Python keras.layers.pooling.MaxPooling2D() Examples
The following are 30
code examples of keras.layers.pooling.MaxPooling2D().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
keras.layers.pooling
, or try the search function
.
.
Example #1
| Source File: inception_blocks_v2.py From Coursera-Ng-Convolutional-Neural-Networks with MIT License | 6 votes |
|
def inception_block_3b(X):
X_3x3 = fr_utils.conv2d_bn(X,
layer='inception_5b_3x3',
cv1_out=96,
cv1_filter=(1, 1),
cv2_out=384,
cv2_filter=(3, 3),
cv2_strides=(1, 1),
padding=(1, 1))
X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
X_pool = fr_utils.conv2d_bn(X_pool,
layer='inception_5b_pool',
cv1_out=96,
cv1_filter=(1, 1))
X_pool = ZeroPadding2D(padding=(1, 1), data_format='channels_first')(X_pool)
X_1x1 = fr_utils.conv2d_bn(X,
layer='inception_5b_1x1',
cv1_out=256,
cv1_filter=(1, 1))
inception = concatenate([X_3x3, X_pool, X_1x1], axis=1)
return inception
Example #2
| Source File: se_resnext.py From TF.Keras-Commonly-used-models with Apache License 2.0 | 6 votes |
|
def __initial_conv_block_inception(input, weight_decay=5e-4):
''' Adds an initial conv block, with batch norm and relu for the inception resnext
Args:
input: input tensor
weight_decay: weight decay factor
Returns: a keras tensor
'''
channel_axis = 1 if K.image_data_format() == 'channels_first' else -1
x = Conv2D(64, (7, 7), padding='same', use_bias=False, kernel_initializer='he_normal',
kernel_regularizer=l2(weight_decay), strides=(2, 2))(input)
x = BatchNormalization(axis=channel_axis)(x)
x = LeakyReLU()(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
return x
Example #3
| Source File: inception_blocks.py From keras-face with MIT License | 6 votes |
|
def inception_block_1c(X):
X_3x3 = fr_utils.conv2d_bn(X,
layer='inception_3c_3x3',
cv1_out=128,
cv1_filter=(1, 1),
cv2_out=256,
cv2_filter=(3, 3),
cv2_strides=(2, 2),
padding=(1, 1))
X_5x5 = fr_utils.conv2d_bn(X,
layer='inception_3c_5x5',
cv1_out=32,
cv1_filter=(1, 1),
cv2_out=64,
cv2_filter=(5, 5),
cv2_strides=(2, 2),
padding=(2, 2))
X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
X_pool = ZeroPadding2D(padding=((0, 1), (0, 1)), data_format='channels_first')(X_pool)
inception = concatenate([X_3x3, X_5x5, X_pool], axis=1)
return inception
Example #4
| Source File: inception_blocks.py From keras-face with MIT License | 6 votes |
|
def inception_block_2b(X):
#inception4e
X_3x3 = fr_utils.conv2d_bn(X,
layer='inception_4e_3x3',
cv1_out=160,
cv1_filter=(1, 1),
cv2_out=256,
cv2_filter=(3, 3),
cv2_strides=(2, 2),
padding=(1, 1))
X_5x5 = fr_utils.conv2d_bn(X,
layer='inception_4e_5x5',
cv1_out=64,
cv1_filter=(1, 1),
cv2_out=128,
cv2_filter=(5, 5),
cv2_strides=(2, 2),
padding=(2, 2))
X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
X_pool = ZeroPadding2D(padding=((0, 1), (0, 1)), data_format='channels_first')(X_pool)
inception = concatenate([X_3x3, X_5x5, X_pool], axis=1)
return inception
Example #5
| Source File: inception_blocks.py From keras-face with MIT License | 6 votes |
|
def inception_block_3b(X):
X_3x3 = fr_utils.conv2d_bn(X,
layer='inception_5b_3x3',
cv1_out=96,
cv1_filter=(1, 1),
cv2_out=384,
cv2_filter=(3, 3),
cv2_strides=(1, 1),
padding=(1, 1))
X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
X_pool = fr_utils.conv2d_bn(X_pool,
layer='inception_5b_pool',
cv1_out=96,
cv1_filter=(1, 1))
X_pool = ZeroPadding2D(padding=(1, 1), data_format='channels_first')(X_pool)
X_1x1 = fr_utils.conv2d_bn(X,
layer='inception_5b_1x1',
cv1_out=256,
cv1_filter=(1, 1))
inception = concatenate([X_3x3, X_pool, X_1x1], axis=1)
return inception
Example #6
