Python keras.layers.convolutional.MaxPooling3D() Examples
The following are 15
code examples of keras.layers.convolutional.MaxPooling3D().
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.convolutional
, or try the search function
.
.
Example #1
| Source File: liver_model.py From MCF-3D-CNN with MIT License | 6 votes |
|
def cnn_3D(self, input_shape, modual=''):
#建立Sequential模型
model_in = Input(input_shape)
model = Convolution3D(
filters = 6,
kernel_size = (3, 3, 3),
input_shape = input_shape,
activation='relu',
kernel_initializer='he_normal',
name = modual+'conv1'
)(model_in)# now 30x30x3x6
model = MaxPooling3D(pool_size=(2,2,1))(model)# now 15x15x3x6
model = Convolution3D(
filters = 8,
kernel_size = (4, 4, 3),
activation='relu',
kernel_initializer='he_normal',
name = modual+'conv2'
)(model)# now 12x12x1x8
model = MaxPooling3D(pool_size=(2,2,1))(model)# now 6x6x1x8
model = Flatten()(model)
model = Dropout(0.5)(model)
model_out = Dense(100, activation='relu', name = modual+'fc1')(model)
return model_in, model_out
Example #2
| Source File: MSnetworks.py From CNNArt with Apache License 2.0 | 6 votes |
|
def fSPP(inp, level=3):
inshape = inp._keras_shape[2:]
Kernel = [[0] * 3 for i in range(level)]
Stride = [[0] * 3 for i in range(level)]
SPPout = T.tensor5()
for iLevel in range(level):
Kernel[iLevel] = np.ceil(np.divide(inshape, iLevel+1, dtype = float)).astype(int)
Stride[iLevel] = np.floor(np.divide(inshape, iLevel+1, dtype = float)).astype(int)
if inshape[2]%3==2:
Kernel[2][2] = Kernel[2][2] + 1
poolLevel = MaxPooling3D(pool_size=Kernel[iLevel], strides=Stride[iLevel])(inp)
if iLevel == 0:
SPPout = Flatten()(poolLevel)
else:
poolFlat = Flatten()(poolLevel)
SPPout = concatenate([SPPout,poolFlat], axis=1)
return SPPout
# Models of FCN
Example #3
| Source File: MSnetworks.py From CNNArt with Apache License 2.0 | 6 votes |
|
def InceptionBlock(inp, l1_reg=0.0, l2_reg=1e-6):
KN = fgetKernelNumber()
branch1 = Conv3D(filters=KN[0], kernel_size=(1,1,1), kernel_initializer='he_normal', weights=None,padding='same',
strides=(1,1,1),kernel_regularizer=l1_l2(l1_reg, l2_reg),activation='relu')(inp)
branch3 = Conv3D(filters=KN[0], kernel_size=(1, 1, 1), kernel_initializer='he_normal', weights=None, padding='same',
strides=(1, 1, 1), kernel_regularizer=l1_l2(l1_reg, l2_reg), activation='relu')(inp)
branch3 = Conv3D(filters=KN[2], kernel_size=(3, 3, 3), kernel_initializer='he_normal', weights=None, padding='same',
strides=(1, 1, 1), kernel_regularizer=l1_l2(l1_reg, l2_reg), activation='relu')(branch3)
branch5 = Conv3D(filters=KN[0], kernel_size=(1, 1, 1), kernel_initializer='he_normal', weights=None, padding='same',
strides=(1, 1, 1), kernel_regularizer=l1_l2(l1_reg, l2_reg), activation='relu')(inp)
branch5 = Conv3D(filters=KN[1], kernel_size=(5, 5, 5), kernel_initializer='he_normal', weights=None, padding='same',
strides=(1, 1, 1), kernel_regularizer=l1_l2(l1_reg, l2_reg), activation='relu')(branch5)
branchpool = MaxPooling3D(pool_size=(3,3,3),strides=(1,1,1),padding='same',data_format='channels_first')(inp)
branchpool = Conv3D(filters=KN[0], kernel_size=(1, 1, 1), kernel_initializer='he_normal', weights=None, padding='same',
strides=(1, 1, 1), kernel_regularizer=l1_l2(l1_reg, l2_reg), activation='relu')(branchpool)
