You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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 ?
The text was updated successfully, but these errors were encountered:
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.
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 ?
The text was updated successfully, but these errors were encountered: