com.intel.analytics.zoo.pipeline.api.keras.layers
Number of convolution filters to use.
Number of rows in the convolution kernel.
Number of columns in the convolution kernel.
Initialization method for the weights of the layer. Default is Xavier. You can also pass in corresponding string representations such as 'glorot_uniform' or 'normal', etc. for simple init methods in the factory method.
Activation function to use. Default is null. You can also pass in corresponding string representations such as 'relu' or 'sigmoid', etc. for simple activations in the factory method.
Either 'valid' or 'same'. Default is 'valid'.
Int array of length 2 corresponding to the step of the convolution in the height and width dimension. Also called strides elsewhere. Default is (1, 1).
How many output channel to use per input channel for the depthwise convolution step. Integer. Default is 1.
Format of input data. Either DataFormat.NCHW (dimOrdering='th') or DataFormat.NHWC (dimOrdering='tf'). Default is NCHW.
An instance of Regularizer, (eg. L1 or L2 regularization), applied to the depthwise weights matrices. Default is null.
An instance of Regularizer, applied to the pointwise weights matrices. Default is null.
An instance of Regularizer, applied to the bias. Default is null.
Whether to include a bias (i.e. make the layer affine rather than linear). Default is true.
A Single Shape, does not include the batch dimension.
Activation function to use.
Activation function to use. Default is null. You can also pass in corresponding string representations such as 'relu' or 'sigmoid', etc. for simple activations in the factory method.
An instance of Regularizer, applied to the bias.
An instance of Regularizer, applied to the bias. Default is null.
Whether to include a bias (i.e.
Whether to include a bias (i.e. make the layer affine rather than linear). Default is true.
Either 'valid' or 'same'.
Either 'valid' or 'same'. Default is 'valid'.
How many output channel to use per input channel for the depthwise convolution step.
How many output channel to use per input channel for the depthwise convolution step. Integer. Default is 1.
An instance of Regularizer, (eg.
An instance of Regularizer, (eg. L1 or L2 regularization), applied to the depthwise weights matrices. Default is null.
Format of input data.
Format of input data. Either DataFormat.NCHW (dimOrdering='th') or DataFormat.NHWC (dimOrdering='tf'). Default is NCHW.
Build graph: some other modules point to current module
Build graph: some other modules point to current module
upstream variables
Variable containing current module
Initialization method for the weights of the layer.
Initialization method for the weights of the layer. Default is Xavier. You can also pass in corresponding string representations such as 'glorot_uniform' or 'normal', etc. for simple init methods in the factory method.
A Single Shape, does not include the batch dimension.
A Single Shape, does not include the batch dimension.
Number of columns in the convolution kernel.
Number of columns in the convolution kernel.
Number of convolution filters to use.
Number of convolution filters to use.
Number of rows in the convolution kernel.
Number of rows in the convolution kernel.
An instance of Regularizer, applied to the pointwise weights matrices.
An instance of Regularizer, applied to the pointwise weights matrices. Default is null.
Int array of length 2 corresponding to the step of the convolution in the height and width dimension.
Int array of length 2 corresponding to the step of the convolution in the height and width dimension. Also called strides elsewhere. Default is (1, 1).
(Since version 0.3.0) please use recommended saveModule(path, overWrite)
Applies separable convolution operator for 2D inputs. Separable convolutions consist in first performing a depthwise spatial convolution (which acts on each input channel separately) followed by a pointwise convolution which mixes together the resulting output channels. The depthMultiplier argument controls how many output channels are generated per input channel in the depthwise step. You can also use SeparableConv2D as an alias of this layer. The input of this layer should be 4D.
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). e.g. inputShape=Shape(3, 128, 128) for 128x128 RGB pictures.
The numeric type of parameter(e.g. weight, bias). Only support float/double now.