Nn Ops

Summary

Classes

tensorflow:: ops:: AvgPool

Performs average pooling on the input.

tensorflow:: ops:: AvgPool3D

Performs 3D average pooling on the input.

tensorflow:: ops:: AvgPool3DGrad

Computes gradients of average pooling function.

tensorflow:: ops:: BiasAdd

Adds bias to value .

tensorflow:: ops:: BiasAddGrad

The backward operation for "BiasAdd" on the "bias" tensor.

tensorflow:: ops:: Conv2D

Computes a 2-D convolution given 4-D input and filter tensors.

tensorflow:: ops:: Conv2DBackpropFilter

Computes the gradients of convolution with respect to the filter.

tensorflow:: ops:: Conv2DBackpropInput

Computes the gradients of convolution with respect to the input.

tensorflow:: ops:: Conv3D

Computes a 3-D convolution given 5-D input and filter tensors.

tensorflow:: ops:: Conv3DBackpropFilterV2

Computes the gradients of 3-D convolution with respect to the filter.

tensorflow:: ops:: Conv3DBackpropInputV2

Computes the gradients of 3-D convolution with respect to the input.

tensorflow:: ops:: DataFormatDimMap

Returns the dimension index in the destination data format given the one in.

tensorflow:: ops:: DataFormatVecPermute

Permute input tensor from src_format to dst_format .

tensorflow:: ops:: DepthwiseConv2dNative

Computes a 2-D depthwise convolution given 4-D input and filter tensors.

tensorflow:: ops:: DepthwiseConv2dNativeBackpropFilter

Computes the gradients of depthwise convolution with respect to the filter.

tensorflow:: ops:: DepthwiseConv2dNativeBackpropInput

Computes the gradients of depthwise convolution with respect to the input.

tensorflow:: ops:: Dilation2D

Computes the grayscale dilation of 4-D input and 3-D filter tensors.

tensorflow:: ops:: Dilation2DBackpropFilter

Computes the gradient of morphological 2-D dilation with respect to the filter.

tensorflow:: ops:: Dilation2DBackpropInput

Computes the gradient of morphological 2-D dilation with respect to the input.

tensorflow:: ops:: Elu

Computes the exponential linear function.

tensorflow:: ops:: FractionalAvgPool

Performs fractional average pooling on the input.

tensorflow:: ops:: FractionalMaxPool

Performs fractional max pooling on the input.

tensorflow:: ops:: FusedBatchNorm

Batch normalization.

tensorflow:: ops:: FusedBatchNormGrad

Gradient for batch normalization.

tensorflow:: ops:: FusedBatchNormGradV2

Gradient for batch normalization.

tensorflow:: ops:: FusedBatchNormGradV3

Gradient for batch normalization.

tensorflow:: ops:: FusedBatchNormV2

Batch normalization.

tensorflow:: ops:: FusedBatchNormV3

Batch normalization.

tensorflow:: ops:: FusedPadConv2D

Performs a padding as a preprocess during a convolution.

tensorflow:: ops:: FusedResizeAndPadConv2D

Performs a resize and padding as a preprocess during a convolution.

tensorflow:: ops:: InTopK

Says whether the targets are in the top K predictions.

tensorflow:: ops:: InTopKV2

Says whether the targets are in the top K predictions.

tensorflow:: ops:: L2Loss

L2 Loss.

tensorflow:: ops:: LRN

Local Response Normalization.

tensorflow:: ops:: LogSoftmax

Computes log softmax activations.

tensorflow:: ops:: MaxPool

Performs max pooling on the input.

tensorflow:: ops:: MaxPool3D

Performs 3D max pooling on the input.

tensorflow:: ops:: MaxPool3DGrad

Computes gradients of 3D max pooling function.

tensorflow:: ops:: MaxPool3DGradGrad

Computes second-order gradients of the maxpooling function.

tensorflow:: ops:: MaxPoolGradGrad

Computes second-order gradients of the maxpooling function.

tensorflow:: ops:: MaxPoolGradGradV2

Computes second-order gradients of the maxpooling function.

tensorflow:: ops:: MaxPoolGradGradWithArgmax

Computes second-order gradients of the maxpooling function.

tensorflow:: ops:: MaxPoolGradV2

Computes gradients of the maxpooling function.

tensorflow:: ops:: MaxPoolV2

Performs max pooling on the input.

tensorflow:: ops:: MaxPoolWithArgmax

Performs max pooling on the input and outputs both max values and indices.

tensorflow:: ops:: NthElement

Finds values of the n -th order statistic for the last dimension.

tensorflow:: ops:: QuantizedAvgPool

Produces the average pool of the input tensor for quantized types.

tensorflow:: ops:: QuantizedBatchNormWithGlobalNormalization

Quantized Batch normalization.

tensorflow:: ops:: QuantizedBiasAdd

Adds Tensor 'bias' to Tensor 'input' for Quantized types.

tensorflow:: ops:: QuantizedConv2D

Computes a 2D convolution given quantized 4D input and filter tensors.

tensorflow:: ops:: QuantizedMaxPool

Produces the max pool of the input tensor for quantized types.

tensorflow:: ops:: QuantizedRelu

Computes Quantized Rectified Linear: max(features, 0)

tensorflow:: ops:: QuantizedRelu6

Computes Quantized Rectified Linear 6: min(max(features, 0), 6)

tensorflow:: ops:: QuantizedReluX

Computes Quantized Rectified Linear X: min(max(features, 0), max_value)

tensorflow:: ops:: Relu

Computes rectified linear: max(features, 0) .

tensorflow:: ops:: Relu6

Computes rectified linear 6: min(max(features, 0), 6) .

tensorflow:: ops:: Selu

Computes scaled exponential linear: scale * alpha * (exp(features) - 1)

tensorflow:: ops:: Softmax

Computes softmax activations.

tensorflow:: ops:: SoftmaxCrossEntropyWithLogits

Computes softmax cross entropy cost and gradients to backpropagate.

tensorflow:: ops:: Softplus

TODO: add doc.

tensorflow:: ops:: Softsign

Computes softsign: features / (abs(features) + 1) .

tensorflow:: ops:: SparseSoftmaxCrossEntropyWithLogits

Computes softmax cross entropy cost and gradients to backpropagate.

tensorflow:: ops:: TopK

Finds values and indices of the k largest elements for the last dimension.