tothebeginning / gcp-colorization Goto Github PK
View Code? Open in Web Editor NEWOfficial code for ICCV 2021 paper "Towards Vivid and Diverse Image Colorization with Generative Color Prior".
License: Apache License 2.0
Official code for ICCV 2021 paper "Towards Vivid and Diverse Image Colorization with Generative Color Prior".
License: Apache License 2.0
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:
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.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.