Class | Description |
---|---|
AvgPool<T extends Number> |
Performs average pooling on the input.
|
AvgPool.Options |
Optional attributes for
AvgPool |
AvgPool3d<T extends Number> |
Performs 3D average pooling on the input.
|
AvgPool3d.Options |
Optional attributes for
AvgPool3d |
AvgPool3dGrad<T extends Number> |
Computes gradients of average pooling function.
|
AvgPool3dGrad.Options |
Optional attributes for
AvgPool3dGrad |
AvgPoolGrad<T extends Number> |
Computes gradients of the average pooling function.
|
AvgPoolGrad.Options |
Optional attributes for
AvgPoolGrad |
BatchNormWithGlobalNormalization<T> |
Batch normalization.
|
BatchNormWithGlobalNormalizationGrad<T> |
Gradients for batch normalization.
|
BiasAdd<T> |
Adds `bias` to `value`.
|
BiasAdd.Options |
Optional attributes for
BiasAdd |
BiasAddGrad<T> |
The backward operation for "BiasAdd" on the "bias" tensor.
|
BiasAddGrad.Options |
Optional attributes for
BiasAddGrad |
ComputeAccidentalHits |
Computes the ids of the positions in sampled_candidates that match true_labels.
|
ComputeAccidentalHits.Options |
Optional attributes for
ComputeAccidentalHits |
Conv2d<T extends Number> |
Computes a 2-D convolution given 4-D `input` and `filter` tensors.
|
Conv2d.Options |
Optional attributes for
Conv2d |
Conv2dBackpropFilter<T extends Number> |
Computes the gradients of convolution with respect to the filter.
|
Conv2dBackpropFilter.Options |
Optional attributes for
Conv2dBackpropFilter |
Conv2dBackpropInput<T extends Number> |
Computes the gradients of convolution with respect to the input.
|
Conv2dBackpropInput.Options |
Optional attributes for
Conv2dBackpropInput |
Conv3d<T extends Number> |
Computes a 3-D convolution given 5-D `input` and `filter` tensors.
|
Conv3d.Options |
Optional attributes for
Conv3d |
Conv3dBackpropFilter<T extends Number> |
Computes the gradients of 3-D convolution with respect to the filter.
|
Conv3dBackpropFilter.Options |
Optional attributes for
Conv3dBackpropFilter |
Conv3dBackpropInput<U extends Number> |
Computes the gradients of 3-D convolution with respect to the input.
|
Conv3dBackpropInput.Options |
Optional attributes for
Conv3dBackpropInput |
CtcBeamSearchDecoder<T extends Number> |
Performs beam search decoding on the logits given in input.
|
CtcBeamSearchDecoder.Options |
Optional attributes for
CtcBeamSearchDecoder |
CtcGreedyDecoder<T extends Number> |
Performs greedy decoding on the logits given in inputs.
|
CtcGreedyDecoder.Options |
Optional attributes for
CtcGreedyDecoder |
CtcLoss<T extends Number> |
Calculates the CTC Loss (log probability) for each batch entry.
|
CtcLoss.Options |
Optional attributes for
CtcLoss |
CudnnRnn<T extends Number> |
A RNN backed by cuDNN.
|
CudnnRnn.Options |
Optional attributes for
CudnnRnn |
CudnnRnnBackprop<T extends Number> |
Backprop step of CudnnRNN.
|
CudnnRnnBackprop.Options |
Optional attributes for
CudnnRnnBackprop |
CudnnRnnCanonicalToParams<T extends Number> |
Converts CudnnRNN params from canonical form to usable form.
|
CudnnRnnCanonicalToParams.Options |
Optional attributes for
CudnnRnnCanonicalToParams |
CudnnRnnParamsSize<U extends Number> |
Computes size of weights that can be used by a Cudnn RNN model.
|
CudnnRnnParamsSize.Options |
Optional attributes for
CudnnRnnParamsSize |
CudnnRnnParamsToCanonical<T extends Number> |
Retrieves CudnnRNN params in canonical form.
