the result of net is something wrong

[xiaoyingzhengrui]

thanks for the shared codes. i test the pretrained models using test2K dataset but the output is wrong just like the pic blow, i can't find the reason, do you know what happened?

[icandle]

It's so weird. I will check the code, pretrained model and requirement later. In my environment, it works well. Could you provide the detail env information like torch version and cuda version？

[icandle]

I guess it is an environmental problem, but I have no idea about where this specific problem comes. I try on my personal device with torch 2.1.1, cuda12.1, and basicsr 1.4.2, where the image can be properly restored. Hope it can help you.

[xiaoyingzhengrui]

I guess it is an environmental problem, but I have no idea about where this specific problem comes. I try on my personal device with torch 2.1.1, cuda12.1, and basicsr 1.4.2, where the image can be properly restored. Hope it can help you.

ohh，i'll try it again, maybe something wrong in my computer and i'll feedback to you

[xiaoyingzhengrui]

i check my environment, but still get the same wrong result,my environment is like this: `Package Version

---

absl-py 2.1.0 accelerate 0.21.0 addict 2.4.0 aenum 3.1.15 aiofiles 23.2.1 aiohttp 3.9.3 aiosignal 1.3.1 aliyun-python-sdk-core 2.15.0 aliyun-python-sdk-kms 2.16.2 altair 5.2.0 annotated-types 0.6.0 antlr4-python3-runtime 4.9.3 anyio 3.7.1 async-timeout 4.0.3 attrs 23.2.0 av 12.0.0 basicsr 1.4.2 beautifulsoup4 4.12.3 blendmodes 2022 blinker 1.7.0 boltons 23.1.1 certifi 2024.2.2 cffi 1.16.0 chardet 5.2.0 charset-normalizer 3.3.2 clean-fid 0.1.35 click 8.1.7 clip 1.0 colorama 0.4.6 coloredlogs 15.0.1 colorlog 6.8.2 contourpy 1.2.0 crcmod 1.7 cryptography 42.0.5 cssselect2 0.7.0 cycler 0.12.1 Cython 3.0.10 deprecation 2.1.0 depth_anything 2024.1.22.0 docutils 0.21rc1 easydict 1.13 einops 0.4.1 embreex 2.17.7.post4 exceptiongroup 1.2.0 facexlib 0.3.0 fastapi 0.94.0 ffmpy 0.3.2 filelock 3.13.1 filterpy 1.4.5 flatbuffers 23.5.26 fonttools 4.49.0 frozenlist 1.4.1 fsspec 2024.2.0 ftfy 6.1.3 future 1.0.0 fvcore 0.1.5.post20221221 gdown 5.1.0 gfpgan 1.3.8 gitdb 4.0.11 GitPython 3.1.32 gradio 3.41.2 gradio_client 0.5.0 greenlet 3.0.3 grpcio 1.62.0 h11 0.12.0 handrefinerportable 2024.2.12.0 httpcore 0.15.0 httpx 0.24.1 huggingface-hub 0.20.3 humanfriendly 10.0 idna 3.6 imageio 2.34.0 importlib-metadata 7.0.1 importlib-resources 6.1.1 inflection 0.5.1 iopath 0.1.9 jax 0.4.24 Jinja2 3.1.3 jmespath 0.10.0 joblib 1.3.2 jsonmerge 1.8.0 jsonschema 4.21.1 jsonschema-specifications 2023.12.1 kiwisolver 1.4.5 kornia 0.6.7 lark 1.1.2 lazy_loader 0.3 lightning-utilities 0.10.1 llvmlite 0.42.0 lmdb 1.4.1 lpips 0.1.4 lxml 5.1.0 mapbox-earcut 1.0.1 Markdown 3.5.2 markdown-it-py 3.0.0 MarkupSafe 2.1.5 matplotlib 3.8.3 mdurl 0.1.2 mediapipe 0.10.10 ml-dtypes 0.3.2 mmcv-full 1.7.2 mmedit 0.16.1 model-index 0.1.11 mpmath 1.3.0 multidict 6.0.5 networkx 3.2.1 nltk 3.8.1 numba 0.59.0 numpy 1.23.5 nvidia-cublas-cu12 12.1.3.1 nvidia-cuda-cupti-cu12 12.1.105 nvidia-cuda-nvrtc-cu12 12.1.105 nvidia-cuda-runtime-cu12 12.1.105 nvidia-cudnn-cu12 8.9.2.26 nvidia-cufft-cu12 11.0.2.54 nvidia-curand-cu12 10.3.2.106 nvidia-cusolver-cu12 11.4.5.107 nvidia-cusparse-cu12 12.1.0.106 nvidia-nccl-cu12 2.19.3 nvidia-nvjitlink-cu12 12.3.101 nvidia-nvtx-cu12 12.1.105 omegaconf 2.2.3 onnxruntime 1.17.1 open-clip-torch 2.20.0 opencv-contrib-python 4.9.0.80 opencv-python 4.9.0.80 opendatalab 0.0.10 openmim 0.3.9 openxlab 0.0.37 opt-einsum 3.3.0 ordered-set 4.1.0 orjson 3.9.14 oss2 2.17.0 packaging 23.2 pandas 2.2.0 piexif 1.1.3 Pillow 9.5.0 pip 23.3.1 platformdirs 4.2.0 portalocker 2.8.2 protobuf 3.20.3 psutil 5.9.5 py-cpuinfo 9.0.0 pycollada 0.8 pycparser 2.21 pycryptodome 3.20.0 pydantic 1.10.14 pydantic_core 2.16.2 pydub 0.25.1 PyFlow 3.0.0 Pygments 2.17.2 pyparsing 3.1.1 PySocks 1.7.1 python-dateutil 2.8.2 python-multipart 0.0.9 pytorch-lightning 1.9.4 pytz 2023.4 PyWavelets 1.5.0 PyYAML 6.0.1 QtPy 2.4.1 realesrgan 0.3.0 referencing 0.33.0 regex 2023.12.25 reportlab 4.1.0 requests 2.28.2 resize-right 0.0.2 rich 13.4.2 rpds-py 0.18.0 Rtree 1.2.0 safetensors 0.3.1 scikit-image 0.21.0 scikit-learn 1.4.2 scipy 1.12.0 seaborn 0.13.2 semantic-version 2.10.0 sentencepiece 0.2.0 setuptools 60.2.0 shapely 2.0.3 six 1.16.0 smmap 5.0.1 sniffio 1.3.0 sounddevice 0.4.6 soupsieve 2.5 SQLAlchemy 2.0.29 starlette 0.26.1 svg.path 6.3 svglib 1.5.1 sympy 1.12 tabulate 0.9.0 tb-nightly 2.17.0a20240222 tensorboard 2.16.2 tensorboard-data-server 0.7.2 termcolor 2.4.0 thop 0.1.1.post2209072238 threadpoolctl 3.4.0 tifffile 2024.2.12 timm 0.9.2 tinycss2 1.2.1 tokenizers 0.13.3 tomesd 0.1.3 tomli 2.0.1 toolz 0.12.1 torch 2.1.1+cu121 torchaudio 2.1.1+cu121 torchdiffeq 0.2.3 torchmetrics 1.3.1 torchsde 0.2.5 torchvision 0.16.1+cu121 tqdm 4.65.2 trampoline 0.1.2 transformers 4.30.2 trimesh 4.2.0 triton 2.1.0 typing_extensions 4.9.0 tzdata 2024.1 ultralytics 8.1.29 urllib3 1.26.18 uvicorn 0.27.1 vhacdx 0.0.6 wcwidth 0.2.13 webencodings 0.5.1 websockets 11.0.3 Werkzeug 3.0.1 wheel 0.41.2 xatlas 0.0.9 xformers 0.0.24 xxhash 3.4.1 yacs 0.1.8 yapf 0.40.2 yarl 1.9.4 zipp 3.17.0`

