Python keras.layers.ZeroPadding3D() Examples
The following are 6
code examples of keras.layers.ZeroPadding3D().
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
, or try the search function
.
.
Example #1
| Source Project: Fabrik Author: Cloud-CV File: test_views.py License: GNU General Public License v3.0 | 6 votes |
|
def test_keras_import(self):
# Pad 1D
model = Sequential()
model.add(ZeroPadding1D(2, input_shape=(224, 3)))
model.add(Conv1D(32, 7, strides=2))
model.build()
self.pad_test(model, 'pad_w', 2)
# Pad 2D
model = Sequential()
model.add(ZeroPadding2D(2, input_shape=(224, 224, 3)))
model.add(Conv2D(32, 7, strides=2))
model.build()
self.pad_test(model, 'pad_w', 2)
# Pad 3D
model = Sequential()
model.add(ZeroPadding3D(2, input_shape=(224, 224, 224, 3)))
model.add(Conv3D(32, 7, strides=2))
model.build()
self.pad_test(model, 'pad_w', 2)
# ********** Export json tests **********
# ********** Data Layers Test **********
Example #2
| Source Project: Music-Transcription-with-Semantic-Segmentation Author: BreezeWhite File: attn_utils.py License: GNU General Public License v3.0 | 5 votes |
|
def pad_to_multiple(x, block_shape):
ori_shape = K.int_shape(x)
pad_t = ori_shape[1] % block_shape[0]
pad_f = ori_shape[2] % block_shape[1]
padding=((0, 0), (0, pad_t), (0, pad_f))
new_x = L.ZeroPadding3D(padding=padding)(x)
return new_x
Example #3
| Source Project: five-video-classification-methods Author: harvitronix File: models.py License: MIT License | 4 votes |
|
def c3d(self):
"""
Build a 3D convolutional network, aka C3D.
https://arxiv.org/pdf/1412.0767.pdf
With thanks:
https://gist.github.com/albertomontesg/d8b21a179c1e6cca0480ebdf292c34d2
"""
model = Sequential()
# 1st layer group
model.add(Conv3D(64, 3, 3, 3, activation='relu',
border_mode='same', name='conv1',
subsample=(1, 1, 1),
input_shape=self.input_shape))
model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2),
border_mode='valid', name='pool1'))
# 2nd layer group
model.add(Conv3D(128, 3, 3, 3, activation='relu',
border_mode='same', name='conv2',
subsample=(1, 1, 1)))
model.add(MaxPooling3D(pool_size=(2, 2, 2), strides=(2, 2, 2),
border_mode='valid', name='pool2'))
# 3rd layer group
model.add(Conv3D(256, 3, 3, 3, activation='relu',
border_mode='same', name='conv3a',
subsample=(1, 1, 1)))
model.add(Conv3D(256, 3, 3, 3, activation='relu',
border_mode='same', name='conv3b',
subsample=(1, 1, 1)))
model.add(MaxPooling3D(pool_size=(2, 2, 2), strides=(2, 2, 2),
border_mode='valid', name='pool3'))
# 4th layer group
model.add(Conv3D(512, 3, 3, 3, activation='relu',
border_mode='same', name='conv4a',
subsample=(1, 1, 1)))
model.add(Conv3D(512, 3, 3, 3, activation='relu',
border_mode='same', name='conv4b',
subsample=(1, 1, 1)))
model.add(MaxPooling3D(pool_size=(2, 2, 2), strides=(2, 2, 2),
border_mode='valid', name='pool4'))
# 5th layer group
model.add(Conv3D(512, 3, 3, 3, activation='relu',
border_mode='same', name='conv5a',
subsample=(1, 1, 1)))
model.add(Conv3D(512, 3, 3, 3, activation='relu',
border_mode='same', name='conv5b',
subsample=(1, 1, 1)))
model.add(ZeroPadding3D(padding=(0, 1, 1)))
model.add(MaxPooling3D(pool_size=(2, 2, 2), strides=(2, 2, 2),
border_mode='valid', name='pool5'))
model.add(Flatten())
# FC layers group
model.add(Dense(4096, activation='relu', name='fc6'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu', name='fc7'))
model.add(Dropout(0.5))
model.add(Dense(self.nb_classes, activation='softmax'))
return model
Example #4
| Source Project: Music-Transcription-with-Semantic-Segmentation Author: BreezeWhite File: model_attn.py License: GNU General Public License v3.0 | 4 votes |
|
def multihead_attention(x, out_channel=64, d_model=32, n_heads=8, query_shape=(128, 24), memory_flange=(8, 8)):
q = Conv2D(d_model, (3, 3), strides=(1, 1), padding="same", name="gen_q_conv")(x)
k = Conv2D(d_model, (3, 3), strides=(1, 1), padding="same", name="gen_k_conv")(x)
v = Conv2D(d_model, (3, 3), strides=(1, 1), padding="same", name="gen_v_conv")(x)
q = split_heads_2d(q, n_heads)
k = split_heads_2d(k, n_heads)
v = split_heads_2d(v, n_heads)
k_depth_per_head = d_model // n_heads
q *= k_depth_per_head**-0.5
"""
# local attetion 2d
v_shape = K.int_shape(v)
q = pad_to_multiple(q, query_shape)
k = pad_to_multiple(k, query_shape)
v = pad_to_multiple(v, query_shape)
paddings = ((0, 0), (memory_flange[0], memory_flange[1]), (memory_flange[0], memory_flange[1]))
k = L.ZeroPadding3D(padding=paddings)(k)
v = L.ZeroPadding3D(padding=paddings)(v)
# Set up query blocks
q_indices = gather_indices_2d(q, query_shape, query_shape)
q_new = gather_blocks_2d(q, q_indices)
# Set up key and value blocks
memory_shape = (query_shape[0] + 2*memory_flange[0],
