='valid',
name='27')
branch3x3dbl = conv2d_bn(x, 64, 1, 1, name='28')
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3, name='29')
branch3x3dbl = conv2d_bn(branch3x3dbl,
96,
3,
3,
strides=(2, 2),
padding='valid',
name='30')
branch_pool = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate([branch3x3, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed3')
# mixed 4: 17 x 17 x 768
if flag or partition_layer == 'mixed3':
if partition_layer == 'mixed3':
x = img_input
flag = True
branch1x1 = conv2d_bn(x, 192, 1, 1, name='31')
branch7x7 = conv2d_bn(x, 128, 1, 1, name='32')
branch7x7 = conv2d_bn(branch7x7, 128, 1, 7, name='33')
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1, name='34')
branch7x7dbl = conv2d_bn(x, 128, 1, 1, name='35')
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1, name='36')
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7, name='37')
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1, name='38')
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7, name='39')
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1, name='40')
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed4')
# mixed 5, 6: 17 x 17 x 768
if flag or partition_layer == 'mixed4':
if partition_layer == 'mixed4':
x = img_input
flag = True
branch1x1 = conv2d_bn(x, 192, 1, 1, name='41')
branch7x7 = conv2d_bn(x, 160, 1, 1, name='42')
branch7x7 = conv2d_bn(branch7x7, 160, 1, 7, name='43')
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1, name='44')
branch7x7dbl = conv2d_bn(x, 160, 1, 1, name='45')
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1, name='46')
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7, name='47')
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1, name='48')
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7, name='49')
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1, name='50')
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(5))
if flag or partition_layer == 'mixed5':
if partition_layer == 'mixed5':
x = img_input
flag = True
branch1x1 = conv2d_bn(x, 192, 1, 1, name='51')
branch7x7 = conv2d_bn(x, 160, 1, 1, name='52')
branch7x7 = conv2d_bn(branch7x7, 160, 1, 7, name='53')
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1, name='54')
branch7x7dbl = conv2d_bn(x, 160, 1, 1, name='55')
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1, name='56')
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7, name='57')
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1, name='58')
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7, name='59')
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1, name='60')
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(6))
# mixed 7: 17 x 17 x 768
if flag or partition_layer == 'mixed6':
if partition_layer == 'mixed6':
flag = True
x = img_input
branch1x1 = conv2d_bn(x, 192, 1, 1, name='61')
branch7x7 = conv2d_bn(x, 192, 1, 1, name='62')
branch7x7 = conv2d_bn(branch7x7, 192, 1, 7, name='63')
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1, name='64')
branch7x7dbl = conv2d_bn(x, 192, 1, 1, name='65')
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1, name='66')
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7, name='67')
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1, name='68')
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7, name='69')
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1, name='70')
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed7')
# mixed 8: 8 x 8 x 1280
if flag or partition_layer == 'mixed7':
if partition_layer == 'mixed7':
x = img_input
flag = True
branch3x3 = conv2d_bn(x, 192, 1, 1, name='71')
branch3x3 = conv2d_bn(branch3x3,
320,
3,
3,
strides=(2, 2),
padding='valid',
name='72')
branch7x7x3 = conv2d_bn(x, 192, 1, 1, name='73')
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7, name='74')
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1, name='75')
branch7x7x3 = conv2d_bn(branch7x7x3,
192,
3,
3,
strides=(2, 2),
padding='valid',
name='76')
branch_pool = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate([branch3x3, branch7x7x3, branch_pool],
axis=channel_axis,
name='mixed8')
# mixed 9: 8 x 8 x 2048
if flag or partition_layer == 'mixed8':
if partition_layer == 'mixed8':
x = img_input
flag = True
branch1x1 = conv2d_bn(x, 320, 1, 1, name='77')
branch3x3 = conv2d_bn(x, 384, 1, 1, name='78')
branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3, name='79')
branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1, name='80')
branch3x3 = layers.concatenate([branch3x3_1, branch3x3_2],
axis=channel_axis,
name='mixed9_' + str(0))
branch3x3dbl = conv2d_bn(x, 448, 1, 1, name='81')
branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3, name='82')
branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3, name='83')
branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1, name='84')
branch3x3dbl = layers.concatenate([branch3x3dbl_1, branch3x3dbl_2],
axis=channel_axis)
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1, name='85')
x = layers.concatenate(
[branch1x1, branch3x3, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(9))
if flag or partition_layer == 'mixed9':
if partition_layer == 'mixed9':
x = img_input
flag = True
branch1x1 = conv2d_bn(x, 320, 1, 1, name='86')
branch3x3 = conv2d_bn(x, 384, 1, 1, name='87')
branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3, name='88')
branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1, name='89')
branch3x3 = layers.concatenate([branch3x3_1, branch3x3_2],
axis=channel_axis,
name='mixed9_' + str(1))
branch3x3dbl = conv2d_bn(x, 448, 1, 1, name='90')
branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3, name='91')
branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3, name='92')
branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1, name='93')
branch3x3dbl = layers.concatenate([branch3x3dbl_1, branch3x3dbl_2],
axis=channel_axis)
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1, name='94')
x = layers.concatenate(
[branch1x1, branch3x3, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(10))
if partition_layer == 'mixed10' or flag:
if partition_layer == 'mixed10':
x = img_input
flag = True
if include_top:
# Classification block
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
name='predictions')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name='inception_v3')
