NAFNet

NAFNet copied to clipboard

Using NAFNET in kaggle denoising competition

2

Hi, Good day. I plan to use NAFNET in the kaggle denoising document competition here: https://www.kaggle.com/competitions/denoising-shabby-pages Would it be fine for me to do so? Thank you.

kwcckw

数据集格式转换

1

亲爱的作者，我在使用png格式的别的数据集进行测试时遇到了困难，自己尝试转化png为lmdb时会导致数据集变大很多，请问能否告诉我将测试集图像的png格式转化为lmdb格式的代码，万分感谢

wangxiaoxiao6

train.py: error: unrecognized arguments: --local-rank=0

6

Encounter this error when trying to train GoPro datasets: `python -m torch.distributed.launch --nproc_per_node=1 --master_port=4321 train.py -opt options/train/GoPro/NAFNet-width32.yml --launcher pytorch` I searched the train.py, there is no `--local-rank=0`. How to fix?

davidvct

Instead of training separate models, can we have just one model to do all the denoise, deblur and super-resolution?

davidvct

Strange output from debluring

12

I have strange and random output using debluring model.

asias96

你好啊，我想引用提出PSNRLoss的论文，非常感谢！

wyyaa123

win_size error

2

ValueError: win_size exceeds image extent. Either ensure that your images are at least 7x7; or pass win_size explicitly in the function call, with an odd value less than or equal...

moyanouo

这适用于摄像头实时进行预测吗

Jeff1933

Not enough memory available to process your request

5

Paste log: Traceback (most recent call last): File "/root/.pyenv/versions/3.9.12/lib/python3.9/site-packages/cog/server/worker.py", line 217, in _predict result = predict(**payload) File "predict.py", line 79, in predict single_image_inference(model, inp, str(out_path)) File "predict.py", line 101, in...

clasking2

![Uploading IMG_0848.JPG…]()

kameraci