UNICON-Noisy-Label
UNICON-Noisy-Label copied to clipboard
Official Implementation of the CVPR 2022 paper "UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning"
```python # in val() function: if acc > best_acc[k-1]: best_acc[k-1] = acc print('| Saving Best Net%d ...'%k) save_point = os.path.join(model_save_loc, '%s_net%d.pth.tar'%(args.id,k)) torch.save(net.state_dict(), save_point) ``` In each epoch, you load the...
``` Traceback (most recent call last): File "/home/lxy/Documents/UNICON-Noisy-Label/Train_webvision.py", line 343, in warmup(epoch,net1,optimizer1,warmup_trainloader) File "/home/lxy/Documents/UNICON-Noisy-Label/Train_webvision.py", line 182, in warmup loss = CEloss(outputs, labels) File "/opt/miniconda3/envs/pt2/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args,...
Thank you very much for your interesting work. I have a question about [this line](https://github.com/nazmul-karim170/UNICON-Noisy-Label/blob/647b3ee9f4e71faf1794cf47a974c9772d43dfbe/Train_cifar.py#L291): in noise learning, is it a normal way to use a clean eval-set to calculate...