# Load weights.
if weights == 'imagenet':
if include_top:
weights_path = data_utils.get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
file_hash='9a0d58056eeedaa3f26cb7ebd46da564')
else:
weights_path = data_utils.get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='bcbd6486424b2319ff4ef7d526e38f63')
model.load_weights(weights_path, by_name=True, skip_mismatch=True)
elif weights is not None:
model.load_weights(weights)
return model
tf.logging.set_verbosity(tf.logging.INFO)
validation_data = data.validation.images, data.validation.labels
# Model
model = models.Sequential()
model.add(layers.InputLayer(input_shape=(img_size_flat,)))
model.add(layers.Reshape(img_shape_full))
model.add(layers.Conv2D(
kernel_size=5,
strides=1,
filters=16,
padding='same',
activation=activation,
name='layer_conv1'))
model.add(layers.MaxPooling2D(pool_size=2, strides=2))
model.add(layers.Conv2D(
kernel_size=5,
strides=1,
filters=36,
padding='same',
activation=activation,
name='layer_conv2'))
model.add(layers.MaxPooling2D(pool_size=2, strides=2))
model.add(layers.Flatten())
for i in range(num_dense_layers):
name = 'layer_dense_{0}'.format(i+1)
model.add(layers.Dense(
num_dense_nodes,
activation=activation,
name=name))
def _reduction_a_cell(ip, p, filters, block_id=None):
channel_dim = -1
with backend.name_scope('reduction_A_block_%s' % block_id):
p = _adjust_block(p, ip, filters, block_id)
h = layers.Activation('relu')(ip)
h = layers.Conv2D(filters, (1, 1),
strides=(1, 1),
padding='same',
name='reduction_conv_1_%s' % block_id,
use_bias=False,
kernel_initializer='he_normal')(h)
h = layers.BatchNormalization(axis=channel_dim,
momentum=0.9997,
epsilon=1e-3,
name='reduction_bn_1_%s' % block_id)(h)
h3 = layers.ZeroPadding2D(padding=imagenet_utils.correct_pad(h, 3),
name='reduction_pad_1_%s' % block_id)(h)
with backend.name_scope('block_1'):
x1_1 = _separable_conv_block(h,
filters, (5, 5),
strides=(2, 2),
block_id='reduction_left1_%s' %
block_id)
x1_2 = _separable_conv_block(p,
filters, (7, 7),
strides=(2, 2),
block_id='reduction_right1_%s' %
block_id)
x1 = layers.add([x1_1, x1_2], name='reduction_add_1_%s' % block_id)
with backend.name_scope('block_2'):
x2_1 = layers.MaxPooling2D(
(3, 3),
strides=(2, 2),
padding='valid',
name='reduction_left2_%s' % block_id)(h3)
x2_2 = _separable_conv_block(p,
filters, (7, 7),
strides=(2, 2),
block_id='reduction_right2_%s' %
block_id)
x2 = layers.add([x2_1, x2_2], name='reduction_add_2_%s' % block_id)
with backend.name_scope('block_3'):
x3_1 = layers.AveragePooling2D(
(3, 3),
strides=(2, 2),
padding='valid',
name='reduction_left3_%s' % block_id)(h3)
x3_2 = _separable_conv_block(p,
filters, (5, 5),
strides=(2, 2),
block_id='reduction_right3_%s' %
block_id)
x3 = layers.add([x3_1, x3_2], name='reduction_add3_%s' % block_id)
with backend.name_scope('block_4'):
x4 = layers.AveragePooling2D(
(3, 3),
strides=(1, 1),
padding='same',
name='reduction_left4_%s' % block_id)(x1)
x4 = layers.add([x2, x4])
with backend.name_scope('block_5'):
x5_1 = _separable_conv_block(x1,
filters, (3, 3),
block_id='reduction_left4_%s' %
block_id)
x5_2 = layers.MaxPooling2D(
(3, 3),
strides=(2, 2),
padding='valid',
name='reduction_right5_%s' % block_id)(h3)
x5 = layers.add([x5_1, x5_2], name='reduction_add4_%s' % block_id)
x = layers.concatenate([x2, x3, x4, x5],
axis=channel_dim,
name='reduction_concat_%s' % block_id)
return x, ip
def ResNet(stack_fn,
preact,
use_bias,
model_name='resnet',
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
**kwargs):
"""Instantiates the ResNet, ResNetV2, and ResNeXt architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
Arguments:
stack_fn: a function that returns output tensor for the
stacked residual blocks.
preact: whether to use pre-activation or not
(True for ResNetV2, False for ResNet and ResNeXt).
use_bias: whether to use biases for convolutional layers or not
(True for ResNet and ResNetV2, False for ResNeXt).
model_name: string, model name.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor
(i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels.
pooling: optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
**kwargs: For backwards compatibility only.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if 'layers' in kwargs:
global layers
layers = kwargs.pop('layers')
if kwargs:
raise ValueError('Unknown argument(s): %s' % (kwargs, ))
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError(
'If using `weights` as `"imagenet"` with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=224,
min_size=32,
data_format=backend.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)),
name='conv1_pad')(img_input)
x = layers.Conv2D(64, 7, strides=2, use_bias=use_bias,
name='conv1_conv')(x)
if not preact:
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name='conv1_bn')(x)
x = layers.Activation('relu', name='conv1_relu')(x)
x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x)
x = layers.MaxPooling2D(3, strides=2, name='pool1_pool')(x)
x = stack_fn(x)
if preact:
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name='post_bn')(x)
x = layers.Activation('relu', name='post_relu')(x)
if include_top:
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
x = layers.Dense(classes, activation='softmax', name='probs')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D(name='max_pool')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name=model_name)
