swz30/MIRNetv2

How many EPOCH has been trained to reach the reported metric in the paper?

bianhao123 opened this issue · 4 comments

bianhao123 commented

Thank you for your excellent work!
In the Low-light image enhancement, the reported metrics of Lol dataset are 24.74(PSNR) and 0.851(SSIM). I want to know that how many EPOCH the model trained to reach this metrics

bianhao123 commented

Can you show your train log in Lol dataset?

bianhao123 commented

您好，你训练代码跑起来了吗？可以帮我看下吗？我训练不起来？单卡单机！ 报错如下： ModuleNotFoundError: No module named 'basicsr' 这个basicsr是项目文件夹，导入为沙会报错阿？

ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 28610) of binary: /home/xtzg/anaconda3/envs/pytorch1.1 我的设置： train.sh中设置为： python -m torch.distributed.run --nproc_per_node=1 --master_port=4321 basicsr/train.py -opt $CONFIG --launcher pytorch yaml配置文件中也修改shuffle为false # data loader use_shuffle: false # true num_worker_per_gpu: 0 # 8 batch_size_per_gpu: 1 # 8

需要安装basicsr，见https://github.com/swz30/MIRNetv2/blob/main/INSTALL.md

Lz-2019317 commented

谢谢！可以了～您对代码改进了吗？您觉得从哪方面可以进行修改？想做人脸图像的去噪，可以和给点宝贵的建议吗？不胜感激～

yujiaolong1120 commented

在测试DND数据集结果时，需要将生成的结果上传官网，请问时直接上传生成的50个mat文件吗，为什么我上传以后显示错误？