org.tensorflow.op.nn

Stay organized with collections Save and categorize content based on your preferences.

Classes

AvgPool<T extends TNumber> Performs average pooling on the input. 
AvgPool.Options Optional attributes for AvgPool  
AvgPool3d<T extends TNumber> Performs 3D average pooling on the input. 
AvgPool3d.Options Optional attributes for AvgPool3d  
AvgPool3dGrad<T extends TNumber> Computes gradients of average pooling function. 
AvgPool3dGrad.Options Optional attributes for AvgPool3dGrad  
AvgPoolGrad<T extends TNumber> Computes gradients of the average pooling function. 
AvgPoolGrad.Options Optional attributes for AvgPoolGrad  
BatchNormWithGlobalNormalization<T extends TType> Batch normalization. 
BatchNormWithGlobalNormalizationGrad<T extends TType> Gradients for batch normalization. 
BiasAdd<T extends TType> Adds `bias` to `value`. 
BiasAdd.Options Optional attributes for BiasAdd  
BiasAddGrad<T extends TType> The backward operation for "BiasAdd" on the "bias" tensor. 
BiasAddGrad.Options Optional attributes for BiasAddGrad  
BlockLSTM<T extends TNumber> Computes the LSTM cell forward propagation for all the time steps. 
BlockLSTM.Options Optional attributes for BlockLSTM  
BlockLSTMGrad<T extends TNumber> Computes the LSTM cell backward propagation for the entire time sequence. 
ComputeAccidentalHits Computes the ids of the positions in sampled_candidates that match true_labels. 
ComputeAccidentalHits.Options Optional attributes for ComputeAccidentalHits  
Conv2d<T extends TNumber> Computes a 2-D convolution given 4-D `input` and `filter` tensors. 
Conv2d.Options Optional attributes for Conv2d  
Conv2dBackpropFilter<T extends TNumber> Computes the gradients of convolution with respect to the filter. 
Conv2dBackpropFilter.Options Optional attributes for Conv2dBackpropFilter  
Conv2dBackpropInput<T extends TNumber> Computes the gradients of convolution with respect to the input. 
Conv2dBackpropInput.Options Optional attributes for Conv2dBackpropInput  
Conv3d<T extends TNumber> Computes a 3-D convolution given 5-D `input` and `filter` tensors. 
Conv3d.Options Optional attributes for Conv3d  
Conv3dBackpropFilter<T extends TNumber> Computes the gradients of 3-D convolution with respect to the filter. 
Conv3dBackpropFilter.Options Optional attributes for Conv3dBackpropFilter  
Conv3dBackpropInput<U extends TNumber> Computes the gradients of 3-D convolution with respect to the input. 
Conv3dBackpropInput.Options Optional attributes for Conv3dBackpropInput  
CtcBeamSearchDecoder<T extends TNumber> Performs beam search decoding on the logits given in input. 
CtcBeamSearchDecoder.Options Optional attributes for CtcBeamSearchDecoder  
CtcGreedyDecoder<T extends TNumber> Performs greedy decoding on the logits given in inputs. 
CtcGreedyDecoder.Options Optional attributes for CtcGreedyDecoder  
CtcLoss<T extends TNumber> Calculates the CTC Loss (log probability) for each batch entry. 
CtcLoss.Options Optional attributes for CtcLoss  
CTCLossV2 Calculates the CTC Loss (log probability) for each batch entry. 
CTCLossV2.Options Optional attributes for CTCLossV2  
CudnnRNN<T extends TNumber> A RNN backed by cuDNN. 
CudnnRNN.Options Optional attributes for CudnnRNN  
CudnnRNNBackprop<T extends TNumber> Backprop step of CudnnRNNV3. 
CudnnRNNBackprop.Options Optional attributes for CudnnRNNBackprop  
CudnnRNNCanonicalToParams<T extends TNumber> Converts CudnnRNN params from canonical form to usable form. 
CudnnRNNCanonicalToParams.Options Optional attributes for CudnnRNNCanonicalToParams  
CudnnRnnParamsSize<U extends TNumber> Computes size of weights that can be used by a Cudnn RNN model. 
CudnnRnnParamsSize.Options Optional attributes for CudnnRnnParamsSize  
CudnnRNNParamsToCanonical<T extends TNumber> Retrieves CudnnRNN params in canonical form. 
CudnnRNNParamsToCanonical.Options Optional attributes for CudnnRNNParamsToCanonical  
DataFormatDimMap<T extends TNumber> Returns the dimension index in the destination data format given the one in

the source data format. 

