xuguodong comments

Repositories
Issues
Comments

Results 4 comments of


                                            xuguodong

Contrastive Prediction

Hi, thanks for running this repo. The batch from train_loader is 64x4x3x32x32. The dimension '4' means one normal data + three transformed data. After x.view(), its shape is (64x4)x3x32x32. Suppose...

Contrastive Prediction

没有使用torchvision.datasets.CIFAR100，而是对dataset进行了修改，参见cifar.py

Hyperparameter discrepancy between paper(s) and code

Thanks for your attention to our work. The results in paper come from the hyper-parameters in this repo, i.e., λ3 = 10.0, λ4 = 2.7. The numbers in arxiv version...

meets problem when train ssp head

The training hyper-parameters (e.g. batchsize, epoch, LR) of CIFAR and ImageNet are different. For ImageNet, we use the hyper-parameters in [pytorch/example](https://github.com/pytorch/examples/tree/master/imagenet). Besides the hyper-parameters, the reason that ssp loss does...