| Source File: inception_blocks_v2.py From Facial-Recognition-using-Facenet with MIT License | 6 votes |
|
def inception_block_3b(X):
X_3x3 = fr_utils.conv2d_bn(X,
layer='inception_5b_3x3',
cv1_out=96,
cv1_filter=(1, 1),
cv2_out=384,
cv2_filter=(3, 3),
cv2_strides=(1, 1),
padding=(1, 1))
X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
X_pool = fr_utils.conv2d_bn(X_pool,
layer='inception_5b_pool',
cv1_out=96,
cv1_filter=(1, 1))
X_pool = ZeroPadding2D(padding=(1, 1), data_format='channels_first')(X_pool)
X_1x1 = fr_utils.conv2d_bn(X,
layer='inception_5b_1x1',
cv1_out=256,
cv1_filter=(1, 1))
inception = concatenate([X_3x3, X_pool, X_1x1], axis=1)
return inception
Example #7
| Source File: inception_blocks_v2.py From Facial-Recognition-using-Facenet with MIT License | 6 votes |
|
def inception_block_2b(X):
#inception4e
X_3x3 = fr_utils.conv2d_bn(X,
layer='inception_4e_3x3',
cv1_out=160,
cv1_filter=(1, 1),
cv2_out=256,
cv2_filter=(3, 3),
cv2_strides=(2, 2),
padding=(1, 1))
X_5x5 = fr_utils.conv2d_bn(X,
layer='inception_4e_5x5',
cv1_out=64,
cv1_filter=(1, 1),
cv2_out=128,
cv2_filter=(5, 5),
cv2_strides=(2, 2),
padding=(2, 2))
X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
X_pool = ZeroPadding2D(padding=((0, 1), (0, 1)), data_format='channels_first')(X_pool)
inception = concatenate([X_3x3, X_5x5, X_pool], axis=1)
return inception
Example #8
| Source File: inception_blocks_v2.py From Facial-Recognition-using-Facenet with MIT License | 6 votes |
|
def inception_block_1c(X):
X_3x3 = fr_utils.conv2d_bn(X,
layer='inception_3c_3x3',
cv1_out=128,
cv1_filter=(1, 1),
cv2_out=256,
cv2_filter=(3, 3),
cv2_strides=(2, 2),
padding=(1, 1))
X_5x5 = fr_utils.conv2d_bn(X,
layer='inception_3c_5x5',
cv1_out=32,
cv1_filter=(1, 1),
cv2_out=64,
cv2_filter=(5, 5),
cv2_strides=(2, 2),
padding=(2, 2))
X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
X_pool = ZeroPadding2D(padding=((0, 1), (0, 1)), data_format='channels_first')(X_pool)
inception = concatenate([X_3x3, X_5x5, X_pool], axis=1)
return inception
Example #9
| Source File: inception_blocks_v2.py From keras-face with MIT License | 6 votes |
|
def inception_block_2b(X):
#inception4e
X_3x3 = fr_utils.conv2d_bn(X,
layer='inception_4e_3x3',
cv1_out=160,
cv1_filter=(1, 1),
cv2_out=256,
cv2_filter=(3, 3),
cv2_strides=(2, 2),
padding=(1, 1))
X_5x5 = fr_utils.conv2d_bn(X,
layer='inception_4e_5x5',
cv1_out=64,
cv1_filter=(1, 1),
cv2_out=128,
cv2_filter=(5, 5),
cv2_strides=(2, 2),
padding=(2, 2))
X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
X_pool = ZeroPadding2D(padding=((0, 1), (0, 1)), data_format='channels_first')(X_pool)
inception = concatenate([X_3x3, X_5x5, X_pool], axis=1)
return inception
Example #10
| Source File: inception_blocks_v2.py From keras-face with MIT License | 6 votes |
|
def inception_block_3b(X):
X_3x3 = fr_utils.conv2d_bn(X,
layer='inception_5b_3x3',
cv1_out=96,
cv1_filter=(1, 1),
cv2_out=384,
cv2_filter=(3, 3),
cv2_strides=(1, 1),
padding=(1, 1))
X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
X_pool = fr_utils.conv2d_bn(X_pool,
layer='inception_5b_pool',
cv1_out=96,
cv1_filter=(1, 1))
X_pool = ZeroPadding2D(padding=(1, 1), data_format='channels_first')(X_pool)
X_1x1 = fr_utils.conv2d_bn(X,
layer='inception_5b_1x1',
cv1_out=256,
cv1_filter=(1, 1))
inception = concatenate([X_3x3, X_pool, X_1x1], axis=1)
return inception
Example #11
| Source File: resnext-checkpoint.py From CBAM-keras with MIT License | 6 votes |
|
def __initial_conv_block_inception(input, weight_decay=5e-4):
''' Adds an initial conv block, with batch norm and relu for the inception resnext
Args:
input: input tensor
weight_decay: weight decay factor
Returns: a keras tensor
