Sixiang Chen
Sixiang Chen
Sorry, these two weights were originally saved on another machine, and now the account of that machine has been logged out. You can use our code to retrain. Or because...
Hi, thanks for your attention. According to our paper, we use the 256 x 256 crop size to train our model, which differs from the default 128 x 128. The...
According to my experience, adjusting both to 256 (the crop size for training is the same as the size for slice inference) should have better results.
Looking forward to your results. We also have a diffusion-based paper on adverse weather restoration accepted by ECCV'24. The paper and code will be available soon. If you are interested,...
Hi, we utilize PyTorch_lightning for training, where checkpoints are saved with other hyperparameters in *.ckpt file. So, you need to first take out the checkpoint of the model from the...
Hello, I seem to have not found my training logs. If possible, could you send me your training logs? I'd be happy to help review them and check for any...