Repository files navigation

Before we start generat uv position map and train it. The first step is generate BFM.mat according toBasel Face Model.For simplicity, The correspondingBFM.mat has been providedhere.

After download it successfully, you need to moveBFM.mat toDS_generator/BFM.

YadiraF/face3d have provide scripts for generating uv_pos_map, here i wrap it forBatch processing.

You can useDS_generator/generate_posmap_300WLP.py as:

cd DS_generatorpython3 generate_posmap_300WLP.pyThen`300WLP_IBUG` dataset is the proper structurefor training PRNet:

- 300WLP_IBUG - 0/  - IBUG_image_xxx.npy  - original.jpg (original RGB)  - uv_posmap.jpg (corresponding UV Position Map) - 1/ - **...** - 100/

Except from download from300WLP,I provide processedoriginal--uv_posmap pair of IBUGhere.

After finish the above two step, you can train your own PRNet as:

run_training.cmd

You can use tensorboard to visualize the intermediate output inlocalhost:6006:

run_tensorboard.cmd