'''
channel_axis = 1 if K.image_data_format() == 'channels_first' else -1
x = Conv2D(64, (7, 7), padding='same', use_bias=False, kernel_initializer='he_normal',
kernel_regularizer=l2(weight_decay), strides=(2, 2))(input)
x = BatchNormalization(axis=channel_axis)(x)
x = LeakyReLU()(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
return x
Example #12
| Source File: resnext.py From CBAM-keras with MIT License | 6 votes |
|
def __initial_conv_block_inception(input, weight_decay=5e-4):
''' Adds an initial conv block, with batch norm and relu for the inception resnext
Args:
input: input tensor
weight_decay: weight decay factor
Returns: a keras tensor
'''
channel_axis = 1 if K.image_data_format() == 'channels_first' else -1
x = Conv2D(64, (7, 7), padding='same', use_bias=False, kernel_initializer='he_normal',
kernel_regularizer=l2(weight_decay), strides=(2, 2))(input)
x = BatchNormalization(axis=channel_axis)(x)
x = LeakyReLU()(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
return x
Example #13
| Source File: inception_blocks_v2.py From Coursera-Ng-Convolutional-Neural-Networks with MIT License | 6 votes |
|
def inception_block_1c(X):
X_3x3 = fr_utils.conv2d_bn(X,
layer='inception_3c_3x3',
cv1_out=128,
cv1_filter=(1, 1),
cv2_out=256,
cv2_filter=(3, 3),
cv2_strides=(2, 2),
padding=(1, 1))
X_5x5 = fr_utils.conv2d_bn(X,
layer='inception_3c_5x5',
cv1_out=32,
cv1_filter=(1, 1),
cv2_out=64,
cv2_filter=(5, 5),
cv2_strides=(2, 2),
padding=(2, 2))
X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
X_pool = ZeroPadding2D(padding=((0, 1), (0, 1)), data_format='channels_first')(X_pool)
inception = concatenate([X_3x3, X_5x5, X_pool], axis=1)
return inception
Example #14
| Source File: inception_blocks_v2.py From Coursera-Ng-Convolutional-Neural-Networks with MIT License | 6 votes |
|
def inception_block_2b(X):
#inception4e
X_3x3 = fr_utils.conv2d_bn(X,
layer='inception_4e_3x3',
cv1_out=160,
cv1_filter=(1, 1),
cv2_out=256,
cv2_filter=(3, 3),
cv2_strides=(2, 2),
padding=(1, 1))
X_5x5 = fr_utils.conv2d_bn(X,
layer='inception_4e_5x5',
cv1_out=64,
cv1_filter=(1, 1),
cv2_out=128,
cv2_filter=(5, 5),
cv2_strides=(2, 2),
padding=(2, 2))
X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
X_pool = ZeroPadding2D(padding=((0, 1), (0, 1)), data_format='channels_first')(X_pool)
inception = concatenate([X_3x3, X_5x5, X_pool], axis=1)
return inception
Example #15
| Source File: read_keypoint.py From poseGuidedImgGeneration with MIT License | 5 votes |
|
def pooling(x, ks, st, name):
x = MaxPooling2D((ks, ks), strides=(st, st), name=name)(x)
return x
Example #16
| Source File: inception_blocks_v2.py From keras-face with MIT License | 5 votes |
|
def inception_block_1a(X):
"""
Implementation of an inception block
"""
X_3x3 = Conv2D(96, (1, 1), data_format='channels_first', name ='inception_3a_3x3_conv1')(X)
X_3x3 = BatchNormalization(axis=1, epsilon=0.00001, name = 'inception_3a_3x3_bn1')(X_3x3)
X_3x3 = Activation('relu')(X_3x3)
X_3x3 = ZeroPadding2D(padding=(1, 1), data_format='channels_first')(X_3x3)
X_3x3 = Conv2D(128, (3, 3), data_format='channels_first', name='inception_3a_3x3_conv2')(X_3x3)
X_3x3 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_3x3_bn2')(X_3x3)
X_3x3 = Activation('relu')(X_3x3)
X_5x5 = Conv2D(16, (1, 1), data_format='channels_first', name='inception_3a_5x5_conv1')(X)
X_5x5 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_5x5_bn1')(X_5x5)
X_5x5 = Activation('relu')(X_5x5)
X_5x5 = ZeroPadding2D(padding=(2, 2), data_format='channels_first')(X_5x5)
X_5x5 = Conv2D(32, (5, 5), data_format='channels_first', name='inception_3a_5x5_conv2')(X_5x5)
