def process(self, ellLayers): """Appends the ELL representation of the current layer to ellLayers.""" # Note that a single CNTK Linear function block is equivalent to the following 3 ELL layers: # - FullyConnectedLayer # - 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. weightsParameter = utilities.find_parameter_by_name( self.layer.parameters, 'W', 0) biasParameter = utilities.find_parameter_by_name( self.layer.parameters, 'b', 1) weightsTensor = converters.get_float_tensor_from_cntk_dense_weight_parameter( weightsParameter) biasVector = converters.get_float_vector_from_cntk_trainable_parameter( biasParameter) # 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 internalNodes = utilities.get_model_layers(self.layer.block_root) activationType = utilities.get_ell_activation_type(internalNodes) # Create the ELL fully connected layer ellLayers.append( ELL.FloatFullyConnectedLayer(layerParameters, 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))
def __init__(self, layer): if not layer.is_block: raise ValueError("Activation node is not a block node") self.op_name = 'Activation' super().__init__(layer) internal_nodes = utilities.get_model_layers(self.layer.block_root) self.activation_type = utilities.get_ell_activation_type(internal_nodes) self.additional_layer_text = utilities.get_cntk_activation_name(internal_nodes)
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))