sequence_linear.py 文件源码

def backward_gpu(self, inputs, gy):
        x = inputs[0]
        W = inputs[1]
        # Backprop weight
        gW = cuda.cupy.empty_like(W)
        handle = cuda.Device().cublas_handle
        k, n = gy[0].shape[0] * gy[0].shape[1], W.shape[0]
        m = W.shape[1]
        lda = max(1, x.shape[-1])
        ldb = max(1, gy[0].shape[-1])
        ldc = max(1, m)
        sgemm(handle, False, True, m, n, k, 1, gy[0].data.ptr, ldb,
              x.data.ptr, lda, 1, gW.data.ptr, ldc)
        # Backprop input
        m, k = W.shape
        n, l = x.shape[0] * x.shape[1], gy[0].shape[2]
        lda = max(1, gy[0].shape[-1])
        ldb = max(1, W.shape[1])
        ldc = max(1, m)
        gx = cuda.cupy.empty_like(x)
        sgemm(handle, True, False, m, n, k, 1, W.data.ptr, ldb,
              gy[0].data.ptr, lda, 0, gx.data.ptr, ldc)
        # Backprop bias
        if len(inputs) > 2:
            gy_2d = _as_mat(gy[0])
            gb = gy_2d.sum(0)
            return gx, gW, gb
        else:
            return gx, gW