resize mode question

[cnnAndBn]

hi：
@ycxioooong in the config file of imagenet, as follows:

one way is use cv2.resize an anther way is the implementation in pillow library ,I wonder the difference between them and any gap in the classification accuracy ?

[ycxioooong]

Hi @dadada101 sorry for my late reply. The only difference is that we use PIL as the backend in RandomResizedCrop. It will not affect the performance.

[ycxioooong]

Hi @dadada101, one correction: the performance would be affected by resize backend. Using OpenCV as resize backend will decrease the accuracy by 0.1% ~ 0.3% in our experience (R50, ImageNet) than using PIL.