out = concatenate([branch1, branch3, branch5, branchpool], axis=1)
return out
Example #4
| Source File: convolutional_test.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
|
def test_maxpooling_3d():
pool_size = (3, 3, 3)
layer_test(convolutional.MaxPooling3D,
kwargs={'strides': 2,
'padding': 'valid',
'pool_size': pool_size},
input_shape=(3, 11, 12, 10, 4))
layer_test(convolutional.MaxPooling3D,
kwargs={'strides': 3,
'padding': 'valid',
'data_format': 'channels_first',
'pool_size': pool_size},
input_shape=(3, 4, 11, 12, 10))
Example #5
| Source File: convolutional_test.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
|
def test_maxpooling_3d():
pool_size = (3, 3, 3)
layer_test(convolutional.MaxPooling3D,
kwargs={'strides': 2,
'padding': 'valid',
'pool_size': pool_size},
input_shape=(3, 11, 12, 10, 4))
layer_test(convolutional.MaxPooling3D,
kwargs={'strides': 3,
'padding': 'valid',
'data_format': 'channels_first',
'pool_size': pool_size},
input_shape=(3, 4, 11, 12, 10))
Example #6
| Source File: convolutional_test.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
|
def test_maxpooling_3d():
pool_size = (3, 3, 3)
layer_test(convolutional.MaxPooling3D,
kwargs={'strides': 2,
'padding': 'valid',
'pool_size': pool_size},
input_shape=(3, 11, 12, 10, 4))
layer_test(convolutional.MaxPooling3D,
kwargs={'strides': 3,
'padding': 'valid',
'data_format': 'channels_first',
'pool_size': pool_size},
input_shape=(3, 4, 11, 12, 10))
Example #7
| Source File: convolutional_test.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
|
def test_maxpooling_3d():
pool_size = (3, 3, 3)
layer_test(convolutional.MaxPooling3D,
kwargs={'strides': 2,
'padding': 'valid',
'pool_size': pool_size},
input_shape=(3, 11, 12, 10, 4))
layer_test(convolutional.MaxPooling3D,
kwargs={'strides': 3,
'padding': 'valid',
'data_format': 'channels_first',
'pool_size': pool_size},
input_shape=(3, 4, 11, 12, 10))
Example #8
| Source File: convolutional_test.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
|
def test_maxpooling_3d():
pool_size = (3, 3, 3)
layer_test(convolutional.MaxPooling3D,
kwargs={'strides': 2,
'padding': 'valid',
'pool_size': pool_size},
input_shape=(3, 11, 12, 10, 4))
layer_test(convolutional.MaxPooling3D,
kwargs={'strides': 3,
'padding': 'valid',
'data_format': 'channels_first',
'pool_size': pool_size},
input_shape=(3, 4, 11, 12, 10))
Example #9
| Source File: convolutional_test.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
|
def test_maxpooling_3d():
pool_size = (3, 3, 3)
layer_test(convolutional.MaxPooling3D,
kwargs={'strides': 2,
'padding': 'valid',
'pool_size': pool_size},
input_shape=(3, 11, 12, 10, 4))
layer_test(convolutional.MaxPooling3D,
kwargs={'strides': 3,
'padding': 'valid',
'data_format': 'channels_first',
'pool_size': pool_size},
input_shape=(3, 4, 11, 12, 10))
Example #10
| Source File: convolutional_test.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
|
def test_maxpooling_3d():
pool_size = (3, 3, 3)
layer_test(convolutional.MaxPooling3D,
kwargs={'strides': 2,
'padding': 'valid',
'pool_size': pool_size},
input_shape=(3, 11, 12, 10, 4))
layer_test(convolutional.MaxPooling3D,
kwargs={'strides': 3,
'padding': 'valid',
'data_format': 'channels_first',
'pool_size': pool_size},
input_shape=(3, 4, 11, 12, 10))
Example #11
| Source File: preds3d_models.py From Kaggle-DSB with MIT License | 5 votes |
|
def preds3d_baseline(width):
learning_rate = 5e-5
#optimizer = SGD(lr=learning_rate, momentum = 0.9, decay = 1e-3, nesterov = True)
optimizer = Adam(lr=learning_rate)
inputs = Input(shape=(1, 136, 168, 168))
conv1 = Convolution3D(width, 3, 3, 3, activation = 'relu', border_mode='same')(inputs)
conv1 = BatchNormalization(axis = 1)(conv1)
conv1 = Convolution3D(width*2, 3, 3, 3, activation = 'relu', border_mode='same')(conv1)
conv1 = BatchNormalization(axis = 1)(conv1)
pool1 = MaxPooling3D(pool_size=(2, 2, 2), border_mode='same')(conv1)
conv2 = Convolution3D(width*2, 3, 3, 3, activation = 'relu', border_mode='same')(pool1)
conv2 = BatchNormalization(axis = 1)(conv2)
conv2 = Convolution3D(width*4, 3, 3, 3, activation = 'relu', border_mode='same')(conv2)
conv2 = BatchNormalization(axis = 1)(conv2)
pool2 = MaxPooling3D(pool_size=(2, 2, 2), border_mode='same')(conv2)
conv3 = Convolution3D(width*4, 3, 3, 3, activation = 'relu', border_mode='same')(pool2)
conv3 = BatchNormalization(axis = 1)(conv3)
conv3 = Convolution3D(width*8, 3, 3, 3, activation = 'relu', border_mode='same')(conv3)
conv3 = BatchNormalization(axis = 1)(conv3)
pool3 = MaxPooling3D(pool_size=(2, 2, 2), border_mode='same')(conv3)
output = GlobalAveragePooling3D()(pool3)
output = Dense(2, activation='softmax', name = 'predictions')(output)
model3d = Model(inputs, output)
model3d.compile(loss='categorical_crossentropy', optimizer = optimizer, metrics = ['accuracy'])
return model3d
Example #12
| Source File: preds3d_models.py From Kaggle-DSB with MIT License | 5 votes |
|
def preds3d_globalavg(width):
learning_rate = 5e-5
#optimizer = SGD(lr=learning_rate, momentum = 0.9, decay = 1e-3, nesterov = True)
optimizer = Adam(lr=learning_rate)
inputs = Input(shape=(1, 136, 168, 168))
conv1 = Convolution3D(width, 3, 3, 3, activation = 'relu', border_mode='same')(inputs)
conv1 = BatchNormalization(axis = 1)(conv1)
conv1 = Convolution3D(width*2, 3, 3, 3, activation = 'relu', border_mode='same')(conv1)
conv1 = BatchNormalization(axis = 1)(conv1)
pool1 = MaxPooling3D(pool_size=(2, 2, 2), border_mode='same')(conv1)
conv2 = Convolution3D(width*2, 3, 3, 3, activation = 'relu', border_mode='same')(pool1)
conv2 = BatchNormalization(axis = 1)(conv2)
conv2 = Convolution3D(width*4, 3, 3, 3, activation = 'relu', border_mode='same')(conv2)
conv2 = BatchNormalization(axis = 1)(conv2)
pool2 = MaxPooling3D(pool_size=(2, 2, 2), border_mode='same')(conv2)
conv3 = Convolution3D(width*4, 3, 3, 3, activation = 'relu', border_mode='same')(pool2)
conv3 = BatchNormalization(axis = 1)(conv3)
conv3 = Convolution3D(width*8, 3, 3, 3, activation = 'relu', border_mode='same')(conv3)
conv3 = BatchNormalization(axis = 1)(conv3)
pool3 = MaxPooling3D(pool_size=(2, 2, 2), border_mode='same')(conv3)
conv4 = Convolution3D(width*8, 3, 3, 3, activation = 'relu', border_mode='same')(pool3)
conv4 = BatchNormalization(axis = 1)(conv4)
conv4 = Convolution3D(width*16, 3, 3, 3, activation = 'relu', border_mode='same')(conv4)
conv4 = BatchNormalization(axis = 1)(conv4)
pool4 = MaxPooling3D(pool_size=(8, 8, 8), border_mode='same')(conv4)
output = GlobalAveragePooling3D()(conv4)
output = Dense(2, activation='softmax', name = 'predictions')(output)
model3d = Model(inputs, output)
