piddnad / ddcolor Goto Github PK

View Code? Open in Web Editor NEW

956.0 956.0 108.0 13.33 MB

[ICCV 2023] DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders

License: Apache License 2.0

Python 99.87% Shell 0.13%

computer-vision image-colorization pytorch

ddcolor's People

Contributors

Stargazers

Watchers

Forkers

jackzhousz cv-ip hanziying myeldib web-logs2 screw-44 julienmlr md-rifatkhan billlin66 delldu ruxes-edu ai-tools chenxwh camenduru davidsche arunbanswal bailixuance iwkoo techthiyanes mirasbrisas lyhiving zcfrank1st luozhenyu336 andruxa-smirnov betalita hadryan hotliu venhow sorokinvld banderas7070 bartek-tos f901107 anthonyyuan slyturn shenliehuozhi jags111 yvrjsharma saulocatharino mechanicss nielsrogge dhee2211 st3alth kornel203 przemyslawbryzek doubleflick suryatmodulus lihuibng mr-nobody-dey teenaxta li9989 haxine aligator77 samirandas1311 skwarson96 garrysson-star choco-zz keyman9848 kuzitony chaozheng liuxing9848 zoxxxx forestp 973398769 alibekkazakhstan pla888 riasl xiaoqingwang pfsprog deymos7777 jinlei652 annalinlin gessyoo songliu80 omnipotentai changzy00 nonomal ericwonghua liuxing9848 bigpot kate-the-programmer moluyouwo leebufan watchet samling-jackyjyo yuyangup starceees derek-zl thinkerchina liuxing9848 alagong lijingle-coder bluegel321 alexey-pronkin enjoyteach asherbond charminglittedeveloper xia-zx shimomurakei orichisonic anmatngu

ddcolor's Issues

ModuleNotFoundError: No module named 'torch'

How to fine-tune existing model?

Basicsr issue

I am trying to train the model on custom dataset,but I meet this problem.
My version is: CUDA==11.7，torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2, basicsr==1.4.2
What version of torch and basicsr should I install?
Thank you!

How to train tiny model

Thank you to share tiny model.

When I want to train this model, can you share train method?

ERROR: Failed building wheel for torch-scatter when installing modelscope

Problem description

I tried to install the package as README says. But I keep running into this error.

Problem script

pip install "modelscope[cv]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Error that encounter

  Building wheel for torch-scatter (setup.py) ... error
  error: subprocess-exited-with-error
  
  × python setup.py bdist_wheel did not run successfully.
  │ exit code: 1
  ╰─> [56 lines of output]
      running bdist_wheel
      running build
      running build_py
      creating build
      creating build/lib.linux-x86_64-cpython-38
      creating build/lib.linux-x86_64-cpython-38/torch_scatter
      copying torch_scatter/__init__.py -> build/lib.linux-x86_64-cpython-38/torch_scatter
      copying torch_scatter/scatter.py -> build/lib.linux-x86_64-cpython-38/torch_scatter
      copying torch_scatter/segment_coo.py -> build/lib.linux-x86_64-cpython-38/torch_scatter
      copying torch_scatter/segment_csr.py -> build/lib.linux-x86_64-cpython-38/torch_scatter
      copying torch_scatter/utils.py -> build/lib.linux-x86_64-cpython-38/torch_scatter
      copying torch_scatter/placeholder.py -> build/lib.linux-x86_64-cpython-38/torch_scatter
      copying torch_scatter/testing.py -> build/lib.linux-x86_64-cpython-38/torch_scatter
      creating build/lib.linux-x86_64-cpython-38/torch_scatter/composite
      copying torch_scatter/composite/__init__.py -> build/lib.linux-x86_64-cpython-38/torch_scatter/composite
      copying torch_scatter/composite/softmax.py -> build/lib.linux-x86_64-cpython-38/torch_scatter/composite
      copying torch_scatter/composite/logsumexp.py -> build/lib.linux-x86_64-cpython-38/torch_scatter/composite
      copying torch_scatter/composite/std.py -> build/lib.linux-x86_64-cpython-38/torch_scatter/composite
      running egg_info
      writing torch_scatter.egg-info/PKG-INFO
      writing dependency_links to torch_scatter.egg-info/dependency_links.txt
      writing requirements to torch_scatter.egg-info/requires.txt
      writing top-level names to torch_scatter.egg-info/top_level.txt
      reading manifest file 'torch_scatter.egg-info/SOURCES.txt'
      reading manifest template 'MANIFEST.in'
      warning: no previously-included files matching '*' found under directory 'test'
      adding license file 'LICENSE'
      writing manifest file 'torch_scatter.egg-info/SOURCES.txt'
      running build_ext
      building 'torch_scatter._scatter_cpu' extension
      creating build/temp.linux-x86_64-cpython-38
      creating build/temp.linux-x86_64-cpython-38/csrc
      creating build/temp.linux-x86_64-cpython-38/csrc/cpu
      gcc -pthread -B /opt/anaconda3/envs/ddcolor/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_PYTHON -Icsrc -I/opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include -I/opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/TH -I/opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/THC -I/opt/anaconda3/envs/ddcolor/include/python3.8 -c csrc/cpu/scatter_cpu.cpp -o build/temp.linux-x86_64-cpython-38/csrc/cpu/scatter_cpu.o -O3 -Wno-sign-compare -DAT_PARALLEL_OPENMP -fopenmp -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=_scatter_cpu -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
      cc1plus: warning: command-line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
      gcc -pthread -B /opt/anaconda3/envs/ddcolor/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_PYTHON -Icsrc -I/opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include -I/opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/TH -I/opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/THC -I/opt/anaconda3/envs/ddcolor/include/python3.8 -c csrc/scatter.cpp -o build/temp.linux-x86_64-cpython-38/csrc/scatter.o -O3 -Wno-sign-compare -DAT_PARALLEL_OPENMP -fopenmp -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=_scatter_cpu -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
      cc1plus: warning: command-line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
      csrc/scatter.cpp: In static member function ‘static torch::autograd::variable_list ScatterMean::forward(torch::autograd::AutogradContext*, torch::autograd::Variable, torch::autograd::Variable, int64_t, c10::optional<at::Tensor>, c10::optional<long int>)’:
      csrc/scatter.cpp:141:15: error: no matching function for call to ‘at::Tensor::div_(at::Tensor&, const char [6])’
        141 |       out.div_(count, "floor");
            |       ~~~~~~~~^~~~~~~~~~~~~~~~
      In file included from /opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3,
                       from /opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                       from /opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                       from /opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                       from /opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/torch/script.h:3,
                       from csrc/scatter.cpp:5:
      /opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:676:12: note: candidate: ‘at::Tensor& at::Tensor::div_(const at::Tensor&) const’
        676 |   Tensor & div_(const Tensor & other) const;
            |            ^~~~
      /opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:676:12: note:   candidate expects 1 argument, 2 provided
      /opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:678:12: note: candidate: ‘at::Tensor& at::Tensor::div_(c10::Scalar) const’
        678 |   Tensor & div_(Scalar other) const;
            |            ^~~~
      /opt/anaconda3/envs/ddcolor/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:678:12: note:   candidate expects 1 argument, 2 provided
      error: command '/usr/bin/gcc' failed with exit code 1
      [end of output]
  
  note: This error originates from a subprocess, and is likely not a problem with pip.
  ERROR: Failed building wheel for torch-scatter
  Running setup.py clean for torch-scatter
  Building wheel for utils (setup.py) ... done
  Created wheel for utils: filename=utils-1.0.2-py2.py3-none-any.whl size=13905 sha256=559e4b50d2eb4c91263f8880f054e721eeda25f962e864fd27dc60db83cb2d0a
  Stored in directory: /home/c4fun/.cache/pip/wheels/45/68/b5/83c1bab8f5f597186752fcbafaf03e9e2f41a5d03604811e02
  Building wheel for aliyun-python-sdk-core (setup.py) ... done
  Created wheel for aliyun-python-sdk-core: filename=aliyun_python_sdk_core-2.14.0-py3-none-any.whl size=535290 sha256=c7097f4124d623742976ee1ebd7723709c49728d8991e456ea1f056394d453bb
  Stored in directory: /home/c4fun/.cache/pip/wheels/89/2c/1d/580922a0f499547b9ae03217fb31dbbde6dbe784c36d511ad4
  Building wheel for crcmod (setup.py) ... done
  Created wheel for crcmod: filename=crcmod-1.7-cp38-cp38-linux_x86_64.whl size=30969 sha256=746468d6d24dffc164325eb8a403b578285f9a253bef9fa6f6a44d29851a6958
  Stored in directory: /home/c4fun/.cache/pip/wheels/ee/bf/82/ac509f3b383e310a168c1da020cbc62d98c03a6c7c74babc63
  Building wheel for iopath (setup.py) ... done
  Created wheel for iopath: filename=iopath-0.1.10-py3-none-any.whl size=31530 sha256=d6643c6f3bdbd547e0680c114e408980c771c67a23e63ee8e60afc96508537f4
  Stored in directory: /home/c4fun/.cache/pip/wheels/c8/ed/fb/2923ab44724b97e6b8b2cdc98222d5a08fdd65137a787305a0
  Building wheel for future (setup.py) ... done
  Created wheel for future: filename=future-0.18.3-py3-none-any.whl size=492024 sha256=a906ee7e8be5d9f9ccff1a96d34d76b152d1254d8e31320036ac3d5f00fd75cf
  Stored in directory: /home/c4fun/.cache/pip/wheels/70/bd/fa/9f18baf78773526a3f6c9d46f27e09ffd7084a2e2f92825b3b
  Building wheel for fire (setup.py) ... done
  Created wheel for fire: filename=fire-0.5.0-py2.py3-none-any.whl size=116934 sha256=cb19389f940afd29757278573db0852ba5c07dd99244ebf223c4c798c68231aa
  Stored in directory: /home/c4fun/.cache/pip/wheels/82/71/1b/c4c3a0d1c95fe96e69a55dacb72c5fc657b38985f15faa98fd
Successfully built fairscale ffmpeg moviepy trimesh chumpy easydict easyrobust fvcore lap ml-collections antlr4-python3-runtime oss2 utils aliyun-python-sdk-core crcmod iopath future fire
Failed to build torch-scatter
ERROR: Could not build wheels for torch-scatter, which is required to install pyproject.toml-based projects

File not found

Blogger hello, would like to ask a question, when I run the train.py script, encountered FileNotFoundError: [Errno 2] No such file or directory: 'data_list/imagenet.txt' this problem. I have imagenet.txt in the data_list file, but it keeps saying it can't find it. And this imagenet.txt is generated when you run data_list/get_meta_file.py (I'm afraid I got this wrong)

是否能实现Docker部署

warnings

Hi there! I really like your colorization model. I'm using it on old images and I think it works better than the other currently available options, except sometimes red color is too strong. When I run it as python script I get a couple of warnings I want to ask if there are any ways to avoid these warnings thanks!

2024-03-15 17:43:21,771 - modelscope - INFO - PyTorch version 2.2.1+rocm5.7 Found.
2024-03-15 17:43:21,797 - modelscope - INFO - Loading ast index from /home/rubing/.cache/modelscope/ast_indexer
2024-03-15 17:43:21,824 - modelscope - INFO - Loading done! Current index file version is 1.13.1, with md5 bf5a0cac5e5265c888d1b6453711fc56 and a total number of 972 components indexed
2024-03-15 17:43:25,009 - modelscope - WARNING - Model revision not specified, use revision: v1.02
2024-03-15 17:43:25,743 - modelscope - INFO - initiate model from /home/rubing/.cache/modelscope/hub/damo/cv_ddcolor_image-colorization
2024-03-15 17:43:25,745 - modelscope - INFO - initiate model from location /home/rubing/.cache/modelscope/hub/damo/cv_ddcolor_image-colorization.
2024-03-15 17:43:25,748 - modelscope - INFO - initialize model from /home/rubing/.cache/modelscope/hub/damo/cv_ddcolor_image-colorization
2024-03-15 17:43:29,373 - modelscope - INFO - Loading DDColor model from /home/rubing/.cache/modelscope/hub/damo/cv_ddcolor_image-colorization/pytorch_model.pt, with param key: [params].
2024-03-15 17:43:29,658 - modelscope - INFO - load model done.
2024-03-15 17:43:29,737 - modelscope - WARNING - No preprocessor field found in cfg.
2024-03-15 17:43:29,779 - modelscope - WARNING - No val key and type key found in preprocessor domain of configuration.json file.
2024-03-15 17:43:29,781 - modelscope - WARNING - Cannot find available config to build preprocessor at mode inference, current config: {'model_dir': '/home/rubing/.cache/modelscope/hub/damo/cv_ddcolor_image-colorization'}. trying to build by task and model information.
2024-03-15 17:43:29,782 - modelscope - WARNING - No preprocessor key ('ddcolor', 'image-colorization') found in PREPROCESSOR_MAP, skip building preprocessor.
2024-03-15 17:43:29,785 - modelscope - INFO - load model done