X_5x5 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_5x5_bn2')(X_5x5)
X_5x5 = Activation('relu')(X_5x5)
X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
X_pool = Conv2D(32, (1, 1), data_format='channels_first', name='inception_3a_pool_conv')(X_pool)
X_pool = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_pool_bn')(X_pool)
X_pool = Activation('relu')(X_pool)
X_pool = ZeroPadding2D(padding=((3, 4), (3, 4)), data_format='channels_first')(X_pool)
X_1x1 = Conv2D(64, (1, 1), data_format='channels_first', name='inception_3a_1x1_conv')(X)
X_1x1 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_1x1_bn')(X_1x1)
X_1x1 = Activation('relu')(X_1x1)
# CONCAT
inception = concatenate([X_3x3, X_5x5, X_pool, X_1x1], axis=1)
return inception
Example #17
| Source File: inception_blocks_v2.py From Coursera-Ng-Convolutional-Neural-Networks with MIT License | 5 votes |
|
def inception_block_1a(X):
"""
Implementation of an inception block
"""
X_3x3 = Conv2D(96, (1, 1), data_format='channels_first', name ='inception_3a_3x3_conv1')(X)
X_3x3 = BatchNormalization(axis=1, epsilon=0.00001, name = 'inception_3a_3x3_bn1')(X_3x3)
X_3x3 = Activation('relu')(X_3x3)
X_3x3 = ZeroPadding2D(padding=(1, 1), data_format='channels_first')(X_3x3)
X_3x3 = Conv2D(128, (3, 3), data_format='channels_first', name='inception_3a_3x3_conv2')(X_3x3)
X_3x3 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_3x3_bn2')(X_3x3)
X_3x3 = Activation('relu')(X_3x3)
X_5x5 = Conv2D(16, (1, 1), data_format='channels_first', name='inception_3a_5x5_conv1')(X)
X_5x5 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_5x5_bn1')(X_5x5)
X_5x5 = Activation('relu')(X_5x5)
X_5x5 = ZeroPadding2D(padding=(2, 2), data_format='channels_first')(X_5x5)
X_5x5 = Conv2D(32, (5, 5), data_format='channels_first', name='inception_3a_5x5_conv2')(X_5x5)
X_5x5 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_5x5_bn2')(X_5x5)
X_5x5 = Activation('relu')(X_5x5)
X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
X_pool = Conv2D(32, (1, 1), data_format='channels_first', name='inception_3a_pool_conv')(X_pool)
X_pool = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_pool_bn')(X_pool)
X_pool = Activation('relu')(X_pool)
X_pool = ZeroPadding2D(padding=((3, 4), (3, 4)), data_format='channels_first')(X_pool)
X_1x1 = Conv2D(64, (1, 1), data_format='channels_first', name='inception_3a_1x1_conv')(X)
X_1x1 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_1x1_bn')(X_1x1)
X_1x1 = Activation('relu')(X_1x1)
# CONCAT
inception = concatenate([X_3x3, X_5x5, X_pool, X_1x1], axis=1)
return inception
Example #18
| Source File: inception_blocks.py From keras-face with MIT License | 5 votes |
|
def inception_block_1a(X):
"""
Implementation of an inception block
"""
X_3x3 = Conv2D(96, (1, 1), data_format='channels_first', name ='inception_3a_3x3_conv1')(X)
X_3x3 = BatchNormalization(axis=1, epsilon=0.00001, name = 'inception_3a_3x3_bn1')(X_3x3)
X_3x3 = Activation('relu')(X_3x3)
X_3x3 = ZeroPadding2D(padding=(1, 1), data_format='channels_first')(X_3x3)
X_3x3 = Conv2D(128, (3, 3), data_format='channels_first', name='inception_3a_3x3_conv2')(X_3x3)
X_3x3 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_3x3_bn2')(X_3x3)
X_3x3 = Activation('relu')(X_3x3)
X_5x5 = Conv2D(16, (1, 1), data_format='channels_first', name='inception_3a_5x5_conv1')(X)
X_5x5 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_5x5_bn1')(X_5x5)
X_5x5 = Activation('relu')(X_5x5)
X_5x5 = ZeroPadding2D(padding=(2, 2), data_format='channels_first')(X_5x5)
X_5x5 = Conv2D(32, (5, 5), data_format='channels_first', name='inception_3a_5x5_conv2')(X_5x5)
