layers

Type Members

class Activation[T] extends keras.layers.Activation[T] with Net

Simple activation function to be applied to the output.
Simple activation function to be applied to the output. Available activations: 'tanh', 'relu', 'sigmoid', 'softmax', 'softplus', 'softsign', 'hard_sigmoid', 'linear', 'relu6', 'tanh_shrink', 'softmin', 'log_sigmoid' and 'log_softmax'.
When you use this layer as the first layer of a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
T
Numeric type of parameter(e.g. weight, bias). Only support float/double now.
class Average[T] extends Merge[T] with Net

Layer that computes the average (element-wise) a list of inputs.
Layer that computes the average (element-wise) a list of inputs.
It takes as input a list of nodes, all of the same shape, and returns a single node (also of the same shape).
class AveragePooling1D[T] extends keras.layers.AveragePooling1D[T] with Net

Average pooling operation for temporal data.
Average pooling operation for temporal data.
Input shape 3D tensor with shape: (batch_size, steps, features).
Output shape 3D tensor with shape: (batch_size, downsampled_steps, features).
T
Numeric type of parameter(e.g. weight, bias). Only support float/double now
class Conv1D[T] extends Convolution1D[T] with Net

1D convolution layer (e.g.
1D convolution layer (e.g. temporal convolution). This layer creates a convolution kernel that is convolved with the layer input over a single spatial (or temporal) dimension to produce a tensor of outputs. If use_bias is True, a bias vector is created and added to the outputs. Finally, if activation is not None, it is applied to the outputs as well.
When using this layer as the first layer in a model, provide an input_shape argument (tuple of integers or None, e.g. (10, 128) for sequences of 10 vectors of 128-dimensional vectors, or (None, 128) for variable-length sequences of 128-dimensional vectors.
Input shape 3D tensor with shape: (batch_size, steps, input_dim)
Output shape 3D tensor with shape: (batch_size, new_steps, filters) steps value might have changed due to padding or strides.
T
Numeric type of parameter(e.g. weight, bias). Only support float/double now.
class Conv2D[T] extends Convolution2D[T] with Net

2D convolution layer (e.g.
2D convolution layer (e.g. spatial convolution over images).
This layer creates a convolution kernel that is convolved with the layer input to produce a tensor of outputs. If use_bias is True, a bias vector is created and added to the outputs. Finally, if activation is not None, it is applied to the outputs as well.
When using this layer as the first layer in a model, provide the keyword argument input_shape (tuple of integers, does not include the sample axis), e.g. input_shape=(128, 128, 3) for 128x128 RGB pictures in data_format="channels_last".
Input shape 4D tensor with shape: (samples, channels, rows, cols) if data_format='channels_first' or 4D tensor with shape: (samples, rows, cols, channels) if data_format='channels_last'.
Output shape 4D tensor with shape: (samples, filters, new_rows, new_cols) if data_format='channels_first' or 4D tensor with shape: (samples, new_rows, new_cols, filters) if data_format='channels_last'. rows and cols values might have changed due to padding.
T
Numeric type of parameter(e.g. weight, bias). Only support float/double now.
class Cropping1D[T] extends keras.layers.Cropping1D[T] with Net

Cropping layer for 1D input (e.g.
Cropping layer for 1D input (e.g. temporal sequence). The input of this layer should be 3D.
When you use this layer as the first layer of a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
T
Numeric type of parameter(e.g. weight, bias). Only support float/double now.
class Dense[T] extends keras.layers.Dense[T] with Net

A densely-connected NN layer.
A densely-connected NN layer. The most common input is 2D.
When you use this layer as the first layer of a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
T
Numeric type of parameter(e.g. weight, bias). Only support float/double now.
class Dropout[T] extends keras.layers.Dropout[T] with Net

Applies Dropout to the input by randomly setting a fraction 'rate' of input units to 0 at each update during training time in order to prevent overfitting.
Applies Dropout to the input by randomly setting a fraction 'rate' of input units to 0 at each update during training time in order to prevent overfitting.
When you use this layer as the first layer of a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
T
Numeric type of parameter(e.g. weight, bias). Only support float/double now.
class Flatten[T] extends keras.layers.Flatten[T] with Net

Flattens the input without affecting the batch size.
Flattens the input without affecting the batch size. For example, if inputShape = Shape(2, 3, 4), then outputShape will be Shape(24) with batch dimension unchanged.
When you use this layer as the first layer of a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
T
Numeric type of parameter(e.g. weight, bias). Only support float/double now.
class GlobalAveragePooling1D[T] extends keras.layers.GlobalAveragePooling1D[T] with Net

Applies global average pooling operation for temporal data.
Applies global average pooling operation for temporal data. The input of this layer should be 3D.
When you use this layer as the first layer of a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
T
The numeric type of parameter(e.g. weight, bias). Only support float/double now.
class GlobalAveragePooling2D[T] extends keras.layers.GlobalAveragePooling2D[T] with Net

Applies global average pooling operation for spatial data.
Applies global average pooling operation for spatial data. The input of this layer should be 4D.
When you use this layer as the first layer of a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
T
The numeric type of parameter(e.g. weight, bias). Only support float/double now.
class GlobalAveragePooling3D[T] extends keras.layers.GlobalAveragePooling3D[T] with Net

Applies global average pooling operation for 3D data.
Applies global average pooling operation for 3D data. Data format currently supported for this layer is 'channels_first' . Padding currently supported for this layer is 'valid'. The input of this layer should be 5D.
When you use this layer as the first layer of a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
T
The numeric type of parameter(e.g. weight, bias). Only support float/double now.
class GlobalMaxPooling1D[T] extends keras.layers.GlobalMaxPooling1D[T] with Net

