Fork自 PaddlePaddle / Paddle
体验新版 GitCode,发现更多精彩内容 >>
- backward_api : conv3d_grad
forward : conv3d (Tensor x, Tensor kernel, int[] paddings, int[] dilations, int[] strides, int groups, bool subm) -> Tensor(out@SparseCooTensor), Tensor(rulebook@DenseTensor) args : (Tensor x, Tensor kernel, Tensor rulebook, Tensor out_grad, int[] paddings, int[] dilations, int[] strides, int groups, bool subm)
output : Tensor(x_grad@DenseTensor), Tensor(kernel_grad@DenseTensor) kernel :
func : sparse_conv3d_grad
- backward_api : sparse_relu_grad forward : sparse_relu(Tensor x) -> Tensor(out@SparseCooTensor) args : (Tensor x, Tensor out_grad) output : Tensor(x_grad@SparseCooTensor) kernel : func : sparse_relu_grad