PyTorch-Pyramid-Feature-Attention-Network-for-Saliency-Detection

PyTorch-Pyramid-Feature-Attention-Network-for-Saliency-Detection copied to clipboard

Hi,Sairajk. Your work is helpful to me. However, the following error pops up during training the model.Thus, the saved model does not achieve the desired effect.  Based on...

Tristesse-stk

TypeError: unsupported operand type(s) for %: 'int' and 'NoneType'

4

Hi, I got the problem, I can begin trainging the code. But while run epoch=2, it show this problem and stop to train. File "train.py", line 212, in trainer.train() File...

cculin18

I have made some changes to your scripts so it can run on Colab. And I have fix some bugs, changed the name of the workers to threads, and made...

ParthPatel-ES

torch.save(mod_chkpt, self.model_path + 'weights/best-model_epoch-{:03}_mae-{:.4f}_loss-{:.4f}.pth'.format(epoch, best_test_mae, te_avg_loss)) while self.model_path = args.base_save_path + '/alph-{}_wbce_w0-{}_w1-{}'.format(str(self.alpha_sal), str(self.wbce_w0), str(self.wbce_w1)) you are supposed to plus a '/' in self.model_path = args.base_save_path + '/alph-{}_wbce_w0-{}_w1-{}/'.

niuniuBUAA

Bumps [torch](https://github.com/pytorch/pytorch) from 1.1.0 to 2.2.0. Release notes Sourced from torch's releases. PyTorch 2.2: FlashAttention-v2, AOTInductor PyTorch 2.2 Release Notes Highlights Backwards Incompatible Changes Deprecations New Features Improvements Bug fixes...

dependabot[bot]