In your default setting, "gpu_trans" is True. but training preprocessor uses "gpu_trans=True" and eval preprocessor uses "gpu_trans=False".
So data' range is different from training phrase and eval
By the way, model.forward has no operation to normalize data range for training phrase, so is is a big bug
In your default setting, "gpu_trans" is True. but training preprocessor uses "gpu_trans=True" and eval preprocessor uses "gpu_trans=False".
So data' range is different from training phrase and eval
By the way, model.forward has no operation to normalize data range for training phrase, so is is a big bug