# Load weights.
if (weights == 'imagenet') and (model_name in WEIGHTS_HASHES):
if include_top:
file_name = model_name + '_weights_tf_dim_ordering_tf_kernels.h5'
file_hash = WEIGHTS_HASHES[model_name][0]
else:
file_name = model_name + '_weights_tf_dim_ordering_tf_kernels_notop.h5'
file_hash = WEIGHTS_HASHES[model_name][1]
weights_path = data_utils.get_file(file_name,
BASE_WEIGHTS_PATH + file_name,
cache_subdir='models',
file_hash=file_hash)
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def ResNet(stack_fn,
use_bias,
model_name='resnet',
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
deep_stem=False,
stem_width=None,
classes=1000,
classifier_activation='softmax',
**kwargs):
"""Instantiates the ResNeSt, ResNeXt, and Wide ResNet architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
Caution: Be sure to properly pre-process your inputs to the application.
Please see `applications.resnet.preprocess_input` for an example.
Arguments:
stack_fn: a function that returns output tensor for the
stacked residual blocks.
use_bias: whether to use biases for convolutional layers or not
(True for ResNet and ResNetV2, False for ResNeXt).
model_name: string, model name.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor
(i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels.
pooling: optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
**kwargs: For backwards compatibility only.
Returns:
A `keras.Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
ValueError: if `classifier_activation` is not `softmax` or `None` when
using a pretrained top layer.
"""
if 'layers' in kwargs:
global layers
layers = kwargs.pop('layers')
if kwargs:
raise ValueError('Unknown argument(s): %s' % (kwargs,))
if not (weights in {'imagenet', 'ssl', 'swsl', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), `ssl` '
'(semi-supervised), `swsl` '
'(semi-weakly supervised), '
'or the path to the weights file to be loaded.')
if (weights == 'imagenet' or weights == 'ssl' or weights == 'swsl') and include_top and classes != 1000:
raise ValueError('If using `weights` as `"imagenet"`, '
'or `weights` as `"ssl"`, '
'or `weights` as `"swsl"`, '
'with `include_top` '
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=224,
min_size=32,
data_format=backend.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
if deep_stem:
# Deep stem based off of ResNet-D
x = layers.ZeroPadding2D(
padding=((1, 1), (1, 1)), name='conv1_0_pad')(img_input)
x = layers.Conv2D(stem_width, 3, strides=2, use_bias=use_bias, name='conv1_0_conv')(x)
x = layers.BatchNormalization(
axis=bn_axis, epsilon=1.001e-5, name='conv1_0_bn')(x)
x = layers.Activation('relu', name='conv1_0_relu')(x)
x = layers.ZeroPadding2D(
padding=((1, 1), (1, 1)), name='conv1_1_pad')(x)
x = layers.Conv2D(stem_width, 3, strides=1, use_bias=use_bias, name='conv1_1_conv')(x)
x = layers.BatchNormalization(
axis=bn_axis, epsilon=1.001e-5, name='conv1_1_bn')(x)
x = layers.Activation('relu', name='conv1_1_relu')(x)
x = layers.ZeroPadding2D(
padding=((1, 1), (1, 1)), name='conv1_2_pad')(x)
x = layers.Conv2D(stem_width * 2, 3, strides=1, use_bias=use_bias, name='conv1_2_conv')(x)
x = layers.BatchNormalization(
axis=bn_axis, epsilon=1.001e-5, name='conv1_2_bn')(x)
x = layers.Activation('relu', name='conv1_2_relu')(x)
else:
x = layers.ZeroPadding2D(
padding=((3, 3), (3, 3)), name='conv1_pad')(img_input)
x = layers.Conv2D(64, 7, strides=2, use_bias=use_bias, name='conv1_conv')(x)
x = layers.BatchNormalization(
axis=bn_axis, epsilon=1.001e-5, name='conv1_bn')(x)
x = layers.Activation('relu', name='conv1_relu')(x)
x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x)
x = layers.MaxPooling2D(3, strides=2, name='pool1_pool')(x)
x = stack_fn(x)
if include_top:
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes, activation=classifier_activation,
name='predictions')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D(name='max_pool')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name=model_name)
# Load weights.
global BASE_WEIGHTS_PATH
if 'resnest' in model_name:
BASE_WEIGHTS_PATH += 'v0.2.0/'
elif 'resnet' in model_name and 'wide' not in model_name:
BASE_WEIGHTS_PATH += 'v0.3.0/'
else:
BASE_WEIGHTS_PATH += 'v0.1.0/'
if (weights == 'imagenet') and (model_name in IMAGENET_WEIGHTS_HASHES):
if include_top:
file_name = model_name + '_imagenet_top.h5'
file_hash = IMAGENET_WEIGHTS_HASHES[model_name][0]
else:
file_name = model_name + '_imagenet_notop.h5'
file_hash = IMAGENET_WEIGHTS_HASHES[model_name][1]
weights_path = data_utils.get_file(
file_name,
BASE_WEIGHTS_PATH + file_name,
cache_subdir='models',
file_hash=file_hash)
model.load_weights(weights_path)
elif (weights == 'ssl') and (model_name in SSL_WEIGHTS_HASHES):
if include_top:
file_name = model_name + '_ssl_top.h5'
file_hash = IMAGENET_WEIGHTS_HASHES[model_name][0]
else:
file_name = model_name + '_ssl_notop.h5'
file_hash = IMAGENET_WEIGHTS_HASHES[model_name][1]
weights_path = data_utils.get_file(
file_name,
BASE_WEIGHTS_PATH + file_name,
cache_subdir='models',
file_hash=file_hash)
model.load_weights(weights_path)
elif (weights == 'swsl') and (model_name in SWSL_WEIGHTS_HASHES):
if include_top:
file_name = model_name + '_swsl_top.h5'
file_hash = SWSL_WEIGHTS_HASHES[model_name][0]
else:
file_name = model_name + '_swsl_notop.h5'
file_hash = SWSL_WEIGHTS_HASHES[model_name][1]
weights_path = data_utils.get_file(
file_name,
BASE_WEIGHTS_PATH + file_name,
cache_subdir='models',
file_hash=file_hash)
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def __init__(self, num_classes=10, dtype="float32", batch_size=None):
super(CustomModel, self).__init__(name="resnet50")
if backend.image_data_format() == "channels_first":
self._lambda = layers.Lambda(
lambda x: backend.permute_dimensions(x, (0, 3, 1, 2)),
name="transpose",
)
bn_axis = 1
data_format = "channels_first"
else:
bn_axis = 3
data_format = "channels_last"
self._padding = layers.ZeroPadding2D(padding=(3, 3),
data_format=data_format,
name="zero_pad")
self._conv2d_1 = layers.Conv2D(
64,
(7, 7),
strides=(2, 2),
padding="valid",
use_bias=False,
kernel_initializer="he_normal",
kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
name="conv1",
)
self._bn_1 = layers.BatchNormalization(
axis=bn_axis,
momentum=BATCH_NORM_DECAY,
epsilon=BATCH_NORM_EPSILON,
name="bn_conv1",
)
self._activation_1 = layers.Activation("relu")
self._maxpooling2d = layers.MaxPooling2D((3, 3),
strides=(2, 2),
padding="same")
self._conv_block_1 = ConvBlock(3, [64, 64, 256],
stage=2,
block="a",
strides=(1, 1))
self._identity_block_1 = IdentityBlock(3, [64, 64, 256],
stage=2,
block="b")
self._identity_block_2 = IdentityBlock(3, [64, 64, 256],
stage=2,
block="c")
self._conv_block_2 = ConvBlock(3, [128, 128, 512], stage=3, block="a")
self._identity_block_3 = IdentityBlock(3, [128, 128, 512],
stage=3,
block="b")
self._identity_block_4 = IdentityBlock(3, [128, 128, 512],
stage=3,
block="c")
self._identity_block_5 = IdentityBlock(3, [128, 128, 512],
stage=3,
block="d")
self._conv_block_3 = ConvBlock(3, [256, 256, 1024], stage=4, block="a")
self._identity_block_6 = IdentityBlock(3, [256, 256, 1024],
stage=4,
block="b")
self._identity_block_7 = IdentityBlock(3, [256, 256, 1024],
stage=4,
block="c")
self._identity_block_8 = IdentityBlock(3, [256, 256, 1024],
stage=4,
block="d")
self._identity_block_9 = IdentityBlock(3, [256, 256, 1024],
stage=4,
block="e")
self._identity_block_10 = IdentityBlock(3, [256, 256, 1024],
stage=4,
block="f")
self._conv_block_4 = ConvBlock(3, [512, 512, 2048], stage=5, block="a")
self._identity_block_11 = IdentityBlock(3, [512, 512, 2048],
stage=5,
block="b")
self._identity_block_12 = IdentityBlock(3, [512, 512, 2048],
stage=5,
block="c")
rm_axes = ([1, 2] if backend.image_data_format() == "channels_last"
else [2, 3])
self._lamba_2 = layers.Lambda(lambda x: backend.mean(x, rm_axes),
name="reduce_mean")
self._dense = layers.Dense(
num_classes,
kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
bias_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
name="fc1000",
)
self._activation_2 = layers.Activation("softmax")
def ResNet50(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
**kwargs):
"""Instantiates the ResNet50 architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 32.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional block.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional block, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
# global backend, layers, models, keras_utils
# backend, layers, models, keras_utils = get_submodules_from_kwargs(kwargs)
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError(
'If using `weights` as `"imagenet"` with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=32,
data_format=backend.image_data_format(),
require_flatten=include_top,
weights=weights)
with tf.name_scope("input_layer") as scope:
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor,
shape=input_shape)
else:
img_input = input_tensor
if backend.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
with tf.name_scope("resnet") as scope:
x = layers.ZeroPadding2D(padding=(3, 3), name='conv1_pad')(img_input)
x = layers.Conv2D(64, (7, 7),
strides=(2, 2),
padding='valid',
kernel_initializer='he_normal',
name='conv1')(x)
x = layers.BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = layers.Activation('relu')(x)
x = layers.ZeroPadding2D(padding=(1, 1), name='pool1_pad')(x)
x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
with tf.name_scope("module_0") as scope:
x = conv_block(x,
3, [64, 64, 256],
stage=2,
block='a',
strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
with tf.name_scope("module_1") as scope:
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
with tf.name_scope("module_2") as scope:
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
with tf.name_scope("module_3") as scope:
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
with tf.name_scope("top_layer") as scope:
if include_top:
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
x = layers.Dense(classes, activation='softmax',
name='fc1000')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D()(x)
else:
warnings.warn(
'The output shape of `ResNet50(include_top=False)` '
'has been changed since Keras 2.2.0.')
