hello, thanks for sharing your code. But I have a question why the preprocessing method differs from the official preprocessing method of pytorch. Your method preprocesses the BGR format image with std value (1.0,1.0,1.0) link however, the pytorch official method preprocesses RGB format image with std value (0.229, 0.224, 0.225) link
hello, thanks for sharing your code. But I have a question why the preprocessing method differs from the official preprocessing method of pytorch. Your method preprocesses the BGR format image with std value (1.0,1.0,1.0) link however, the pytorch official method preprocesses RGB format image with std value (0.229, 0.224, 0.225) link