|
CudnnRnnParamsToCanonical.Options |
Optional attributes for
CudnnRnnParamsToCanonical |
DataFormatDimMap<T extends Number> |
Returns the dimension index in the destination data format given the one in
|
DataFormatDimMap.Options |
Optional attributes for
DataFormatDimMap |
DataFormatVecPermute<T extends Number> |
Returns the permuted vector/tensor in the destination data format given the
|
DataFormatVecPermute.Options |
Optional attributes for
DataFormatVecPermute |
DepthToSpace<T> |
DepthToSpace for tensors of type T.
|
DepthToSpace.Options |
Optional attributes for
DepthToSpace |
DepthwiseConv2dNative<T extends Number> |
Computes a 2-D depthwise convolution given 4-D `input` and `filter` tensors.
|
DepthwiseConv2dNative.Options |
Optional attributes for
DepthwiseConv2dNative |
DepthwiseConv2dNativeBackpropFilter<T extends Number> |
Computes the gradients of depthwise convolution with respect to the filter.
|
DepthwiseConv2dNativeBackpropFilter.Options |
Optional attributes for
DepthwiseConv2dNativeBackpropFilter |
DepthwiseConv2dNativeBackpropInput<T extends Number> |
Computes the gradients of depthwise convolution with respect to the input.
|
DepthwiseConv2dNativeBackpropInput.Options |
Optional attributes for
DepthwiseConv2dNativeBackpropInput |
Dilation2d<T extends Number> |
Computes the grayscale dilation of 4-D `input` and 3-D `filter` tensors.
|
Dilation2dBackpropFilter<T extends Number> |
Computes the gradient of morphological 2-D dilation with respect to the filter.
|
Dilation2dBackpropInput<T extends Number> |
Computes the gradient of morphological 2-D dilation with respect to the input.
|
Elu<T extends Number> |
Computes exponential linear: `exp(features) - 1` if < 0, `features` otherwise.
|
EluGrad<T extends Number> |
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 Number> |
Performs fractional average pooling on the input.
|
FractionalAvgPool.Options |
Optional attributes for
FractionalAvgPool |
FractionalAvgPoolGrad<T extends Number> |
Computes gradient of the FractionalAvgPool function.
|
FractionalAvgPoolGrad.Options |
Optional attributes for
FractionalAvgPoolGrad |
FractionalMaxPool<T extends Number> |
Performs fractional max pooling on the input.
|
FractionalMaxPool.Options |
Optional attributes for
FractionalMaxPool |
FractionalMaxPoolGrad<T extends Number> |
Computes gradient of the FractionalMaxPool function.
|
FractionalMaxPoolGrad.Options |
Optional attributes for
FractionalMaxPoolGrad |
FusedBatchNorm<T extends Number,U extends Number> |
Batch normalization.
|
FusedBatchNorm.Options |
Optional attributes for
FusedBatchNorm |
FusedBatchNormGrad<T extends Number,U extends Number> |
Gradient for batch normalization.
|
FusedBatchNormGrad.Options |
Optional attributes for
FusedBatchNormGrad |
FusedPadConv2d<T extends Number> |
Performs a padding as a preprocess during a convolution.
|
FusedResizeAndPadConv2d<T extends Number> |
Performs a resize and padding as a preprocess during a convolution.
|
FusedResizeAndPadConv2d.Options |
Optional attributes for
FusedResizeAndPadConv2d |
InTopK |
Says whether the targets are in the top `K` predictions.
|
InvGrad<T> |
Computes the gradient for the inverse of `x` wrt its input.
|
L2Loss<T extends Number> |
L2 Loss.
|
LeakyRelu<T extends Number> |
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 Number> |
Local Response Normalization.
|
LocalResponseNormalization.Options |
Optional attributes for
LocalResponseNormalization |
LocalResponseNormalizationGrad<T extends Number> |
Gradients for Local Response Normalization.
|
LocalResponseNormalizationGrad.Options |
Optional attributes for
LocalResponseNormalizationGrad |
LogSoftmax<T extends Number> |
Computes log softmax activations.
|
MaxPool<T> |
Performs max pooling on the input.
|
MaxPool.Options |
Optional attributes for
MaxPool |
MaxPool3d<T extends Number> |
Performs 3D max pooling on the input.
|
MaxPool3d.Options |
Optional attributes for
MaxPool3d |
MaxPool3dGrad<U extends Number> |
Computes gradients of max pooling function.
