hi，你好，请问能否提供用于真实世界图片的测试代码？

The work looks well and I'd like to try it. But I can't run the code with the provided pretrained weights due to the memory constraint of my gpu. Could you please include the pretrained weights of vit_base_patch32_384 and vit_small_patch32_384? Thanks!

I load the provided pretrained weight to test ,but the effect seems not very good.

When I ran the testing scripts with the pretrained models, I find I can only use 256*256 input image (or resize/crop my input image to 256*256). May I ask is there any chance for me to test any size image on its original demension?

thanks for your great work! I want to know how to generate L1-L4 luminance prior. Could you provide some code?

The approcha to specify the test image path is missing in the read file

Welcome update to OpenMMLab 2.0

I am Vansin, the technical operator of OpenMMLab. In September of last year, we announced the release of OpenMMLab 2.0 at the World Artificial Intelligence Conference in Shanghai. We invite you to upgrade your algorithm library to OpenMMLab 2.0 using MMEngine, which can be used for both research and commercial purposes. If you have any questions, please feel free to join us on the OpenMMLab Discord at https://discord.gg/amFNsyUBvm or add me on WeChat (van-sin) and I will invite you to the OpenMMLab WeChat group.

Here are the OpenMMLab 2.0 repos branches:

Attention: please create a new virtual environment for OpenMMLab 2.0.

Could you please provide the clean train data list in segm/data/coco.py's L85, since there may exist something different with the one generated on the whole training set of ImageNet.

Your code looks very interesting and I'd like to test it locally. But I can't connect to the link to download the pretrained weights. Others who have tried to download the pretrained weights report that the link requires the user to download and install an unknown application, which raises security and privacy concerns. Could you please include the pretrained weights on your github page or put the weights on a more user-friendly, easily accessible public site?

Hi, When I was trying download the pretrained model on Baidu Pan, it requires me to provide the extraction code. Could you please also include the extraction in README?
Thank you!

Missing declaration and description for "ptu" and "dist" in metrics.py. Hopefully it will be explained!

FileNotFoundError: [Errno 2] No such file or directory: 'E:/samsung/datasets/imagenetval/val5000/val_fullfilenames.pickle'
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 6067)

Firstly, thank you for your great work!

I am running test.py, but there is an option "--add_mask", which is "default=True".

Then I checked the dataset, it seems load an extra file named "mask_prior.pickle" in coco.py. I also found it in single_test.py.

I wonder what it does & can you provide this file?

Hi @shuchenweng :
Could you please provide mask_prior.pickle?
Now i want to test my own images for colorization but the test.py and single_test.py can't run successfully due to the lack of some pre-trained weights.
It will be better if you can provide one easy to run Colab demo for testing colorization.