question about training

How to train by google colab?

about evaluation

When testing on the validation set of COCO Stuff, ADE20K, and ImageNet, did you first resize the input image to (512,512), and then linearly interpolate the coloring results to the original resolution?

Amanul

LICENSE

training errors

I get the following errors when i try to run the training script:

/usr/local/lib/python3.9/site-packages/torch/distributed/launch.py:183: FutureWarning: The module torch.distributed.launch is deprecated
and will be removed in future. Use torchrun.
Note that --use-env is set by default in torchrun.
If your script expects --local-rank argument to be set, please
change it to read from os.environ['LOCAL_RANK'] instead. See
https://pytorch.org/docs/stable/distributed.html#launch-utility for
further instructions

warnings.warn(
[2024-03-27 23:53:06,101] torch.distributed.run: [WARNING]
[2024-03-27 23:53:06,101] torch.distributed.run: [WARNING] *****
[2024-03-27 23:53:06,101] torch.distributed.run: [WARNING] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
[2024-03-27 23:53:06,101] torch.distributed.run: [WARNING] *
usage: train.py [-h] -opt OPT [--launcher {none,pytorch,slurm}] [--auto_resume] [--debug]
[--local_rank LOCAL_RANK] [--force_yml FORCE_YML [FORCE_YML ...]]
usage: train.py [-h] -opt OPT [--launcher {none,pytorch,slurm}] [--auto_resume] [--debug]
[--local_rank LOCAL_RANK] [--force_yml FORCE_YML [FORCE_YML ...]]
train.py: error: unrecognized arguments: --local-rank=2
train.py: error: unrecognized arguments: --local-rank=0
usage: train.py [-h] -opt OPT [--launcher {none,pytorch,slurm}] [--auto_resume] [--debug]
[--local_rank LOCAL_RANK] [--force_yml FORCE_YML [FORCE_YML ...]]
train.py: error: unrecognized arguments: --local-rank=3
usage: train.py [-h] -opt OPT [--launcher {none,pytorch,slurm}] [--auto_resume] [--debug]
[--local_rank LOCAL_RANK] [--force_yml FORCE_YML [FORCE_YML ...]]
train.py: error: unrecognized arguments: --local-rank=1
[2024-03-27 23:53:31,246] torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: 2) local_rank: 0 (pid: 56905) of binary: /usr/local/bin/python3
Traceback (most recent call last):
File "/usr/local/lib/python3.9/runpy.py", line 197, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/local/lib/python3.9/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/usr/local/lib/python3.9/site-packages/torch/distributed/launch.py", line 198, in
main()
File "/usr/local/lib/python3.9/site-packages/torch/distributed/launch.py", line 194, in main
launch(args)
File "/usr/local/lib/python3.9/site-packages/torch/distributed/launch.py", line 179, in launch
run(args)
File "/usr/local/lib/python3.9/site-packages/torch/distributed/run.py", line 803, in run
elastic_launch(
File "/usr/local/lib/python3.9/site-packages/torch/distributed/launcher/api.py", line 135, in call
return launch_agent(self._config, self._entrypoint, list(args))
File "/usr/local/lib/python3.9/site-packages/torch/distributed/launcher/api.py", line 268, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:

basicsr/train.py FAILED

Failures:
[1]:
time : 2024-03-27_23:53:31
host : 7b4bdae11b42
rank : 1 (local_rank: 1)
exitcode : 2 (pid: 56906)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
[2]:
time : 2024-03-27_23:53:31
host : 7b4bdae11b42
rank : 2 (local_rank: 2)
exitcode : 2 (pid: 56907)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
[3]:
time : 2024-03-27_23:53:31
host : 7b4bdae11b42
rank : 3 (local_rank: 3)
exitcode : 2 (pid: 56908)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html