model3d.compile(loss='categorical_crossentropy', optimizer = optimizer, metrics = ['accuracy'])
return model3d
Example #13
| Source File: preds3d_run.py From Kaggle-DSB with MIT License | 5 votes |
|
def preds3d_baseline(width):
learning_rate = 5e-5
optimizer = SGD(lr=learning_rate, momentum = 0.9, decay = 1e-3, nesterov = True)
#optimizer = Adam(lr=learning_rate)
inputs = Input(shape=(1, 136, 168, 168))
conv1 = Convolution3D(width, 3, 3, 3, activation = 'relu', border_mode='same')(inputs)
conv1 = BatchNormalization(axis = 1)(conv1)
conv1 = Convolution3D(width*2, 3, 3, 3, activation = 'relu', border_mode='same')(conv1)
conv1 = BatchNormalization(axis = 1)(conv1)
pool1 = MaxPooling3D(pool_size=(2, 2, 2), border_mode='same')(conv1)
conv2 = Convolution3D(width*2, 3, 3, 3, activation = 'relu', border_mode='same')(pool1)
conv2 = BatchNormalization(axis = 1)(conv2)
conv2 = Convolution3D(width*4, 3, 3, 3, activation = 'relu', border_mode='same')(conv2)
conv2 = BatchNormalization(axis = 1)(conv2)
pool2 = MaxPooling3D(pool_size=(2, 2, 2), border_mode='same')(conv2)
conv3 = Convolution3D(width*4, 3, 3, 3, activation = 'relu', border_mode='same')(pool2)
conv3 = BatchNormalization(axis = 1)(conv3)
conv3 = Convolution3D(width*8, 3, 3, 3, activation = 'relu', border_mode='same')(conv3)
conv3 = BatchNormalization(axis = 1)(conv3)
pool3 = MaxPooling3D(pool_size=(2, 2, 2), border_mode='same')(conv3)
output = GlobalAveragePooling3D()(pool3)
output = Dense(2, activation='softmax', name = 'predictions')(output)
model3d = Model(inputs, output)
model3d.compile(loss='categorical_crossentropy', optimizer = optimizer, metrics = ['accuracy'])
return model3d
# 1398 stage1 original examples
Example #14
| Source File: preds3d_models.py From Kaggle-DSB with MIT License | 4 votes |
|
def preds3d_dense(width):
learning_rate = 5e-5
#optimizer = SGD(lr=learning_rate, momentum = 0.9, decay = 1e-3, nesterov = True)
optimizer = Adam(lr=learning_rate)
inputs = Input(shape=(1, 136, 168, 168))
conv1 = Convolution3D(width, 3, 3, 3, activation = 'relu', border_mode='same')(inputs)
conv1 = BatchNormalization(axis = 1)(conv1)
conv1 = Convolution3D(width*2, 3, 3, 3, activation = 'relu', border_mode='same')(conv1)
conv1 = BatchNormalization(axis = 1)(conv1)
pool1 = MaxPooling3D(pool_size=(2, 2, 2), border_mode='same')(conv1)
conv2 = Convolution3D(width*2, 3, 3, 3, activation = 'relu', border_mode='same')(pool1)
conv2 = BatchNormalization(axis = 1)(conv2)
conv2 = Convolution3D(width*4, 3, 3, 3, activation = 'relu', border_mode='same')(conv2)
conv2 = BatchNormalization(axis = 1)(conv2)
pool2 = MaxPooling3D(pool_size=(2, 2, 2), border_mode='same')(conv2)
conv3 = Convolution3D(width*4, 3, 3, 3, activation = 'relu', border_mode='same')(pool2)
conv3 = BatchNormalization(axis = 1)(conv3)
conv3 = Convolution3D(width*8, 3, 3, 3, activation = 'relu', border_mode='same')(conv3)
conv3 = BatchNormalization(axis = 1)(conv3)
pool3 = MaxPooling3D(pool_size=(2, 2, 2), border_mode='same')(conv3)
conv4 = Convolution3D(width*8, 3, 3, 3, activation = 'relu', border_mode='same')(pool3)
conv4 = BatchNormalization(axis = 1)(conv4)
conv4 = Convolution3D(width*16, 3, 3, 3, activation = 'relu', border_mode='same')(conv4)
conv4 = BatchNormalization(axis = 1)(conv4)
pool4 = MaxPooling3D(pool_size=(8, 8, 8), border_mode='same')(conv4)