DataFormatDimMap.Options Optional attributes for DataFormatDimMap  
DataFormatVecPermute<T extends TNumber> Permute input tensor from `src_format` to `dst_format`. 
DataFormatVecPermute.Options Optional attributes for DataFormatVecPermute  
DepthToSpace<T extends TType> DepthToSpace for tensors of type T. 
DepthToSpace.Options Optional attributes for DepthToSpace  
DepthwiseConv2dNative<T extends TNumber> Computes a 2-D depthwise convolution given 4-D `input` and `filter` tensors. 
DepthwiseConv2dNative.Options Optional attributes for DepthwiseConv2dNative  
DepthwiseConv2dNativeBackpropFilter<T extends TNumber> Computes the gradients of depthwise convolution with respect to the filter. 
DepthwiseConv2dNativeBackpropFilter.Options Optional attributes for DepthwiseConv2dNativeBackpropFilter  
DepthwiseConv2dNativeBackpropInput<T extends TNumber> Computes the gradients of depthwise convolution with respect to the input. 
DepthwiseConv2dNativeBackpropInput.Options Optional attributes for DepthwiseConv2dNativeBackpropInput  
Dilation2d<T extends TNumber> Computes the grayscale dilation of 4-D `input` and 3-D `filter` tensors. 
Dilation2dBackpropFilter<T extends TNumber> Computes the gradient of morphological 2-D dilation with respect to the filter. 
Dilation2dBackpropInput<T extends TNumber> Computes the gradient of morphological 2-D dilation with respect to the input. 
Elu<T extends TNumber> Computes exponential linear: `exp(features) - 1` if < 0, `features` otherwise. 
EluGrad<T extends TNumber> Computes gradients for the exponential linear (Elu) operation. 
FixedUnigramCandidateSampler Generates labels for candidate sampling with a learned unigram distribution. 
FixedUnigramCandidateSampler.Options Optional attributes for FixedUnigramCandidateSampler  
FractionalAvgPool<T extends TNumber> Performs fractional average pooling on the input. 
FractionalAvgPool.Options Optional attributes for FractionalAvgPool  
FractionalAvgPoolGrad<T extends TNumber> Computes gradient of the FractionalAvgPool function. 
FractionalAvgPoolGrad.Options Optional attributes for FractionalAvgPoolGrad  
FractionalMaxPool<T extends TNumber> Performs fractional max pooling on the input. 
FractionalMaxPool.Options Optional attributes for FractionalMaxPool  
FractionalMaxPoolGrad<T extends TNumber> Computes gradient of the FractionalMaxPool function. 
FractionalMaxPoolGrad.Options Optional attributes for FractionalMaxPoolGrad  
FusedBatchNorm<T extends TNumber, U extends TNumber> Batch normalization. 
FusedBatchNorm.Options Optional attributes for FusedBatchNorm  
FusedBatchNormGrad<T extends TNumber, U extends TNumber> Gradient for batch normalization. 
FusedBatchNormGrad.Options Optional attributes for FusedBatchNormGrad  
FusedPadConv2d<T extends TNumber> Performs a padding as a preprocess during a convolution. 
FusedResizeAndPadConv2d<T extends TNumber> Performs a resize and padding as a preprocess during a convolution. 
FusedResizeAndPadConv2d.Options Optional attributes for FusedResizeAndPadConv2d  
GRUBlockCell<T extends TNumber> Computes the GRU cell forward propagation for 1 time step. 
GRUBlockCellGrad<T extends TNumber> Computes the GRU cell back-propagation for 1 time step. 
InTopK Says whether the targets are in the top `K` predictions. 
InvGrad<T extends TType> Computes the gradient for the inverse of `x` wrt its input. 
IsotonicRegression<U extends TNumber> Solves a batch of isotonic regression problems. 