Root Cause (first observed failure):
[0]:
time : 2024-03-27_23:53:31
host : 7b4bdae11b42
rank : 0 (local_rank: 0)
exitcode : 2 (pid: 56905)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html

Why can't obtain the FID results reported in the paper using pretrained weights？

The FID obtained from testing ImageNet using the pretrained weights provided by you is approximately 17.96.Is there any mistake?

For a given gray image with high contrast, how to process it to pull it into training data distribution for better result

Hi, I find that, for some gray image with very high contrast, processing it by decreasing contrast can lead to better results. Perhaps the reason is that it aligns more closely with the distribution of the training data.
I wonder if there is any general algorithm or code that can process any given grayscale image, taking into account statistical properties such as color temperature and hue? Thanks a lot!

How to train on my own dataset?

Sorry to bother. I'm trying to train DDColor on my own dataset. Is there any training scripts? By the way, how to prepare and organize my dataset?

train own datasets

Excuse me, can I train this on my own datasets?

shenmind.com —— Another Website to Try DDColor

DDColor has impressive performance to colorize images. We offer a demo page for trying DDColor, supporting both Chinese and English.

DDColor

train

Your work is excellent, and I am very interested in it. I'm a beginner and would like to know how to run this code in a Windows environment. When I enter the command, it tells me that basicSR does not exist. Thank you for informing me.

error on windows 11

When i run bash scripts/train.sh get error
how can i solve it?
thanks

self._store = TCPStore( # type: ignore[call-arg] RuntimeError: unmatched '}' in format string

Small pretrained models?

Any plan to release small pretrained models?

DDColor ONNX

Thanks for your great work, results on images even better than deoldify.

I've converted the models to onnx for more simple installation...

Extending Model Training

Hi,

Thanks for your great work! I trained a model for 400,000 iterations on one dataset, and now I want to continue training for an additional 400,000 iterations using the net_g_400000.pth model. Do I just need to change the total_iter value from 400,000 to 800,000?

Thanks!

color embeddings are initialized to zero

Mentioned in the paper：”These color embeddings are initialized to zero during the training phase and used as color queries in the first CDB” , but I can't find the code in the code that initializes to zero in question. Is the initialization to zero mentioned in the paper really zero? Looking forward to your answers.

Incredible work, unfortunately there is a color instability in the colorization video.

Hello congratulations for this work, it's really incredible, is there a way to fix the color instability in the video colorization for objects that move such as cars and people walking? Are there any modifications to be made? Where to train the model with specific modifications? Thank you for your reply

about reproduce

The configuration you provided is 4 cards, with each card having a batch size of 4. Have you tried training the model with two cards and each card having a batch size of 8? How would this affect the model's performance?
How do you choose a model? Do you directly select the model that has trained 400000 steps as the selected model?
May I ask if the training code you provided is DDColor-large?

Minimal GPU memory?

Hello
What is minimum GPU memory value required to run the training?

Code release date

The paper is great, I liked it a lot. Could you tell an approximate date for code realease so that I can start experimenting too? Thanks.