it seems like the number of result image's channel or bit cause this problem, but i have no idea where is different between us, i run all the test scripts you provided and just change the data path

[icandle]

So it only happens to partial images? Do this phenomenon happen with other ratios？Currently, I have no idea about why it happens. I will check the uploaded datasets and try to reproduce the problem on other device. Since I am on vocation, I may feedback to you later. Thanks.

[caojiehui]

So it only happens to partial images? Do this phenomenon happen with other ratios？Currently, I have no idea about why it happens. I will check the uploaded datasets and try to reproduce the problem on other device. Since I am on vocation, I may feedback to you later. Thanks.

Hello, authors. I encountered the same problem when testing my own samples.

[xiaoyingzhengrui]

So it only happens to partial images? Do this phenomenon happen with other ratios？Currently, I have no idea about why it happens. I will check the uploaded datasets and try to reproduce the problem on other device. Since I am on vocation, I may feedback to you later. Thanks.

I tested 4k/2k dataset, all results ran into the same trouble

[icandle]

Sorry, I can still not reproduce this problem. May you try it on colab or other opening platforms? I have tried with several machines and only observed PSNR fluctuating.

[jlzhou1]

Thanks for the code. I should point out that I'm having the same problem, can you switch computers to find out why?

[jlzhou1]

Thanks for the code. I should point out that I'm having the same problem, can you switch computers to find out why?

[jlzhou1]

Sorry, I can still not reproduce this problem. May you try it on colab or other opening platforms? I have tried with several machines and only observed PSNR fluctuating.

Hi, have you solved it? The same problem is plaguing me. If you've fix it, please contact me ，thanks！

[jlzhou1]

Sorry, I can still not reproduce this problem. May you try it on colab or other opening platforms? I have tried with several machines and only observed PSNR fluctuating.

Hi, have you solved it? The same problem is plaguing me. If you've fix it, please contact me，thanks！

[xiaoyingzhengrui]

Sorry, I can still not reproduce this problem. May you try it on colab or other opening platforms? I have tried with several machines and only observed PSNR fluctuating.

Hi, have you solved it? The same problem is plaguing me. If you've fix it, please contact me，thanks！

still not

[lz1054864168]

Sorry, I can still not reproduce this problem. May you try it on colab or other opening platforms? I have tried with several machines and only observed PSNR fluctuating.

Hi, have you solved it? The same problem is plaguing me. If you've fix it, please contact me，thanks！

Hi, I had the same problem and fixed it. I think you should modify the '.yml' file, where the 'pretrain_network_g:' must be modified to the corresponding '.pth' instead of the default.

[jlzhou1]

Sorry, I can still not reproduce this problem. May you try it on colab or other opening platforms? I have tried with several machines and only observed PSNR fluctuating.

Hi, have you solved it? The same problem is plaguing me. If you've fix it, please contact me，thanks！

Hi, I had the same problem and fixed it. I think you should modify the '.yml' file, where the 'pretrain_network_g:' must be modified to the corresponding '.pth' instead of the default.

Thank you very much. it is useful~