ztlearn.dl.layers package

Subpackages

• ztlearn.dl.layers.recurrent package
  • Submodules
  • ztlearn.dl.layers.recurrent.gru module
  • ztlearn.dl.layers.recurrent.lstm module
  • ztlearn.dl.layers.recurrent.rnn module
  • Module contents

Submodules

ztlearn.dl.layers.base module

class ztlearn.dl.layers.base.Layer(layer_name='zeta_squential')

Bases: abc.ABC

input_shape

layer_name

layer_parameters

output_shape

pass_backward()

pass_forward()

ztlearn.dl.layers.convolutional module

class ztlearn.dl.layers.convolutional.Conv(filters=32, kernel_size=(3, 3), activation=None, input_shape=(1, 8, 8), strides=(1, 1), padding='valid')

Bases: ztlearn.dl.layers.base.Layer

layer_activation

layer_parameters

output_shape

prep_layer()

trainable

weight_initializer

weight_optimizer

class ztlearn.dl.layers.convolutional.Conv2D(filters=32, kernel_size=(3, 3), activation=None, input_shape=(1, 8, 8), strides=(1, 1), padding='valid')

Bases: ztlearn.dl.layers.convolutional.Conv

pass_backward(grad, epoch_num, batch_num, batch_size)

pass_forward(inputs, train_mode=True, **kwargs)

class ztlearn.dl.layers.convolutional.ConvLoop2D(filters=32, kernel_size=(3, 3), activation=None, input_shape=(1, 8, 8), strides=(1, 1), padding='valid')

Bases: ztlearn.dl.layers.convolutional.Conv

pass_backward(grad, epoch_num, batch_num, batch_size)

pass_forward(inputs, train_mode=True, **kwargs)

class ztlearn.dl.layers.convolutional.ConvToeplitzMat(filters=32, kernel_size=(3, 3), activation=None, input_shape=(1, 8, 8), strides=(1, 1), padding='valid')

Bases: ztlearn.dl.layers.convolutional.Conv

pass_backward(grad, epoch_num, batch_num, batch_size)

pass_forward(inputs, train_mode=True, **kwargs)

ztlearn.dl.layers.core module

class ztlearn.dl.layers.core.Activation(function_name, input_shape=None, **kwargs)

Bases: ztlearn.dl.layers.base.Layer

layer_name

output_shape

pass_backward(grad, epoch_num, batch_num, batch_size)

pass_forward(input_signal, train_mode=True, **kwargs)

prep_layer()

trainable

class ztlearn.dl.layers.core.Dense(units, activation=None, input_shape=None)

Bases: ztlearn.dl.layers.base.Layer

layer_activation

layer_parameters

output_shape

pass_backward(grad, epoch_num, batch_num, batch_size)

pass_forward(inputs, train_mode=True)

prep_layer()

trainable

weight_initializer

weight_optimizer

class ztlearn.dl.layers.core.Dropout(drop=0.5)

Bases: ztlearn.dl.layers.base.Layer

output_shape

pass_backward(grad, epoch_num, batch_num, batch_size)

pass_forward(inputs, train_mode=True, **kwargs)

prep_layer()

trainable

class ztlearn.dl.layers.core.Flatten(input_shape=None)

Bases: ztlearn.dl.layers.base.Layer

output_shape

pass_backward(grad, epoch_num, batch_num, batch_size)

pass_forward(inputs, train_mode=True, **kwargs)

prep_layer()

trainable

class ztlearn.dl.layers.core.Reshape(target_shape, input_shape=None)

Bases: ztlearn.dl.layers.base.Layer

output_shape

pass_backward(grad, epoch_num, batch_num, batch_size)

pass_forward(inputs, train_mode=True, **kwargs)

prep_layer()

trainable

class ztlearn.dl.layers.core.UpSampling2D(size=(2, 2), input_shape=None)

Bases: ztlearn.dl.layers.base.Layer

output_shape

pass_backward(grad, epoch_num, batch_num, batch_size)

pass_forward(inputs, train_mode=True, **kwargs)

prep_layer()

trainable

ztlearn.dl.layers.embedding module

class ztlearn.dl.layers.embedding.Embedding(input_dim, output_dim, embeddings_init='uniform', input_length=10)

Bases: ztlearn.dl.layers.base.Layer

layer_parameters

output_shape

pass_backward(grad, epoch_num, batch_num, batch_size)

pass_forward(inputs, train_mode=True, **kwargs)

prep_layer()

trainable

weight_initializer

weight_optimizer

ztlearn.dl.layers.normalization module

class ztlearn.dl.layers.normalization.BatchNormalization(eps=0.01, momentum=0.99)

Bases: ztlearn.dl.layers.base.Layer

layer_parameters

output_shape

pass_backward(grad, epoch_num, batch_num, batch_size)

pass_forward(inputs, train_mode=True, **kwargs)

prep_layer()

trainable

weight_optimizer

class ztlearn.dl.layers.normalization.LayerNormalization1D(eps=1e-05)

Bases: ztlearn.dl.layers.base.Layer

output_shape

pass_backward(grad, epoch_num, batch_num, batch_size)

pass_forward(inputs, train_mode=True, **kwargs)

prep_layer()

trainable

weight_optimizer

ztlearn.dl.layers.pooling module

class ztlearn.dl.layers.pooling.AveragePool2D(pool_size=(2, 2), strides=(1, 1), padding='valid')

Bases: ztlearn.dl.layers.pooling.Pool

pool_backward(d_input_col, grad_col, pool_cache=None)

pool_forward(input_col)

class ztlearn.dl.layers.pooling.MaxPooling2D(pool_size=(2, 2), strides=(1, 1), padding='valid')

Bases: ztlearn.dl.layers.pooling.Pool

pool_backward(d_input_col, grad_col, pool_cache)

pool_forward(input_col)

class ztlearn.dl.layers.pooling.Pool(pool_size=(2, 2), strides=(1, 1), padding='valid')

Bases: ztlearn.dl.layers.base.Layer

output_shape

pass_backward(grad, epoch_num, batch_num, batch_size)

pass_forward(inputs, train_mode=True, **kwargs)

prep_layer()

trainable

Module contents