output = Flatten(name='flatten')(pool4)
output = Dropout(0.2)(output)
output = Dense(128)(output)
output = PReLU()(output)
output = BatchNormalization()(output)
output = Dropout(0.2)(output)
output = Dense(128)(output)
output = PReLU()(output)
output = BatchNormalization()(output)
output = Dropout(0.3)(output)
output = Dense(2, activation='softmax', name = 'predictions')(output)
model3d = Model(inputs, output)
model3d.compile(loss='categorical_crossentropy', optimizer = optimizer, metrics = ['accuracy'])
return model3d
Example #15
| Source File: 3DUNet_train_generator.py From Kaggle-DSB with MIT License | 4 votes |
|
def unet_model():
inputs = Input(shape=(1, max_slices, img_size, img_size))
conv1 = Convolution3D(width, 3, 3, 3, activation = 'relu', border_mode='same')(inputs)
conv1 = BatchNormalization(axis = 1)(conv1)
conv1 = Convolution3D(width*2, 3, 3, 3, activation = 'relu', border_mode='same')(conv1)
conv1 = BatchNormalization(axis = 1)(conv1)
pool1 = MaxPooling3D(pool_size=(2, 2, 2), strides = (2, 2, 2), border_mode='same')(conv1)
conv2 = Convolution3D(width*2, 3, 3, 3, activation = 'relu', border_mode='same')(pool1)
conv2 = BatchNormalization(axis = 1)(conv2)
conv2 = Convolution3D(width*4, 3, 3, 3, activation = 'relu', border_mode='same')(conv2)
conv2 = BatchNormalization(axis = 1)(conv2)
pool2 = MaxPooling3D(pool_size=(2, 2, 2), strides = (2, 2, 2), border_mode='same')(conv2)
conv3 = Convolution3D(width*4, 3, 3, 3, activation = 'relu', border_mode='same')(pool2)
conv3 = BatchNormalization(axis = 1)(conv3)
conv3 = Convolution3D(width*8, 3, 3, 3, activation = 'relu', border_mode='same')(conv3)
conv3 = BatchNormalization(axis = 1)(conv3)
pool3 = MaxPooling3D(pool_size=(2, 2, 2), strides = (2, 2, 2), border_mode='same')(conv3)
conv4 = Convolution3D(width*8, 3, 3, 3, activation = 'relu', border_mode='same')(pool3)
conv4 = BatchNormalization(axis = 1)(conv4)
conv4 = Convolution3D(width*8, 3, 3, 3, activation = 'relu', border_mode='same')(conv4)
conv4 = BatchNormalization(axis = 1)(conv4)
conv4 = Convolution3D(width*16, 3, 3, 3, activation = 'relu', border_mode='same')(conv4)
conv4 = BatchNormalization(axis = 1)(conv4)
up5 = merge([UpSampling3D(size=(2, 2, 2))(conv4), conv3], mode='concat', concat_axis=1)
conv5 = SpatialDropout3D(dropout_rate)(up5)
conv5 = Convolution3D(width*8, 3, 3, 3, activation = 'relu', border_mode='same')(conv5)
conv5 = Convolution3D(width*8, 3, 3, 3, activation = 'relu', border_mode='same')(conv5)
up6 = merge([UpSampling3D(size=(2, 2, 2))(conv5), conv2], mode='concat', concat_axis=1)
conv6 = SpatialDropout3D(dropout_rate)(up6)
conv6 = Convolution3D(width*4, 3, 3, 3, activation = 'relu', border_mode='same')(conv6)
conv6 = Convolution3D(width*4, 3, 3, 3, activation = 'relu', border_mode='same')(conv6)
up7 = merge([UpSampling3D(size=(2, 2, 2))(conv6), conv1], mode='concat', concat_axis=1)
conv7 = SpatialDropout3D(dropout_rate)(up7)
conv7 = Convolution3D(width*2, 3, 3, 3, activation = 'relu', border_mode='same')(conv7)
conv7 = Convolution3D(width*2, 3, 3, 3, activation = 'relu', border_mode='same')(conv7)
conv8 = Convolution3D(1, 1, 1, 1, activation='sigmoid')(conv7)
model = Model(input=inputs, output=conv8)
model.compile(optimizer=Adam(lr=1e-5),
loss=dice_coef_loss, metrics=[dice_coef])
return model