X_5x5 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_5x5_bn2')(X_5x5)
X_5x5 = Activation('relu')(X_5x5)
X_pool = MaxPooling2D(pool_size=3, strides=2, data_format='channels_first')(X)
X_pool = Conv2D(32, (1, 1), data_format='channels_first', name='inception_3a_pool_conv')(X_pool)
X_pool = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_pool_bn')(X_pool)
X_pool = Activation('relu')(X_pool)
X_pool = ZeroPadding2D(padding=((3, 4), (3, 4)), data_format='channels_first')(X_pool)
X_1x1 = Conv2D(64, (1, 1), data_format='channels_first', name='inception_3a_1x1_conv')(X)
X_1x1 = BatchNormalization(axis=1, epsilon=0.00001, name='inception_3a_1x1_bn')(X_1x1)
X_1x1 = Activation('relu')(X_1x1)
# CONCAT
inception = concatenate([X_3x3, X_5x5, X_pool, X_1x1], axis=1)
return inception
Example #19
| Source File: topcoder_crnn.py From crnn-lid with GNU General Public License v3.0 | 5 votes |
|
def create_model(input_shape, config, is_training=True):
weight_decay = 0.001
model = Sequential()
model.add(Convolution2D(16, 7, 7, W_regularizer=l2(weight_decay), activation="relu", input_shape=input_shape))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(32, 5, 5, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(64, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(128, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(256, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
# (bs, y, x, c) --> (bs, x, y, c)
model.add(Permute((2, 1, 3)))
# (bs, x, y, c) --> (bs, x, y * c)
bs, x, y, c = model.layers[-1].output_shape
model.add(Reshape((x, y*c)))
model.add(Bidirectional(LSTM(512, return_sequences=False), merge_mode="concat"))
model.add(Dense(config["num_classes"], activation="softmax"))
return model
Example #20
| Source File: densenet.py From DIIN-in-Keras with MIT License | 5 votes |
|
def __transition_block(self, x, nb_filter, compression, apply_batch_norm):
if apply_batch_norm:
x = BatchNormalization(axis=self.concat_axis, epsilon=1.1e-5)(x)
x = Conv2D(int(nb_filter * compression), (1, 1), padding='same', activation=None)(x)
x = MaxPooling2D(strides=(2, 2))(x)
return x
Example #21
| Source File: models.py From DeepLearningImplementations with MIT License | 5 votes |
|
def standard_conv_block(x, nb_filter, strides=(1,1), pooling=False, bn=False, dropout_rate=None, weight_decay=0):
x = Conv2D(nb_filter, (3, 3),
strides=strides,
padding="same",
kernel_regularizer=l2(weight_decay))(x)
if bn:
x = BatchNormalization(mode=2, axis=1)(x)
x = Activation("relu")(x)
if pooling:
x = MaxPooling2D()(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
return x
Example #22
| Source File: encoder.py From enet-keras with MIT License | 5 votes |
|
def initial_block(inp, nb_filter=13, nb_row=3, nb_col=3, strides=(2, 2)):
conv = Conv2D(nb_filter, (nb_row, nb_col), padding='same', strides=strides)(inp)
max_pool = MaxPooling2D()(inp)
merged = concatenate([conv, max_pool], axis=3)
return merged
Example #23
| Source File: MaskRCNN.py From PyTorch-Luna16 with Apache License 2.0 | 5 votes |
|
def resnet_graph(input_image, architecture, stage5=False):
assert architecture in ["resnet50", "resnet101"]
# Stage 1
x = ZeroPadding2D((3, 3))(input_image)
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1', use_bias=True)(x)
x = BatchNorm(axis=3, name='bn_conv1')(x)
x = Activation('relu')(x)
C1 = x = MaxPooling2D((3, 3), strides=(2, 2), padding="same")(x)
# Stage 2
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')
C2 = x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
# Stage 3
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')
C3 = x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
