Skip to content

clibdev/colorization

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Differences between original repository and fork:

  • Compatibility with PyTorch >=2.4. (🔥)
  • Original pretrained models and converted ONNX models from GitHub releases page. (🔥)
  • Model conversion to ONNX format using the export.py file. (🔥)
  • Installation with updated requirements.txt file.
  • Additional command line options for specifying model weights in the demo_release.py file.

Installation

pip install -r requirements.txt

Pretrained models

Name Model Size (MB) Link SHA-256
Colorization ECCV 16 123.0
123.0
PyTorch, ONNX 9b330a0bae53f4ded77b1e23defbf78beaa09c10ebc4c4999e8e4f4a160b93f9
b4a4cecae9e84e776d665e85774815b0bb43de382813b02fb13144f8fd5d6c83
Colorization SIGGRAPH 17 130.5
129.9
PyTorch, ONNX df00044c0a4d7c3edcecf6f75437ce346a66e7a42612d9b968e1a7e17dbc6f66
7db825910668ee321327d2e6b446e57cbc9c066e196e8be0e152bf76e1206eb7

Inference

python demo_release.py --eccv16_weights colorization-eccv-16.pth --siggraph17_weights colorization-siggraph-17.pth -i imgs/ansel_adams3.jpg

Export to ONNX format

pip install onnx
python export.py --weights colorization-eccv-16.pth --net_type eccv16
python export.py --weights colorization-siggraph-17.pth --net_type siggraph17

About

Colorization in Pytorch and ONNX

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages