pub fn convolve2_gradient_nn<T>(
incoming_grad: &Array<T>,
original_signal: &Array<T>,
original_filter: &Array<T>,
convolved_output: &Array<T>,
strides: Dim4,
padding: Dim4,
dilation: Dim4,
grad_type: ConvGradientType
) -> Array<T> where
T: HasAfEnum + RealFloating,
Backward pass gradient of 2D convolution
incoming_gradient
gradients to be distributed in backwards passoriginal_signal
input signal to forward pass of convolution assumed structure of input is ( d0 x d1 x d2 x N )original_filter
input filter to forward pass of convolution assumed structure of input is ( d0 x d1 x d2 x N )convolved_output
output from forward pass of convolutionstrides
are distance between consecutive elements along each dimension for original convolutionpadding
specifies padding width along each dimension for original convolutiondilation
specifies filter dilation along each dimension for original convolutiongrad_type
specifies which gradient to returnGradient Array w.r.t input generated from convolve2_nn
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4