Applies global max pooling operation for temporal data.
Applies global max pooling operation for temporal data. The input of this layer should be 3D.
When you use this layer as the first layer of a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
T
The numeric type of parameter(e.g. weight, bias). Only support float/double now.
class GlobalMaxPooling2D[T] extends keras.layers.GlobalMaxPooling2D[T] with Net

Applies global max pooling operation for spatial data.
Applies global max pooling operation for spatial data. The input of this layer should be 4D.
When you use this layer as the first layer of a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
T
The numeric type of parameter(e.g. weight, bias). Only support float/double now.
class GlobalMaxPooling3D[T] extends keras.layers.GlobalMaxPooling3D[T] with Net

Applies global max pooling operation for 3D data.
Applies global max pooling operation for 3D data. Data format currently supported for this layer is 'channels_first' (. padding currently supported for this layer is 'valid'. The input of this layer should be 5D.
When you use this layer as the first layer of a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
T
The numeric type of parameter(e.g. weight, bias). Only support float/double now.
class LocallyConnected1D[T] extends keras.layers.LocallyConnected1D[T] with Net

Locally-connected layer for 1D inputs which works similarly to the TemporalConvolution layer, except that weights are unshared, that is, a different set of filters is applied at each different patch of the input.
Locally-connected layer for 1D inputs which works similarly to the TemporalConvolution layer, except that weights are unshared, that is, a different set of filters is applied at each different patch of the input. Padding currently supported for this layer is 'valid'. The input of this layer should be 3D.
When using this layer as the first layer in a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).
T
The numeric type of parameter(e.g. weight, bias). Only support float/double now.
class MaxPooling1D[T] extends keras.layers.MaxPooling1D[T] with Net

Max pooling operation for temporal data.
Max pooling operation for temporal data.
Input shape 3D tensor with shape: (batch_size, steps, features).
Output shape 3D tensor with shape: (batch_size, downsampled_steps, features).
T
Numeric type of parameter(e.g. weight, bias). Only support float/double now
class Maximum[T] extends Merge[T] with Net

Layer that computes the maximum (element-wise) a list of inputs.
Layer that computes the maximum (element-wise) a list of inputs.
It takes as input a list of nodes, all of the same shape, and returns a single node (also of the same shape).
class Minimum[T] extends Merge[T] with Net

Layer that computes the minimum (element-wise) a list of inputs.
Layer that computes the minimum (element-wise) a list of inputs.
It takes as input a list of nodes, all of the same shape, and returns a single node (also of the same shape).
class SoftMax[T] extends keras.layers.SoftMax[T] with Net

Value Members

object Activation extends Serializable
object Average extends Serializable
object AveragePooling1D extends Serializable
object Conv1D extends Serializable
object Conv2D extends Serializable
object Cropping1D extends Serializable
object Dense extends Serializable
object Dropout extends Serializable
object Flatten extends Serializable
object GlobalAveragePooling1D extends Serializable
object GlobalAveragePooling2D extends Serializable
object GlobalAveragePooling3D extends Serializable
object GlobalMaxPooling1D extends Serializable
object GlobalMaxPooling2D extends Serializable
object GlobalMaxPooling3D extends Serializable
object LocallyConnected1D extends Serializable
object MaxPooling1D extends Serializable
object Maximum extends Serializable
object Minimum extends Serializable
object SoftMax extends Serializable
package utils

package layers

Type Members

class Activation[T] extends keras.layers.Activation[T] with Net

class Average[T] extends Merge[T] with Net

class AveragePooling1D[T] extends keras.layers.AveragePooling1D[T] with Net

class Conv1D[T] extends Convolution1D[T] with Net

class Conv2D[T] extends Convolution2D[T] with Net

class Cropping1D[T] extends keras.layers.Cropping1D[T] with Net

class Dense[T] extends keras.layers.Dense[T] with Net

class Dropout[T] extends keras.layers.Dropout[T] with Net

class Flatten[T] extends keras.layers.Flatten[T] with Net

class GlobalAveragePooling1D[T] extends keras.layers.GlobalAveragePooling1D[T] with Net

class GlobalAveragePooling2D[T] extends keras.layers.GlobalAveragePooling2D[T] with Net

class GlobalAveragePooling3D[T] extends keras.layers.GlobalAveragePooling3D[T] with Net

class GlobalMaxPooling1D[T] extends keras.layers.GlobalMaxPooling1D[T] with Net

class GlobalMaxPooling2D[T] extends keras.layers.GlobalMaxPooling2D[T] with Net

class GlobalMaxPooling3D[T] extends keras.layers.GlobalMaxPooling3D[T] with Net

class LocallyConnected1D[T] extends keras.layers.LocallyConnected1D[T] with Net

class MaxPooling1D[T] extends keras.layers.MaxPooling1D[T] with Net

class Maximum[T] extends Merge[T] with Net

class Minimum[T] extends Merge[T] with Net

class SoftMax[T] extends keras.layers.SoftMax[T] with Net

Value Members

object Activation extends Serializable

object Average extends Serializable

object AveragePooling1D extends Serializable

object Conv1D extends Serializable

object Conv2D extends Serializable

object Cropping1D extends Serializable

object Dense extends Serializable

object Dropout extends Serializable

object Flatten extends Serializable

object GlobalAveragePooling1D extends Serializable

object GlobalAveragePooling2D extends Serializable

object GlobalAveragePooling3D extends Serializable

object GlobalMaxPooling1D extends Serializable

object GlobalMaxPooling2D extends Serializable

object GlobalMaxPooling3D extends Serializable

object LocallyConnected1D extends Serializable

object MaxPooling1D extends Serializable

object Maximum extends Serializable

object Minimum extends Serializable

object SoftMax extends Serializable

package utils

Ungrouped