Very minimalistic wrapper for EnlightenGAN inference.
It uses carefully converted pretrained weights (+ baked in preprocessing) from the original repo and only requires onnxruntime
as inference engine.
pip install git+https://github.com/arsenyinfo/EnlightenGAN-inference
from enlighten_inference import EnlightenOnnxModel
import cv2
img = cv2.imread('/path/to/image.jpg')
model = EnlightenOnnxModel()
processed = model.predict(img)
- src1
- dst1
- src2
- dst2
- src3
- dst3
- src4
- dst4
- src5
- dst5
- src6
- dst6
- src7
- dst7
- src8
- dst8
- src9
- dst9
- src10
- dst10
- src11
- dst11
- src12
- dst12
- src13
- dst13
- src14
- dst14
- src15
- dst15