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
{{ message }}
This repository was archived by the owner on Sep 8, 2021. It is now read-only.
I ran through the models and was able to reproduce the top-1/top-5 scores for all the models but the largest SWSL one (to within typical variations for specific PyTorch version, PIL, etc).
For SWSL ResNeXt-101 32x16d I'm getting 83.338 top-1 and 96.852 top-5.
For comparison, on my setup, the SWSL 8d is 84.294, 4d is 83.234 top-1.
Edit: Tested on two machines, both Pytorch 1.2, Pillow 6.1
I ran through the models and was able to reproduce the top-1/top-5 scores for all the models but the largest SWSL one (to within typical variations for specific PyTorch version, PIL, etc).
For SWSL ResNeXt-101 32x16d I'm getting 83.338 top-1 and 96.852 top-5.
For comparison, on my setup, the SWSL 8d is 84.294, 4d is 83.234 top-1.
Edit: Tested on two machines, both Pytorch 1.2, Pillow 6.1