jarun.vtn
Results
2
comments of
jarun.vtn
Try checking if your input tensor shape to cvcuda.as_tensor() is 4 dimensions. I got the same error when I use 'NHWC' with three dimensions tensor, it should be just 'HWC'.
[QUESTION] : Must the shape of the output tensor for warp_affine_into be same with its input tensor?
You have to set dst dimension as you desire. This work for me. ``` dst = torch.empty((h, w, c), device='cuda').to(torch.uint8) dst = cvcuda.as_tensor(dst, 'HWC') ```