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
Thanks for your great work. Can you share the code for training imagenet? I use the code (https://github.com/rwightman/pytorch-image-models) and train ResNeXt-50+PSConv with the same setting in your paper (SGD, 120 epochs, half cosine function shaped schedule, cross entropy, standard augmentation, weight decay 1e-4). The top1 performance is only 77.57%, which is lower than the results reported in your paper (79.622%).
The text was updated successfully, but these errors were encountered:
Thanks for your great work. Can you share the code for training imagenet? I use the code (https://github.com/rwightman/pytorch-image-models) and train ResNeXt-50+PSConv with the same setting in your paper (SGD, 120 epochs, half cosine function shaped schedule, cross entropy, standard augmentation, weight decay 1e-4). The top1 performance is only 77.57%, which is lower than the results reported in your paper (79.622%).
The text was updated successfully, but these errors were encountered: