Closed Usernamezhx closed 4 years ago
This is very likely caused by the difference between Pillow and OpenCV. PyTorch uses Pillow to load & resize images, cv2 uses OpenCV. There are a lot of similar discussions: https://discuss.pytorch.org/t/torchvision-resize-vs-cv2-resize/47530, https://discuss.pytorch.org/t/difference-between-pil-resize-and-opencv-resize/33138.
thanks for your reply.
first of all. thanks for work. it is what i want. the opencv _transform snippet output
the pytorch transform output
the result : tensor(0.2453) 0.1939379