tomguluson92/ PRNet_PyTorch

Python

C++

3d-reconstruction

face-alignment

View on GitHub

Need help with PRNet_PyTorch?

Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

tomguluson92

164 Stars

40 Forks

28 Commits

7 Opened issues

Description

Training & Inference Code of PRNet in PyTorch 1.1.0

Services available

Need anything else?

Contributors list

tomguluson92 tomguluson92

# 66,964

Keras

C++

face-re...

Tensorf...

28 commits

Readme

PRNet PyTorch 1.1.0

Name: PRNet_PyTorch
Brand: PRNet_PyTorch
SKU: //tomguluson92/PRNet_PyTorch
Rating: 2.16 (164 reviews)

This is an unofficial pytorch implementation of PRNet since there is not a complete generating and training code of

300WLP

dataset.

Author: Samuel Ko, mjanddy.

Update Log

@date: 2019.11.13

@notice: An important bug has been fixed by mj in loading uv map. The original

uv_map.jpg

is flipped, so *.npy is used here to redress this problem. Thanks to mjanddy!

@date: 2019.11.14

@notice: Inference Stage Uploaded, pretrain model available in

results/latest.pth

. Thanks to mjanddy!

Noitce

Since replacing the default

PIL.Imgae

cv2.imread

in image reader, you need do a little revise on your

tensorboard

package in

your_python_path/site-packages/torch/utils/tensorboard/summary.py

What you should do is add

tensor = tensor[:, :, ::-1]

before

image = Image.fromarray(tensor)

in function

make_image(...)

. ```shell ... def makeimage(tensor, rescale=1, rois=None): """Convert an numpy representation image to Image protobuf""" from PIL import Image height, width, channel = tensor.shape scaledheight = int(height * rescale) scaled_width = int(width * rescale)

tensor = tensor[:, :, ::-1]
image = Image.fromarray(tensor)
...

... ```

① Pre-Requirements

Before we start generat uv position map and train it. The first step is generate BFM.mat according to Basel Face Model. For simplicity, The corresponding

BFM.mat

has been provided here.

After download it successfully, you need to move

BFM.mat

utils/

Besides, the essential python packages were listed in

requirements.txt

② Generate uvposmap

YadiraF/face3d have provide scripts for generating uvposmap, here i wrap it for Batch processing.

You can use

utils/generate_posmap_300WLP.py

as:

python3 generate_posmap_300WLP.py --input_dir ./dataset/300WLP/IBUG/ --save_dir ./300WLP_IBUG/

Then

300WLP_IBUG

dataset is the proper structure for 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 from

300WLP

, I provide processed original--uv_posmap pair of IBUG here.

③ Training

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

python3 train.py --train_dir ./300WLP_IBUG

You can use tensorboard to visualize the intermediate output in

localhost:6006

shell
tensorboard --logdir=absolute_path_of_prnet_runs/

The following image is used to judge the effectiveness of PRNet to unknown data.

(Original, UVMAPgt, UVMAPpredicted)

④ Inference

You can use following instruction to do your prnet inference. The detail about parameters you can find in

inference.py

shell
python3 inference.py -i input_dir(default is TestImages) -o output_dir(default is TestImages/results) --model model_path(default is results/latest.pth) --gpu 0 (-1 denotes cpu)

Citation

If you use this code, please consider citing:

@inProceedings{feng2018prn,
  title     = {Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network},
  author    = {Yao Feng and Fan Wu and Xiaohu Shao and Yanfeng Wang and Xi Zhou},
  booktitle = {ECCV},
  year      = {2018}
}