tothebeginning / gcp-colorization Goto Github PK

When I test the images for testcase_in_the_wild and run the code python predict_imagenet_label.py testcase_in_the_wild --model beit_large_patch16_512 --pretrained.
It could generate this issue which is Unknown model (beit_large_patch16_512) for test testcase_in_the_wild

The paper do not mention ImageNet

Please provide Controllable Diverse Colorization codes(eg. background color, object, saturation), thanks

Which file do you put the pre-trained model in?

Thank you for your excellent work. I was greatly inspired after reading your paper and wanted to reproduce your experimental results, but I encountered a problem during training. The ImageNet dataset from the official website:

https://image-net.org/download-images.php

There are a lot of versions to choose from. Which ImageNet subset did you choose for your network?
Since I don't know enough about the ImageNet dataset, this may be a stupid question, thanks, and looking forward to your answer.

/home/fzh/.conda/envs/video/lib/python3.8/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: /home/fzh/.conda/envs/video/lib/python3.8/site-packages/torchvision/image.so: undefined symbol: _ZN5torch3jit17parseSchemaOrNameERKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE warn(f"Failed to load image Python extension: {e}") Cannot import deform_conv_ext. You can ignore this message if you are using torchvision >= 0.9.0. Otherwise you may need to check whether the DCN has been successfully installed. Adding attention layer in D at resolution 64 Adding attention layer in E at resolution 64 Adding attention layer in G at resolution 64 Traceback (most recent call last): File "main.py", line 32, in <module> main() File "main.py", line 28, in main sol.run() File "/home/fzh/workspace/GCP-Colorization/solvers/base_solver.py", line 29, in run self.test() File "/home/fzh/workspace/GCP-Colorization/solvers/refcolor_solver.py", line 67, in test self.test_dl = data.get_loader(cfg=self.cfg, ds=self.cfg.DATA.NAME) File "/home/fzh/workspace/GCP-Colorization/data/__init__.py", line 21, in get_loader dataset = dataset_cls(cfg) File "/home/fzh/workspace/GCP-Colorization/data/imagenet_inference.py", line 99, in __init__ assert img_name in label_map AssertionError

Thank you for your work and your patience in answering my earlier issue.
I noticed that the training part of the GCP-colorization doesn't seem to be released in the current released code. When I tried to reproduce your results, I encountered some difficulties due to the lack of some implementation details. Do you have any plans to open-source the code of the training part? If so, when will you release it?
Thanks for your work again and looking forward to your reply.