search

yfeng95 / DECA

DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)
Other
2.11k stars 421 forks source link

Prepare dataset #71

Open Ned09 opened 2 years ago

Ned09 commented 2 years ago

Can you please give me more explanation about preparing data for training the model from scratch? I want to use VGGFace2 for the first step. Do I need to generate landmarks for every image and save the landmarks as a text file or npy file? and what about masks? I really appreciate it if you give me some clue

I am trying to do this step: b. Prepare label FAN to predict 68 2D landmark face_segmentation to get skin mask

littlePrince126 commented 2 years ago

How do you get the five faces of every subject? (vggface2_val_list_max_normal_100_ring_5_1_serial.npy') I could get landmarks or skin mask. Author choose five normoal faces with every identity. It is more important!

Ned09 commented 2 years ago

@littlePrince126 Can you please help me on generating facial masks? I couldn't install https://github.com/YuvalNirkin/face_segmentation

when I run the repository I get this error image

Ned09 commented 2 years ago

@littlePrince126 I want to try with some simple data just to run the code so I didnt get the five faces from every object yet. we can work on it together if you want.

littlePrince126 commented 2 years ago

@Ned09 It seems that you don't set the variables in a right way. You can have a try by using the python script.

Ned09 commented 2 years ago

@littlePrince126 Do you mean without installing this repository and just by running the python script in the "face-segmentation/interfaces/python/face-seg.py" , I can generate the segmentation images?

littlePrince126 commented 2 years ago

@Ned09 Yes, because you should compile caffe and opencv if you want to install this repo. Anyway, you need a caffe environment at first.

Shelomith commented 2 years ago

@littlePrince126 Hi, what's your GPU used when runing face-segmentation? when I use caffe-gpu env with docker,

F1103 05:56:53.555362 430 pooling_layer.cu:212] Check failed: error == cudaSuccess (8 vs. 0) invalid device function

I got this error, It may because the difference of GPU computation ability between authur's and mine.

What's your situation?

littlePrince126 commented 2 years ago

@Shelomith Telsa P100

HITKJ commented 2 years ago

identity. It is more important!

Have you got the file(vggface2_val_list_max_normal_100_ring_5_1_serial.npy)? I would really appreciate it , if you share it with me.

littlePrince126 commented 2 years ago

@1180800817 I generate it by myself. You can generate it with dataset（VggFace2，BUPT-Face，voxceleb2 ）. voxceleb2 is a video dataset, you should choose good quality videos first, then get the images from videos.

lhyfst commented 2 years ago

@littlePrince126 Can you reproduce the reported result on NoW using your generated data? Additionally, could you please share vggface2_val_list_max_normal_100_ring_5_1_serial.npy with me? Even a demo is helpful! I just want to know the explicit format of this file.

littlePrince126 commented 2 years ago

@lhyfst I trained the model without any pretrained model. Finally, I get median1.217mm mean1.517mm std 1.249mm with NOW validation set. (DECA median:1.18, mean:1.46mm,std:1.25mm)

Shelomith commented 2 years ago

I've test DECA pretrained model in NoW dataset, result is median:1.15, mean:1.44mm,std:1.24mm... but in DECA paper they report median:1.09, mean:1.38mm,std:1.18mm @littlePrince126 朋友，方便加个微信讨论吗？

littlePrince126 commented 2 years ago

@Shelomith Because your results is based on validation set. (median:1.09, mean:1.38mm,std:1.18mm )This result is based on test set. But I only get results(meadian:1.1778,Mean:1.4636,std:1.2529) with DECA model.

littlePrince126 commented 2 years ago

meadian:1.1778,Mean:1.4636,std:1.2529 This result is the same as papr(DECA)

super3kl commented 2 years ago

I've test DECA pretrained model in NoW dataset, result is median:1.15, mean:1.44mm,std:1.24mm... but in DECA paper they report median:1.09, mean:1.38mm,std:1.18mm @littlePrince126 朋友，方便加个微信讨论吗？ hello 你好 最近也在跑这个代码 方便加个微信讨论吗？或者邮箱？

Shelomith commented 2 years ago

@super3kl wx: shelomith1001

Victcode commented 2 years ago

@littlePrince126 Hi,can you share the method of choosing five normoal faces?Thank you!

Eric3778 commented 2 years ago

@littlePrince126 你好，我最近在跑这个代码实验，我想请教一下你是怎么进行数据处理的，可以的话能否分享一下数据处理的代码，非常感谢！

chen990627 commented 1 year ago

@lhyfst I trained the model without any pretrained model. Finally, I get median1.217mm mean1.517mm std 1.249mm with NOW validation set. (DECA median:1.18, mean:1.46mm,std:1.25mm)

您好，方便给个联系方式吗？想请教一下怎么训练的，有偿。

prokaryote-hgy commented 1 year ago

@chen990627 @pfeducode @Eric3778 你们复现出来了吗？方便微信交流一下吗？

prokaryote-hgy commented 1 year ago

choose good quality videos

Hi, how do you choose good quality videos? @littlePrince126

prokaryote-hgy commented 1 year ago

@YalanHe 你好，查找不到该微信账号，是否账号有误

nainsheng commented 1 year ago

你能帮我制作面膜吗？我无法安装 https://github.com/YuvalNirkin/face_segmentation

当我运行存储库时，出现此错误 image

May I ask how you resolved this issue and ultimately achieved training?

mumucc1 commented 6 months ago

How do you get the five faces of every subject? (vggface2_val_list_max_normal_100_ring_5_1_serial.npy') I could get landmarks or skin mask. Author choose five normoal faces with every identity. It is more important!

Hi！Can you reproduce the model training？