Reducing flickering artifacts (temporal inconsistency)

Coloring video will cause flickering

When I turn a black-and-white video into a colored one, the video flickers. Sometimes, there is a big difference in color between adjacent frames, which causes the video to flicker. Is there any way to make the video more stable?

local install error, pls help

At first I use python=3.8 which as told from https://github.com/piddnad/DDColor, but got error like below

ERROR: Ignored the following yanked versions: 0.20.0.dev0, 0.20.0rc2, 0.20.0rc3, 0.20.0rc6, 0.20.0rc7
ERROR: Ignored the following versions that require a different python version: 0.22.0 Requires-Python >=3.9; 0.22.0rc1 Requires-Python >=3.9; 0.23.0 Requires-Python >=3.10; 0.23.0rc0 Requires-Python >=3.10; 0.23.0rc2 Requires-Python >=3.10; 0.23.1 Requires-Python >=3.10; 0.23.2 Requires-Python >=3.10; 0.23.2rc1 Requires-Python >=3.10; 1.11.0 Requires-Python <3.13,>=3.9; 1.11.0rc1 Requires-Python <3.13,>=3.9; 1.11.0rc2 Requires-Python <3.13,>=3.9; 1.11.1 Requires-Python <3.13,>=3.9; 1.11.2 Requires-Python <3.13,>=3.9; 1.11.3 Requires-Python <3.13,>=3.9; 1.11.4 Requires-Python >=3.9; 1.12.0 Requires-Python >=3.9; 1.12.0rc1 Requires-Python >=3.9; 1.12.0rc2 Requires-Python >=3.9; 1.13.0 Requires-Python >=3.9; 1.13.0rc1 Requires-Python >=3.9; 1.25.0 Requires-Python >=3.9; 1.25.0rc1 Requires-Python >=3.9; 1.25.1 Requires-Python >=3.9; 1.25.2 Requires-Python >=3.9; 1.26.0 Requires-Python <3.13,>=3.9; 1.26.0b1 Requires-Python <3.13,>=3.9; 1.26.0rc1 Requires-Python <3.13,>=3.9; 1.26.1 Requires-Python <3.13,>=3.9; 1.26.2 Requires-Python >=3.9; 1.26.3 Requires-Python >=3.9; 1.26.4 Requires-Python >=3.9; 2.0.0b1 Requires-Python >=3.9; 2.0.0rc1 Requires-Python >=3.9
ERROR: Could not find a version that satisfies the requirement scikit-image==0.22.0 (from versions: 0.7.2, 0.8.0, 0.8.1, 0.8.2, 0.9.0, 0.9.1, 0.9.3, 0.10.0, 0.10.1, 0.11.2, 0.11.3, 0.12.0, 0.12.1, 0.12.2, 0.12.3, 0.13.0, 0.13.1, 0.14.0, 0.14.1, 0.14.2, 0.14.3, 0.14.5, 0.15.0, 0.16.2, 0.17.1, 0.17.2, 0.18.0, 0.18.1, 0.18.2, 0.18.3, 0.19.0rc0, 0.19.0, 0.19.1, 0.19.2, 0.19.3, 0.20.0rc4, 0.20.0rc5, 0.20.0rc8, 0.20.0, 0.21.0rc0, 0.21.0rc1, 0.21.0)
ERROR: No matching distribution found for scikit-image==0.22.0

I realized maybe the python version is low, so i changed into 'python3.10' beacuase the erros msg said Requires-Python >=3.10 but still error like below

Building wheels for collected packages: dlib
  Building wheel for dlib (pyproject.toml) ... error
  error: subprocess-exited-with-error

  × Building wheel for dlib (pyproject.toml) did not run successfully.
  │ exit code: 1
  ╰─> [73 lines of output]
      running bdist_wheel
      running build
      running build_ext
      <string>:125: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
      Building extension for Python 3.10.14 | packaged by Anaconda, Inc. | (main, Mar 21 2024, 16:20:14) [MSC v.1916 64 bit (AMD64)]
      Invoking CMake setup: 'cmake C:\Users\shadow\AppData\Local\Temp\pip-install-373trf7q\dlib_669ba91aa7214a9eb95805ba13046fd7\tools\python -DCMAKE_LIBRARY_OUTPUT_DIRECTORY=C:\Users\shadow\AppData\Local\Temp\pip-install-373trf7q\dlib_669ba91aa7214a9eb95805ba13046fd7\build\lib.win-amd64-cpython-310 -DPYTHON_EXECUTABLE=D:\soft\miniconda3\envs\python310\python.exe -DCMAKE_LIBRARY_OUTPUT_DIRECTORY_RELEASE=C:\Users\shadow\AppData\Local\Temp\pip-install-373trf7q\dlib_669ba91aa7214a9eb95805ba13046fd7\build\lib.win-amd64-cpython-310 -A x64'
      -- Building for: NMake Makefiles
      CMake Error at CMakeLists.txt:5 (message):



        !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!