# Stage 4
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
block_count = {"resnet50": 5, "resnet101": 22}[architecture]
for i in range(block_count):
x = identity_block(x, 3, [256, 256, 1024], stage=4, block=chr(98 + i))
C4 = x
# Stage 5
if stage5:
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
C5 = x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
else:
C5 = None
return [C1, C2, C3, C4, C5]
############################################################
# Proposal Layer
############################################################
Example #24
| Source File: network_agent.py From Multi-Commander with Apache License 2.0 | 5 votes |
|
def conv2d_bn(input_layer, index_layer,
filters=16,
kernel_size=(3, 3),
strides=(1, 1)):
"""Utility function to apply conv + BN.
# Arguments
x: input tensor.
filters: filters in `Conv2D`.
num_row: height of the convolution kernel.
num_col: width of the convolution kernel.
padding: padding mode in `Conv2D`.
strides: strides in `Conv2D`.
name: name of the ops; will become `name + '_conv'`
for the convolution and `name + '_bn'` for the
batch norm layer.
# Returns
Output tensor after applying `Conv2D` and `BatchNormalization`.
"""
if K.image_data_format() == 'channels_first':
bn_axis = 1
else:
bn_axis = 3
conv = Conv2D(filters=filters,
kernel_size=kernel_size,
strides=strides,
padding='same',
use_bias=False,
name="conv{0}".format(index_layer))(input_layer)
bn = BatchNormalization(axis=bn_axis, scale=False, name="bn{0}".format(index_layer))(conv)
act = Activation('relu', name="act{0}".format(index_layer))(bn)
pooling = MaxPooling2D(pool_size=2)(act)
x = Dropout(0.3)(pooling)
return x
Example #25
| Source File: models.py From kaggle-carvana-2017 with MIT License | 5 votes |
|
def get_simple_unet(input_shape):
img_input = Input(input_shape)
conv1 = conv_block_simple(img_input, 32, "conv1_1")
conv1 = conv_block_simple(conv1, 32, "conv1_2")
pool1 = MaxPooling2D((2, 2), strides=(2, 2), padding="same", name="pool1")(conv1)
conv2 = conv_block_simple(pool1, 64, "conv2_1")
conv2 = conv_block_simple(conv2, 64, "conv2_2")
pool2 = MaxPooling2D((2, 2), strides=(2, 2), padding="same", name="pool2")(conv2)
conv3 = conv_block_simple(pool2, 128, "conv3_1")
conv3 = conv_block_simple(conv3, 128, "conv3_2")
pool3 = MaxPooling2D((2, 2), strides=(2, 2), padding="same", name="pool3")(conv3)
conv4 = conv_block_simple(pool3, 256, "conv4_1")
conv4 = conv_block_simple(conv4, 256, "conv4_2")
conv4 = conv_block_simple(conv4, 256, "conv4_3")
up5 = concatenate([UpSampling2D()(conv4), conv3], axis=-1)
conv5 = conv_block_simple(up5, 128, "conv5_1")
conv5 = conv_block_simple(conv5, 128, "conv5_2")
up6 = concatenate([UpSampling2D()(conv5), conv2], axis=-1)
conv6 = conv_block_simple(up6, 64, "conv6_1")
conv6 = conv_block_simple(conv6, 64, "conv6_2")
up7 = concatenate([UpSampling2D()(conv6), conv1], axis=-1)
conv7 = conv_block_simple(up7, 32, "conv7_1")
conv7 = conv_block_simple(conv7, 32, "conv7_2")
conv7 = SpatialDropout2D(0.2)(conv7)
prediction = Conv2D(1, (1, 1), activation="sigmoid", name="prediction")(conv7)
model = Model(img_input, prediction)
return model
Example #26
| Source File: cnn.py From crnn-lid with GNU General Public License v3.0 | 5 votes |
|
def create_model(input_shape, config, is_training=True):
weight_decay = 0.001
model = Sequential()
model.add(Convolution2D(64, 3, 3, W_regularizer=l2(weight_decay), activation="relu", input_shape=input_shape))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(128, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(256, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
