- addBias
Operation addBias(Operation input, Operation bias, string mod, size_t line)
Undocumented in source. Be warned that the author may not have intended to support it.
- addBiasGrad
Operation addBiasGrad(Operation parentGrad, string mod, size_t line)
Undocumented in source. Be warned that the author may not have intended to support it.
- batchNormGrad
Operation batchNormGrad(Operation parentGrad, Operation input, Operation scale, string mod, size_t line)
Undocumented in source. Be warned that the author may not have intended to support it.
- batchNormTrain
Operation batchNormTrain(Operation input, Operation scale, Operation bias, string mod, size_t line)
Undocumented in source. Be warned that the author may not have intended to support it.
- convolution
Operation convolution(Operation features, Operation filters, size_t[] padding, size_t[] stride, string mod, size_t line)
Creates a convolution operation that performs the computation required to implement a convolutional layer.
- convolutionFeaturesGrad
Operation convolutionFeaturesGrad(Operation parentGrad, Operation filters, size_t[] featuresShape, size_t[] padding, size_t[] stride, string mod, size_t line)
Creates an operation representing the derivative of a convolution operation with respect to the feature maps.
- convolutionFiltersGrad
Operation convolutionFiltersGrad(Operation parentGrad, Operation features, size_t[] filtersShape, size_t[] padding, size_t[] stride, string mod, size_t line)
Creates an operation representing the derivative of a convolution operation with respect to the filters.
- convolutionTranspose
Operation convolutionTranspose(Operation features, Operation filters, size_t[] padding, size_t[] stride, string mod, size_t line)
Creates a transposed convolution operation (also known, incorrectly, as deconvolution).
- initialize
void initialize()
Undocumented in source. Be warned that the author may not have intended to support it.
- maxpool
Operation maxpool(Operation features, size_t[] dims, string mod, size_t line)
Creates a max pool operation that performs the computation required to implement a max pooling layer.
- maxpoolGrad
Operation maxpoolGrad(Operation parentGrad, Operation op, string mod, size_t line)
Creates an operation representing the derivative of a maxpool operation with respect to the feature maps.
- softmax
Operation softmax(Operation inputs, string mod, size_t line)
Creates an operation representing the computation required for a softmax layer.
- softmaxGrad
Operation softmaxGrad(Operation parentGrad, Operation op, string mod, size_t line)
Creates an operation representing the gradient of the softmax function.
Contains common neural network operations.
These operations are currently only implemented for the CUDA backend.