def process(self, ellLayers):
"""Helper to convert a binary convolutional layer to the ELL equivalent."""
# A CNTK Binary Convolutional layer is a single function.
# Bias and Activation are separate layers (processed outside of this class).
weightsTensor = converters.get_float_tensor_from_cntk_convolutional_weight_parameter(
self.weights_parameter)
layerParameters = ELL.LayerParameters(
self.layer.ell_inputShape, self.layer.ell_inputPaddingParameters,
self.layer.ell_outputShape, self.layer.ell_outputPaddingParameters)
# Fill in the convolutional parameters
weightsShape = self.weights_parameter.shape
receptiveField = weightsShape[2]
stride = self.attributes['strides'][2]
convolutionalParameters = ELL.BinaryConvolutionalParameters(
receptiveField, stride, self.convolution_method,
self.weights_scale)
ellLayers.append(
ELL.FloatBinaryConvolutionalLayer(layerParameters,
convolutionalParameters,
weightsTensor))
def process(self, ellLayers):
"""Appends the ELL representation of the current layer to ellLayers."""
preluTensor = converters.get_float_tensor_from_cntk_convolutional_weight_parameter(
self.prelu_parameter)
# Create the ell.LayerParameters for the ELL layer
layerParameters = ell.LayerParameters(
self.layer.ell_inputShape, self.layer.ell_inputPaddingParameters, self.layer.ell_outputShape, self.layer.ell_outputPaddingParameters)
# Create the ELL PReLU activation layer
ellLayers.append(ell.FloatPReLUActivationLayer(
layerParameters, preluTensor))
def process(self, ellLayers):
"""Helper to convert a convolutional layer to the ELL equivalent."""
# Note that a single CNTK Convolutional function block is equivalent to the following 3 ELL layers:
# - ConvolutionalLayer
# - BiasLayer
# - ActivationLayer. This layer is sometimes missing, depending on activation type.
#
# Therefore, make sure the output padding characteristics of the last layer reflect the next layer's
# padding requirements.
weightsTensor = converters.get_float_tensor_from_cntk_convolutional_weight_parameter(
self.weights_parameter)
biasVector = converters.get_float_vector_from_cntk_trainable_parameter(
self.bias_parameter)
# Create the ELL.LayerParameters for the various ELL layers
firstLayerParameters = ELL.LayerParameters(
self.layer.ell_inputShape, self.layer.ell_inputPaddingParameters,
self.layer.ell_outputShapeMinusPadding, ELL.NoPadding())
middleLayerParameters = ELL.LayerParameters(
self.layer.ell_outputShapeMinusPadding, ELL.NoPadding(),
self.layer.ell_outputShapeMinusPadding, ELL.NoPadding())
lastLayerParameters = ELL.LayerParameters(
self.layer.ell_outputShapeMinusPadding, ELL.NoPadding(),
self.layer.ell_outputShape, self.layer.ell_outputPaddingParameters)
layerParameters = firstLayerParameters
# Fill in the convolutional parameters
weightsShape = self.weights_parameter.shape
receptiveField = weightsShape[2]
stride = self.attributes['strides'][2]
filterBatchSize = layerParameters.outputShape.channels
internalNodes = utilities.get_model_layers(self.layer.block_root)
activationType = utilities.get_ell_activation_type(internalNodes)
convolutionalParameters = ELL.ConvolutionalParameters(
receptiveField, stride, self.convolution_method, filterBatchSize)
# Create the ELL convolutional layer
ellLayers.append(
ELL.FloatConvolutionalLayer(layerParameters,
convolutionalParameters,
weightsTensor))
# Create the ELL bias layer
isSoftmaxActivation = utilities.is_softmax_activation(internalNodes)
hasActivation = isSoftmaxActivation or activationType != None
if (hasActivation):
layerParameters = middleLayerParameters
else:
layerParameters = lastLayerParameters
ellLayers.append(ELL.FloatBiasLayer(layerParameters, biasVector))
# Create the ELL activation layer
if (hasActivation):
layerParameters = lastLayerParameters
# Special case: if this is softmax activation, create an ELL Softmax layer.
# Else, insert an ELL ActivationLayer
if (isSoftmaxActivation):
ellLayers.append(ELL.FloatSoftmaxLayer(layerParameters))
else:
ellLayers.append(
ELL.FloatActivationLayer(layerParameters, activationType))