with tf.name_scope("input_layer") as scope:
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = keras_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = models.Model(inputs, x, name='resnet50')
# Load weights.
# if weights == 'imagenet':
# if include_top:
# weights_path = keras_utils.get_file(
# 'resnet50_weights_tf_dim_ordering_tf_kernels.h5',
# WEIGHTS_PATH,
# cache_subdir='models',
# md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
# else:
# weights_path = keras_utils.get_file(
# 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
# WEIGHTS_PATH_NO_TOP,
# cache_subdir='models',
# md5_hash='a268eb855778b3df3c7506639542a6af')
# model.load_weights(weights_path)
# if backend.backend() == 'theano':
# keras_utils.convert_all_kernels_in_model(model)
# elif weights is not None:
# model.load_weights(weights)
return model
import tensorflow as tf
from tensorflow.python.keras import layers
model = tf.keras.Sequential([
layers.Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)),
layers.MaxPooling2D(pool_size=(2, 2)),
layers.Dropout(0.25),
layers.Conv2D(64, (3, 3), activation='relu'),
layers.MaxPooling2D(pool_size=(2, 2)),
layers.Dropout(0.25),
layers.Conv2D(64, (3, 3), activation='relu'),
layers.MaxPooling2D(pool_size=(2, 2)),
layers.Dropout(0.25),
layers.Flatten(),
layers.Dense(256, activation='relu'),
layers.Dense(10, activation='softmax')
])
num_classes = 10
model.compile(optimizer=tf.train.RMSPropOptimizer(0.0001, decay=1e-6),
loss='categorical_crossentropy',
metrics=['accuracy'])
(trainX, trainY), (testX, testY) = tf.keras.datasets.cifar10.load_data()
trainY = tf.keras.utils.to_categorical(trainY, num_classes=num_classes)
testY = tf.keras.utils.to_categorical(testY, num_classes=num_classes)
model.fit(trainX, trainY, batch_size=32, epochs=10)
def InceptionV3(input_shape=None):
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=299,
min_size=75,
data_format=backend.image_data_format(),
require_flatten=True)
img_input = layers.Input(shape=input_shape)
if backend.image_data_format() == 'channels_first':
channel_axis = 1
else:
channel_axis = 3
x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='valid')
x = conv2d_bn(x, 32, 3, 3, padding='valid')
x = conv2d_bn(x, 64, 3, 3)
x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv2d_bn(x, 80, 1, 1, padding='valid')
x = conv2d_bn(x, 192, 3, 3, padding='valid')
x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
# mixed 0: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 32, 1, 1)
x = layers.concatenate([branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed0')
# mixed 1: 35 x 35 x 288
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate([branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed1')
# mixed 2: 35 x 35 x 288
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate([branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed2')
# mixed 3: 17 x 17 x 768
branch3x3 = conv2d_bn(x, 384, 3, 3, strides=(2, 2), padding='valid')
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl,
96,
3,
3,
strides=(2, 2),
padding='valid')
branch_pool = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate([branch3x3, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed3')
# mixed 4: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 128, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 128, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 128, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate([branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed4')
# mixed 5, 6: 17 x 17 x 768
for i in range(2):
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 160, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 160, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 160, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(5 + i))
# mixed 7: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 192, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 192, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate([branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed7')
# mixed 8: 8 x 8 x 1280
branch3x3 = conv2d_bn(x, 192, 1, 1)
branch3x3 = conv2d_bn(branch3x3,
320,
3,
3,
strides=(2, 2),
padding='valid')
branch7x7x3 = conv2d_bn(x, 192, 1, 1)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1)
branch7x7x3 = conv2d_bn(branch7x7x3,
192,
3,
3,
strides=(2, 2),
padding='valid')
branch_pool = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate([branch3x3, branch7x7x3, branch_pool],
axis=channel_axis,
name='mixed8')
# mixed 9: 8 x 8 x 2048
for i in range(2):
branch1x1 = conv2d_bn(x, 320, 1, 1)
branch3x3 = conv2d_bn(x, 384, 1, 1)
branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3)
branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1)
branch3x3 = layers.concatenate([branch3x3_1, branch3x3_2],
axis=channel_axis,
name='mixed9_' + str(i))
branch3x3dbl = conv2d_bn(x, 448, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3)
branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3)
branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1)
branch3x3dbl = layers.concatenate([branch3x3dbl_1, branch3x3dbl_2],
axis=channel_axis)
branch_pool = layers.AveragePooling2D((3, 3),
strides=(1, 1),
padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch3x3, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(9 + i))
# Classification block
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
imagenet_utils.validate_activation('softmax', None)
x = layers.Dense(NUM_CLASSES, activation='softmax', name='predictions')(x)
# Create model.
model = training.Model(img_input, x, name='inception_v3')
return model
def InceptionResNetV2(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation='softmax',
**kwargs):
"""Instantiates the Inception-ResNet v2 architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
Caution: Be sure to properly pre-process your inputs to the application.
Please see `applications.inception_resnet_v2.preprocess_input` for an example.
Arguments:
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is `False` (otherwise the input shape
has to be `(299, 299, 3)` (with `'channels_last'` data format)
or `(3, 299, 299)` (with `'channels_first'` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 75.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the last convolutional block.
- `'avg'` means that global average pooling
will be applied to the output of the
last convolutional block, and thus
the output of the model will be a 2D tensor.
- `'max'` means that global max pooling will be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is `True`, and
if no `weights` argument is specified.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
**kwargs: For backwards compatibility only.
Returns:
A `keras.Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
ValueError: if `classifier_activation` is not `softmax` or `None` when
using a pretrained top layer.
"""
if 'layers' in kwargs:
global layers
layers = kwargs.pop('layers')
if kwargs:
raise ValueError('Unknown argument(s): %s' % (kwargs, ))
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError(
'If using `weights` as `"imagenet"` with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=299,
min_size=75,
data_format=backend.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Stem block: 35 x 35 x 192
x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid')
x = conv2d_bn(x, 32, 3, padding='valid')
x = conv2d_bn(x, 64, 3)
x = layers.MaxPooling2D(3, strides=2)(x)
x = conv2d_bn(x, 80, 1, padding='valid')
x = conv2d_bn(x, 192, 3, padding='valid')
x = layers.MaxPooling2D(3, strides=2)(x)
# Mixed 5b (Inception-A block): 35 x 35 x 320
branch_0 = conv2d_bn(x, 96, 1)
branch_1 = conv2d_bn(x, 48, 1)
branch_1 = conv2d_bn(branch_1, 64, 5)
branch_2 = conv2d_bn(x, 64, 1)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_pool = layers.AveragePooling2D(3, strides=1, padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1)
branches = [branch_0, branch_1, branch_2, branch_pool]
channel_axis = 1 if backend.image_data_format() == 'channels_first' else 3
x = layers.Concatenate(axis=channel_axis, name='mixed_5b')(branches)
# 10x block35 (Inception-ResNet-A block): 35 x 35 x 320
for block_idx in range(1, 11):
x = inception_resnet_block(x,
scale=0.17,
block_type='block35',
block_idx=block_idx)
# Mixed 6a (Reduction-A block): 17 x 17 x 1088
branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 256, 3)
branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='valid')
branch_pool = layers.MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_pool]
x = layers.Concatenate(axis=channel_axis, name='mixed_6a')(branches)
# 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088
for block_idx in range(1, 21):
x = inception_resnet_block(x,
scale=0.1,
block_type='block17',
block_idx=block_idx)
# Mixed 7a (Reduction-B block): 8 x 8 x 2080
branch_0 = conv2d_bn(x, 256, 1)
branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding='valid')
branch_2 = conv2d_bn(x, 256, 1)
branch_2 = conv2d_bn(branch_2, 288, 3)
branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding='valid')
branch_pool = layers.MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_2, branch_pool]
x = layers.Concatenate(axis=channel_axis, name='mixed_7a')(branches)
# 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080
for block_idx in range(1, 10):
x = inception_resnet_block(x,
scale=0.2,
block_type='block8',
block_idx=block_idx)
x = inception_resnet_block(x,
scale=1.,
activation=None,
block_type='block8',
block_idx=10)
# Final convolution block: 8 x 8 x 1536
x = conv2d_bn(x, 1536, 1, name='conv_7b')
if include_top:
# Classification block
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
name='predictions')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name='inception_resnet_v2')
# Load weights.
if weights == 'imagenet':
if include_top:
fname = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5'
weights_path = data_utils.get_file(
fname,
BASE_WEIGHT_URL + fname,
cache_subdir='models',
file_hash='e693bd0210a403b3192acc6073ad2e96')
else:
fname = ('inception_resnet_v2_weights_'
'tf_dim_ordering_tf_kernels_notop.h5')
weights_path = data_utils.get_file(
fname,
BASE_WEIGHT_URL + fname,
cache_subdir='models',
file_hash='d19885ff4a710c122648d3b5c3b684e4')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def deep_cnn(features_shape, num_classes, activation_function='relu'):
model = models.Sequential()
model.add(
layers.InputLayer(input_shape=features_shape,
name='Inputs',
dtype='float32'))
# Block 1
model.add(
layers.Conv2D(input_shape=features_shape,
filters=32,
kernel_size=(3, 3),
strides=1,
padding='same',
activation=activation_function,
name='Block1_Convolution'))
model.add(
layers.MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='same',
name='Block1_MaxPooling'))
model.add(layers.BatchNormalization(name='Block1_BatchNormalization'))
# Block 2
model.add(
layers.Conv2D(filters=32,
kernel_size=(3, 3),
strides=1,
padding='same',
activation=activation_function,
name='Block2_Convolution'))
model.add(
layers.MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='same',
name='Block2_MaxPooling'))
model.add(layers.BatchNormalization(name='Block2_BatchNormalization'))
# Block 3
model.add(
layers.Conv2D(filters=32,
kernel_size=(3, 3),
strides=1,
padding='same',
activation=activation_function,
name='Block3_Convolution'))
model.add(
layers.MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='same',
name='Block3_MaxPooling'))
model.add(layers.BatchNormalization(name='Block3_BatchNormalization'))
# Flatten
model.add(layers.Flatten(name='Flatten'))
# Dense block
model.add(
layers.Dense(units=64,
activation=activation_function,
name='Dense_Dense'))
model.add(layers.BatchNormalization(name='Dense_BatchNormalization'))
model.add(layers.Dropout(rate=0.2, name='Dense_Dropout'))
# Predictions
model.add(
layers.Dense(units=num_classes,
activation='softmax',
name='Predictions_Dense'))
# Print network summary
model.summary()
return model
def VGG19(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the VGG19 architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
Arguments:
include_top: whether to include the 3 fully-connected
layers at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor
(i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)`
(with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 32.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional block.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional block, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as `"imagenet"` with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=224,
min_size=32,
data_format=backend.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = layers.Conv2D(
64, (3, 3), activation='relu', padding='same', name='block1_conv1')(
img_input)
x = layers.Conv2D(
64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = layers.Conv2D(
128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
x = layers.Conv2D(
128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = layers.Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
x = layers.Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
x = layers.Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
x = layers.Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv4')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = layers.Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
x = layers.Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
x = layers.Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
x = layers.Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv4')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = layers.Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
x = layers.Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
x = layers.Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)
x = layers.Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv4')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = layers.Flatten(name='flatten')(x)
x = layers.Dense(4096, activation='relu', name='fc1')(x)
x = layers.Dense(4096, activation='relu', name='fc2')(x)
x = layers.Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name='vgg19')