        You must use Visual Studio to build a python extension on windows.  If you
        are getting this error it means you have not installed Visual C++.  Note
        that there are many flavors of Visual Studio, like Visual Studio for C#
        development.  You need to install Visual Studio for C++.


        !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!




      -- Configuring incomplete, errors occurred!
      Traceback (most recent call last):
        File "D:\soft\miniconda3\envs\python310\lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 353, in <module>
          main()
        File "D:\soft\miniconda3\envs\python310\lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 335, in main
          json_out['return_val'] = hook(**hook_input['kwargs'])
        File "D:\soft\miniconda3\envs\python310\lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 251, in build_wheel
          return _build_backend().build_wheel(wheel_directory, config_settings,
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\build_meta.py", line 410, in build_wheel
          return self._build_with_temp_dir(
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\build_meta.py", line 395, in _build_with_temp_dir
          self.run_setup()
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\build_meta.py", line 311, in run_setup
          exec(code, locals())
        File "<string>", line 218, in <module>
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\__init__.py", line 104, in setup
          return distutils.core.setup(**attrs)
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\_distutils\core.py", line 184, in setup
          return run_commands(dist)
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\_distutils\core.py", line 200, in run_commands
          dist.run_commands()
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\_distutils\dist.py", line 969, in run_commands
          self.run_command(cmd)
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\dist.py", line 967, in run_command
          super().run_command(command)
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\_distutils\dist.py", line 988, in run_command
          cmd_obj.run()
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\wheel\bdist_wheel.py", line 368, in run
          self.run_command("build")
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\_distutils\cmd.py", line 316, in run_command
          self.distribution.run_command(command)
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\dist.py", line 967, in run_command
          super().run_command(command)
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\_distutils\dist.py", line 988, in run_command
          cmd_obj.run()
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\_distutils\command\build.py", line 132, in run
          self.run_command(cmd_name)
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\_distutils\cmd.py", line 316, in run_command
          self.distribution.run_command(command)
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\dist.py", line 967, in run_command
          super().run_command(command)
        File "C:\Users\shadow\AppData\Local\Temp\pip-build-env-b5s6o_5j\overlay\Lib\site-packages\setuptools\_distutils\dist.py", line 988, in run_command
          cmd_obj.run()
        File "<string>", line 130, in run
        File "<string>", line 167, in build_extension
        File "D:\soft\miniconda3\envs\python310\lib\subprocess.py", line 369, in check_call
          raise CalledProcessError(retcode, cmd)
      subprocess.CalledProcessError: Command '['cmake', 'C:\\Users\\shadow\\AppData\\Local\\Temp\\pip-install-373trf7q\\dlib_669ba91aa7214a9eb95805ba13046fd7\\tools\\python', '-DCMAKE_LIBRARY_OUTPUT_DIRECTORY=C:\\Users\\shadow\\AppData\\Local\\Temp\\pip-install-373trf7q\\dlib_669ba91aa7214a9eb95805ba13046fd7\\build\\lib.win-amd64-cpython-310', '-DPYTHON_EXECUTABLE=D:\\soft\\miniconda3\\envs\\python310\\python.exe', '-DCMAKE_LIBRARY_OUTPUT_DIRECTORY_RELEASE=C:\\Users\\shadow\\AppData\\Local\\Temp\\pip-install-373trf7q\\dlib_669ba91aa7214a9eb95805ba13046fd7\\build\\lib.win-amd64-cpython-310', '-A', 'x64']' returned non-zero exit status 1.
      [end of output]

  note: This error originates from a subprocess, and is likely not a problem with pip.
  ERROR: Failed building wheel for dlib
Failed to build dlib
ERROR: Could not build wheels for dlib, which is required to install pyproject.toml-based projects

So, i don't know how to fix it, somewhere wrong? Any help will be appreciated.