A C++ implementation of inference part of the paper: Gharbi, Michaël, et al. "Deep bilateral learning for real-time image enhancement." ACM Transactions on Graphics (TOG) 36.4 (2017): 118.
- create binary model dir from tensorflow ( pretrained models )
python script/get_tfmodel_value.py
- build shared library and c++ executable
make -B
- test a picture
python script/run.py A_PICTURE(like xxx.jpg) your_binary_model_dir
- optimize the c++ code
- create an Android NDK version
- use OpenCL to accelerate
- retrain the hdrnet+ model, change it to a post process tensorflow model