Imagenet performance reproduction problem with swav pretrain weights in torch hub
seominseok0429 opened this issue · 5 comments
I download imagenet data through Kaggle and loaded the swav pretrained weights using the torch.hub.load method.
After that, for evaluation, we tried to evaluate the imagenet val set as a swav model. But the performance is 10% Is it possible to receive data from Kaggle?(https://www.kaggle.com/c/imagenet-object-localization-challenge)
Hi, this is because the last fully connected layer is randomly initialized. You can find the weights of the fc
layer here: https://dl.fbaipublicfiles.com/deepcluster/swav_800ep_eval_linear.pth.tar
Does the weights mentioned in the table here include the projection head trained weights or are they randomly initialized like the last fc layer? If they are random then where can I find the trained weights for them. Thank you @mathildecaron31
Hi @Sreyas-108
The weights from the table do include the projection head trained weights :)
Hi, this is because the last fully connected layer is randomly initialized. You can find the weights of the
fc
layer here: https://dl.fbaipublicfiles.com/deepcluster/swav_800ep_eval_linear.pth.tar
Thanks @mathildecaron31 , I'm wondering if only swav_800ep_eval_linear.pth.tar
is provided, where we can find other eval_linear.pth.tar
like 400/200ep? Do we need to train them ourselves?