|
MaxPool3dGrad.Options |
Optional attributes for
MaxPool3dGrad |
MaxPool3dGradGrad<T extends Number> |
Computes second-order gradients of the maxpooling function.
|
MaxPool3dGradGrad.Options |
Optional attributes for
MaxPool3dGradGrad |
MaxPoolGrad<T extends Number> |
Computes gradients of the maxpooling function.
|
MaxPoolGrad.Options |
Optional attributes for
MaxPoolGrad |
MaxPoolGradGrad<T extends Number> |
Computes second-order gradients of the maxpooling function.
|
MaxPoolGradGrad.Options |
Optional attributes for
MaxPoolGradGrad |
MaxPoolGradGradWithArgmax<T extends Number> |
Computes second-order gradients of the maxpooling function.
|
MaxPoolGradGradWithArgmax.Options |
Optional attributes for
MaxPoolGradGradWithArgmax |
MaxPoolGradWithArgmax<T extends Number> |
Computes gradients of the maxpooling function.
|
MaxPoolGradWithArgmax.Options |
Optional attributes for
MaxPoolGradWithArgmax |
MaxPoolWithArgmax<T extends Number,U extends Number> |
Performs max pooling on the input and outputs both max values and indices.
|
MaxPoolWithArgmax.Options |
Optional attributes for
MaxPoolWithArgmax |
NthElement<T extends Number> |
Finds values of the `n`-th order statistic for the last dimension.
|
NthElement.Options |
Optional attributes for
NthElement |
QuantizedAvgPool<T> |
Produces the average pool of the input tensor for quantized types.
|
QuantizedBatchNormWithGlobalNormalization<U> |
Quantized Batch normalization.
|
QuantizedBiasAdd<V> |
Adds Tensor 'bias' to Tensor 'input' for Quantized types.
|
QuantizedConv2d<V> |
Computes a 2D convolution given quantized 4D input and filter tensors.
|
QuantizedConv2d.Options |
Optional attributes for
QuantizedConv2d |
QuantizedInstanceNorm<T> |
Quantized Instance normalization.
|
QuantizedInstanceNorm.Options |
Optional attributes for
QuantizedInstanceNorm |
QuantizedMaxPool<T> |
Produces the max pool of the input tensor for quantized types.
|
QuantizedRelu<U> |
Computes Quantized Rectified Linear: `max(features, 0)`
|
QuantizedRelu6<U> |
Computes Quantized Rectified Linear 6: `min(max(features, 0), 6)`
|
QuantizedReluX<U> |
Computes Quantized Rectified Linear X: `min(max(features, 0), max_value)`
|
Relu<T> |
Computes rectified linear: `max(features, 0)`.
|
Relu6<T extends Number> |
Computes rectified linear 6: `min(max(features, 0), 6)`.
|
Relu6Grad<T extends Number> |
Computes rectified linear 6 gradients for a Relu6 operation.
|
ReluGrad<T extends Number> |
Computes rectified linear gradients for a Relu operation.
|
Selu<T extends Number> |
Computes scaled exponential linear: `scale * alpha * (exp(features) - 1)`
|
SeluGrad<T extends Number> |
Computes gradients for the scaled exponential linear (Selu) operation.
|
Softmax<T extends Number> |
Computes softmax activations.
|
SoftmaxCrossEntropyWithLogits<T extends Number> |
Computes softmax cross entropy cost and gradients to backpropagate.
|
Softsign<T extends Number> |
Computes softsign: `features / (abs(features) + 1)`.
|
SoftsignGrad<T extends Number> |
Computes softsign gradients for a softsign operation.
|
SpaceToBatch<T> |
SpaceToBatch for 4-D tensors of type T.
|
SpaceToDepth<T> |
SpaceToDepth for tensors of type T.
|
SpaceToDepth.Options |
Optional attributes for
SpaceToDepth |
SparseSoftmaxCrossEntropyWithLogits<T extends Number> |
Computes softmax cross entropy cost and gradients to backpropagate.
|
TopK<T extends Number> |
Finds values and indices of the `k` largest elements for the last dimension.
|
TopK.Options |
Optional attributes for
TopK |
Copyright © 2022. All rights reserved.