query_shape[1] + 2*memory_flange[1])
k_and_v_indices = gather_indices_2d(k, memory_shape, query_shape)
k_new = gather_blocks_2d(k, k_and_v_indices)
v_new = gather_blocks_2d(v, k_and_v_indices)
output = dot_attention(q_new, k_new, v_new)
# Put output back into original shapes
padded_shape = K.shape(q)
output = scatter_blocks_2d(output, q_indices, padded_shape)
# Remove padding
output = K.slice(output, [0, 0, 0, 0, 0], [-1, -1, v_shape[2], v_shape[3], -1])
"""
output = local_attention_2d(q, k, v, query_shape=query_shape, memory_flange=memory_flange)
output = combine_heads_2d(output)
output = Conv2D(out_channel, (3, 3), strides=(1, 1), padding="same", use_bias=False)(output)
return output
Example #5
| Source Project: cocktail-party Author: avivga File: network.py License: MIT License | 4 votes |
|
def build(video_shape, audio_spectrogram_size): model = Sequential() model.add(ZeroPadding3D(padding=(1, 2, 2), name='zero1', input_shape=video_shape)) model.add(Convolution3D(32, (3, 5, 5), strides=(1, 2, 2), kernel_initializer='he_normal', name='conv1')) model.add(BatchNormalization()) model.add(LeakyReLU()) model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2), name='max1')) model.add(Dropout(0.25)) model.add(ZeroPadding3D(padding=(1, 2, 2), name='zero2')) model.add(Convolution3D(64, (3, 5, 5), strides=(1, 1, 1), kernel_initializer='he_normal', name='conv2')) model.add(BatchNormalization()) model.add(LeakyReLU()) model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2), name='max2')) model.add(Dropout(0.25)) model.add(ZeroPadding3D(padding=(1, 1, 1), name='zero3')) model.add(Convolution3D(128, (3, 3, 3), strides=(1, 1, 1), kernel_initializer='he_normal', name='conv3')) model.add(BatchNormalization()) model.add(LeakyReLU()) model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2), name='max3')) model.add(Dropout(0.25)) model.add(TimeDistributed(Flatten(), name='time')) model.add(Dense(1024, kernel_initializer='he_normal', name='dense1')) model.add(BatchNormalization()) model.add(LeakyReLU()) model.add(Dropout(0.25)) model.add(Dense(1024, kernel_initializer='he_normal', name='dense2')) model.add(BatchNormalization()) model.add(LeakyReLU()) model.add(Dropout(0.25)) model.add(Flatten()) model.add(Dense(2048, kernel_initializer='he_normal', name='dense3')) model.add(BatchNormalization()) model.add(LeakyReLU()) model.add(Dropout(0.25)) model.add(Dense(2048, kernel_initializer='he_normal', name='dense4')) model.add(BatchNormalization()) model.add(LeakyReLU()) model.add(Dropout(0.25)) model.add(Dense(audio_spectrogram_size, name='output')) model.summary() return VideoToSpeechNet(model)
Example #6
| Source Project: Fabrik Author: Cloud-CV File: layers_export.py License: GNU General Public License v3.0 | 4 votes |
|
def pooling(layer, layer_in, layerId, tensor=True):
poolMap = {
('1D', 'MAX'): MaxPooling1D,
('2D', 'MAX'): MaxPooling2D,
('3D', 'MAX'): MaxPooling3D,
('1D', 'AVE'): AveragePooling1D,
('2D', 'AVE'): AveragePooling2D,
('3D', 'AVE'): AveragePooling3D,
}
out = {}
layer_type = layer['params']['layer_type']
pool_type = layer['params']['pool']
padding = get_padding(layer)
if (layer_type == '1D'):
strides = layer['params']['stride_w']
kernel = layer['params']['kernel_w']
if (padding == 'custom'):
p_w = layer['params']['pad_w']
out[layerId + 'Pad'] = ZeroPadding1D(padding=p_w)(*layer_in)
padding = 'valid'
layer_in = [out[layerId + 'Pad']]
elif (layer_type == '2D'):
strides = (layer['params']['stride_h'], layer['params']['stride_w'])
kernel = (layer['params']['kernel_h'], layer['params']['kernel_w'])
if (padding == 'custom'):
p_h, p_w = layer['params']['pad_h'], layer['params']['pad_w']
out[layerId + 'Pad'] = ZeroPadding2D(padding=(p_h, p_w))(*layer_in)
padding = 'valid'
layer_in = [out[layerId + 'Pad']]
else:
strides = (layer['params']['stride_h'], layer['params']['stride_w'],
layer['params']['stride_d'])
kernel = (layer['params']['kernel_h'], layer['params']['kernel_w'],
layer['params']['kernel_d'])
if (padding == 'custom'):
p_h, p_w, p_d = layer['params']['pad_h'], layer['params']['pad_w'],\
layer['params']['pad_d']
out[layerId +
'Pad'] = ZeroPadding3D(padding=(p_h, p_w, p_d))(*layer_in)
padding = 'valid'
layer_in = [out[layerId + 'Pad']]
# Note - figure out a permanent fix for padding calculation of layers
# in case padding is given in layer attributes
# if ('padding' in layer['params']):
# padding = layer['params']['padding']
out[layerId] = poolMap[(layer_type, pool_type)](
pool_size=kernel, strides=strides, padding=padding)
if tensor:
out[layerId] = out[layerId](*layer_in)
return out
# ********** Locally-connected Layers **********
