Skip to content
This repository has been archived by the owner on Jan 31, 2022. It is now read-only.

Latest commit

 

History

History
27 lines (19 loc) · 890 Bytes

README.md

File metadata and controls

27 lines (19 loc) · 890 Bytes

HINet

Half Instance Normalization Network for Image Restoration, based on https://github.com/megvii-model/HINet.

Dependencies

  • NumPy
  • PyTorch, preferably with CUDA. Note that torchvision and torchaudio are not required and hence can be omitted from the command.
  • VapourSynth
  • (Optional) TensorRT. Note that uff and PyCUDA are not required and hence can be skipped from the guide.
  • (Optional) torch2trt

Installation

pip install --upgrade vshinet
python -m vshinet

Usage

from vshinet import HINet

ret = HINet(clip)

See __init__.py for the description of the parameters.