# Load weights.
if weights == 'imagenet':
if include_top:
weights_path = data_utils.get_file(
'vgg19_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
file_hash='cbe5617147190e668d6c5d5026f83318')
else:
weights_path = data_utils.get_file(
'vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='253f8cb515780f3b799900260a226db6')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
x_train /= 255.0
x_test /= 255.0
# Convert class vectors to class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
# Define model
model = keras.Sequential()
model.add(
layers.Convolution2D(16, (3, 3),
padding='same',
input_shape=x_train.shape[1:],
activation='relu'))
model.add(layers.MaxPooling2D(pool_size=(2, 2)))
model.add(layers.Convolution2D(32, (3, 3), padding='same', activation='relu'))
model.add(layers.MaxPooling2D(pool_size=(2, 2)))
model.add(layers.Convolution2D(64, (3, 3), padding='same', activation='relu'))
model.add(layers.MaxPooling2D(pool_size=(2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(128, activation='relu'))
model.add(layers.Dense(100, activation='softmax'))
# Train model
adam = tf.optimizers.Adam()
model.compile(loss='categorical_crossentropy',
optimizer=adam,
metrics=['top_k_categorical_accuracy'])
print(model.summary())
import tensorflow as tf from tensorflow.python.keras.models import Model from tensorflow.python.keras import layers from tensorflow.python.keras import backend from tensorflow.python.keras.optimizer_v2.adam import Adam from tensorflow.python.keras.optimizer_v2.rmsprop import RMSprop from tensorflow.python.keras.callbacks import TensorBoard from dataset import IMG_HEIGHT, IMG_WIDTH, letters, BATCH_SIZE backend.clear_session() img_input = layers.Input(shape=(IMG_HEIGHT, IMG_WIDTH, 1)) x = layers.Conv2D(32, 3, activation="relu")(img_input) x = layers.Conv2D(64, 3, activation="relu")(x) x = layers.MaxPooling2D(2, 2)(x) x = layers.Dropout(0.25)(x) x = layers.Flatten()(x) x = layers.Dense(128, activation="relu")(x) x = layers.Dropout(0.5)(x) output = layers.Dense(52, activation="softmax")(x) model = Model(img_input, output) model.compile(loss="categorical_cross", optimizer=Adam(), metrics=['accuracy']) training_set=list(filter(lambda letter: random.random() < 0.6, letters)) validation_set=list(filter(lambda cur: random.random() < 0.05, map(lambda letter: (letter.input, letter.output), letters))) model.fit(
def resnet50(num_classes, dtype='float32', batch_size=None):
# TODO(tfboyd): add training argument, just lik resnet56.
"""Instantiates the ResNet50 architecture.
Args:
num_classes: `int` number of classes for image classification.
Returns:
A Keras model instance.
"""
input_shape = (224, 224, 3)
img_input = layers.Input(shape=input_shape,
dtype=dtype,
batch_size=batch_size)
if backend.image_data_format() == 'channels_first':
x = layers.Lambda(
lambda x: backend.permute_dimensions(x, (0, 3, 1, 2)),
name='transpose')(img_input)
bn_axis = 1
else: # channels_last
x = img_input
bn_axis = 3
x = layers.ZeroPadding2D(padding=(3, 3), name='conv1_pad')(x)
x = layers.Conv2D(64, (7, 7),
strides=(2, 2),
padding='valid',
use_bias=False,
kernel_initializer='he_normal',
kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
name='conv1')(x)
x = layers.BatchNormalization(axis=bn_axis,
scale=False,
momentum=BATCH_NORM_DECAY,
epsilon=BATCH_NORM_EPSILON,
name='bn_conv1')(x)
x = layers.Activation('relu')(x)
x = layers.ZeroPadding2D(padding=(1, 1), name='pool1_pad')(x)
x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
x = layers.Dense(num_classes,
kernel_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
bias_regularizer=regularizers.l2(L2_WEIGHT_DECAY),
name='fc1000')(x)
# TODO(reedwm): Remove manual casts once mixed precision can be enabled with a
# single line of code.
x = backend.cast(x, 'float32')
x = layers.Activation('softmax')(x)
# Create model.
return models.Model(img_input, x, name='resnet50')
def encoder_block(input_tensor, num_filters):
encoder = conv_block(input_tensor, num_filters)
encoder_pool = layers.MaxPooling2D((1, 2), strides=(1, 2))(encoder)
return encoder_pool, encoder
def DenseNet(blocks,
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the DenseNet architecture.
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at `~/.keras/keras.json`.
Arguments:
blocks: numbers of building blocks for the four dense layers.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor
(i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `'channels_last'` data format)
or `(3, 224, 224)` (with `'channels_first'` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 32.
E.g. `(200, 200, 3)` would be one valid value.
pooling: optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional block.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional block, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError(
'If using `weights` as `"imagenet"` with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=224,
min_size=32,
data_format=backend.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)))(img_input)
x = layers.Conv2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x)
x = layers.BatchNormalization(axis=bn_axis,
epsilon=1.001e-5,
name='conv1/bn')(x)
x = layers.Activation('relu', name='conv1/relu')(x)
x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)))(x)
x = layers.MaxPooling2D(3, strides=2, name='pool1')(x)
x = dense_block(x, blocks[0], name='conv2')
x = transition_block(x, 0.5, name='pool2')
x = dense_block(x, blocks[1], name='conv3')
x = transition_block(x, 0.5, name='pool3')
x = dense_block(x, blocks[2], name='conv4')
x = transition_block(x, 0.5, name='pool4')
x = dense_block(x, blocks[3], name='conv5')
x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='bn')(x)
x = layers.Activation('relu', name='relu')(x)
if include_top:
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
x = layers.Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D(name='max_pool')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
if blocks == [6, 12, 24, 16]:
model = training.Model(inputs, x, name='densenet121')
elif blocks == [6, 12, 32, 32]:
model = training.Model(inputs, x, name='densenet169')
elif blocks == [6, 12, 48, 32]:
model = training.Model(inputs, x, name='densenet201')
else:
model = training.Model(inputs, x, name='densenet')
# Load weights.
if weights == 'imagenet':
if include_top:
if blocks == [6, 12, 24, 16]:
weights_path = data_utils.get_file(
'densenet121_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET121_WEIGHT_PATH,
cache_subdir='models',
file_hash='9d60b8095a5708f2dcce2bca79d332c7')
elif blocks == [6, 12, 32, 32]:
weights_path = data_utils.get_file(
'densenet169_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET169_WEIGHT_PATH,
cache_subdir='models',
file_hash='d699b8f76981ab1b30698df4c175e90b')
elif blocks == [6, 12, 48, 32]:
weights_path = data_utils.get_file(
'densenet201_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET201_WEIGHT_PATH,
cache_subdir='models',
file_hash='1ceb130c1ea1b78c3bf6114dbdfd8807')
else:
if blocks == [6, 12, 24, 16]:
weights_path = data_utils.get_file(
'densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET121_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='30ee3e1110167f948a6b9946edeeb738')
elif blocks == [6, 12, 32, 32]:
weights_path = data_utils.get_file(
'densenet169_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET169_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='b8c4d4c20dd625c148057b9ff1c1176b')
elif blocks == [6, 12, 48, 32]:
weights_path = data_utils.get_file(
'densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET201_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='c13680b51ded0fb44dff2d8f86ac8bb1')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
# MODEL WEAK FOREGROUNDS
#################################################################
##CNN model
model = tf.keras.Sequential()
model.add(
layers.Conv2D(16, (7, 7),
input_shape=(size, size, 1),
strides=(1, 1),
padding='same'))
model.add(layers.BatchNormalization())
model.add(layers.Activation('relu'))
model.add(layers.Conv2D(32, (7, 7), padding='same'))
model.add(layers.BatchNormalization())
model.add(layers.Activation('relu'))
model.add(layers.MaxPooling2D((2, 2), strides=(2, 2)))
model.add(layers.Activation('relu'))
model.add(layers.Conv2DTranspose(64, (5, 5), strides=(2, 2), padding='same'))
model.add(layers.BatchNormalization())
model.add(layers.Activation('relu'))
model.add(layers.Conv2D(1, (1, 1), activation='sigmoid'))
model.compile(optimizer=tf.keras.optimizers.Adam(0.01),
loss='binary_crossentropy',
metrics=[tf.keras.metrics.BinaryAccuracy()])
model.summary()
history = model.fit(data_full[:lenj, :, :, :],
data_label[:lenj, :, :, :],
epochs=12,
batch_size=50,
def VGG16(
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation='softmax',
):
"""Instantiates the VGG16 model.
By default, it loads weights pre-trained on ImageNet. Check 'weights' for
other options.
This model can be built both with 'channels_first' data format
(channels, height, width) or 'channels_last' data format
(height, width, channels).
The default input size for this model is 224x224.
Caution: Be sure to properly pre-process your inputs to the application.
Please see `applications.vgg16.preprocess_input` for an example.
Arguments:
include_top: whether to include the 3 fully-connected
layers at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor
(i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)`
(with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 input channels,
and width and height should be no smaller than 32.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional block.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional block, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
Returns:
A `keras.Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
ValueError: if `classifier_activation` is not `softmax` or `None` when
using a pretrained top layer.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError(
'If using `weights` as `"imagenet"` with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=224,
min_size=32,
data_format=backend.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = layers.Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv1')(img_input)
x = layers.Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv2')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = layers.Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv1')(x)
x = layers.Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv2')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = layers.Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv1')(x)
x = layers.Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv2')(x)
x = layers.Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv3')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv1')(x)
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv2')(x)
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv3')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv1')(x)
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv2')(x)
x = layers.Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv3')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = layers.Flatten(name='flatten')(x)
x = layers.Dense(4096, activation='relu', name='fc1')(x)
x = layers.Dense(4096, activation='relu', name='fc2')(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes,
activation=classifier_activation,
name='predictions')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name='vgg16')
# Load weights.
if weights == 'imagenet':
if include_top:
weights_path = data_utils.get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
file_hash='64373286793e3c8b2b4e3219cbf3544b')
else:
weights_path = data_utils.get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='6d6bbae143d832006294945121d1f1fc')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