L2Loss<T extends TNumber> L2 Loss. 
LeakyRelu<T extends TNumber> Computes rectified linear: `max(features, features * alpha)`. 
LeakyRelu.Options Optional attributes for LeakyRelu  
LearnedUnigramCandidateSampler Generates labels for candidate sampling with a learned unigram distribution. 
LearnedUnigramCandidateSampler.Options Optional attributes for LearnedUnigramCandidateSampler  
LocalResponseNormalization<T extends TNumber> Local Response Normalization. 
LocalResponseNormalization.Options Optional attributes for LocalResponseNormalization  
LocalResponseNormalizationGrad<T extends TNumber> Gradients for Local Response Normalization. 
LocalResponseNormalizationGrad.Options Optional attributes for LocalResponseNormalizationGrad  
LogSoftmax<T extends TNumber> Computes log softmax activations. 
LSTMBlockCell<T extends TNumber> Computes the LSTM cell forward propagation for 1 time step. 
LSTMBlockCell.Options Optional attributes for LSTMBlockCell  
LSTMBlockCellGrad<T extends TNumber> Computes the LSTM cell backward propagation for 1 timestep. 
MaxPool<T extends TType> Performs max pooling on the input. 
MaxPool.Options Optional attributes for MaxPool  
MaxPool3d<T extends TNumber> Performs 3D max pooling on the input. 
MaxPool3d.Options Optional attributes for MaxPool3d  
MaxPool3dGrad<U extends TNumber> Computes gradients of 3D max pooling function. 
MaxPool3dGrad.Options Optional attributes for MaxPool3dGrad  
MaxPool3dGradGrad<T extends TNumber> Computes second-order gradients of the maxpooling function. 
MaxPool3dGradGrad.Options Optional attributes for MaxPool3dGradGrad  
MaxPoolGrad<T extends TNumber> Computes gradients of the maxpooling function. 
MaxPoolGrad.Options Optional attributes for MaxPoolGrad  
MaxPoolGradGrad<T extends TNumber> Computes second-order gradients of the maxpooling function. 
MaxPoolGradGrad.Options Optional attributes for MaxPoolGradGrad  
MaxPoolGradGradWithArgmax<T extends TNumber> Computes second-order gradients of the maxpooling function. 
MaxPoolGradGradWithArgmax.Options Optional attributes for MaxPoolGradGradWithArgmax  
MaxPoolGradWithArgmax<T extends TNumber> Computes gradients of the maxpooling function. 
MaxPoolGradWithArgmax.Options Optional attributes for MaxPoolGradWithArgmax  
MaxPoolWithArgmax<T extends TNumber, U extends TNumber> Performs max pooling on the input and outputs both max values and indices. 
MaxPoolWithArgmax.Options Optional attributes for MaxPoolWithArgmax  
NthElement<T extends TNumber> Finds values of the `n`-th order statistic for the last dimension. 
NthElement.Options Optional attributes for NthElement  
QuantizedAvgPool<T extends TType> Produces the average pool of the input tensor for quantized types. 
QuantizedBatchNormWithGlobalNormalization<U extends TType> Quantized Batch normalization. 
QuantizedBiasAdd<V extends TType> Adds Tensor 'bias' to Tensor 'input' for Quantized types. 
QuantizedConv2d<V extends TType> Computes a 2D convolution given quantized 4D input and filter tensors. 
QuantizedConv2d.Options Optional attributes for QuantizedConv2d  
QuantizedConv2DAndRelu<V extends TType>  
QuantizedConv2DAndRelu.Options Optional attributes for QuantizedConv2DAndRelu  
QuantizedConv2DAndReluAndRequantize<V extends TType>  
QuantizedConv2DAndReluAndRequantize.Options Optional attributes for QuantizedConv2DAndReluAndRequantize  
QuantizedConv2DAndRequa