# model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(256, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(512, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
# model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(512, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(512, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Flatten())
model.add(Dense(1024, W_regularizer=l2(weight_decay), activation="relu"))
model.add(Dense(config["num_classes"], activation="softmax"))
return model
Example #27
| Source File: topcoder.py From crnn-lid with GNU General Public License v3.0 | 5 votes |
|
def create_model(input_shape, config, is_training=True):
weight_decay = 0.001
model = Sequential()
model.add(Convolution2D(16, 7, 7, W_regularizer=l2(weight_decay), activation="relu", input_shape=input_shape))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(32, 5, 5, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(64, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(128, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(256, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(1024, W_regularizer=l2(weight_decay), activation="relu"))
model.add(Dense(config["num_classes"], activation="softmax"))
return model
Example #28
| Source File: topcoder_finetune.py From crnn-lid with GNU General Public License v3.0 | 5 votes |
|
def create_model(input_shape, config, is_training=True):
weight_decay = 0.001
model = Sequential()
model.add(Convolution2D(16, 7, 7, W_regularizer=l2(weight_decay), activation="relu", input_shape=input_shape))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(32, 5, 5, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(64, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(128, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(256, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Dropout(0.5))
model.add(Flatten())
# Restore layer weights
model.load_weights("logs/2016-12-16-15-58-20/weights.131.model", by_name=True)
# Retrain last two layers from scratch
model.add(Dense(1024, W_regularizer=l2(weight_decay), activation="relu"))
model.add(Dense(config["num_classes"], activation="softmax"))
return model
Example #29
| Source File: topcoder_deeper.py From crnn-lid with GNU General Public License v3.0 | 5 votes |
|
def create_model(input_shape, config, is_training=True):
weight_decay = 0.001
model = Sequential()
model.add(Convolution2D(32, 7, 7, W_regularizer=l2(weight_decay), activation="relu", input_shape=input_shape))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(64, 5, 5, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(128, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(256, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Convolution2D(512, 3, 3, W_regularizer=l2(weight_decay), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(1024, W_regularizer=l2(weight_decay), activation="relu"))
model.add(Dense(config["num_classes"], activation="softmax"))
return model
Example #30
| Source File: run.py From Generative-Adversarial-Networks-Projects with MIT License | 5 votes |
|
def build_discriminator():
dis_model = Sequential()
dis_model.add(
Conv2D(128, (5, 5),
padding='same',
input_shape=(64, 64, 3))
)
dis_model.add(LeakyReLU(alpha=0.2))
dis_model.add(MaxPooling2D(pool_size=(2, 2)))
dis_model.add(Conv2D(256, (3, 3)))
dis_model.add(LeakyReLU(alpha=0.2))
dis_model.add(MaxPooling2D(pool_size=(2, 2)))
dis_model.add(Conv2D(512, (3, 3)))
dis_model.add(LeakyReLU(alpha=0.2))
dis_model.add(MaxPooling2D(pool_size=(2, 2)))
dis_model.add(Flatten())
dis_model.add(Dense(1024))
dis_model.add(LeakyReLU(alpha=0.2))
dis_model.add(Dense(1))
dis_model.add(Activation('sigmoid'))
return dis_model
