PRNet-PyTorch
PRNet-PyTorch copied to clipboard
reshow
The training and evaluation code for PRNet (《Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network》)
Hi, I ran torchrun.py using the argument _**python torchrun.py -train=False -test=True -pd=data/images/AFLW2000 --loadModelPath=savedmodel/temp_best_model/2019-11-18-12-34-19/best.pth**_ and get this error: UnboundLocalError: local variable 'mean_errors' referenced before assignment Can you help me figure this...
很感谢您的代码分享。我在进行训练的时候，总是出现卡在from .collection import imread_collection_wrapper 这里，一直没解决掉这个问题，请问这是怎么回事呢？谢谢
Thank you for sharing your project. But I have some trouble in running the training code. > Traceback (most recent call last): > File "torchrun.py", line 325, in > net_manager.train()...
Hi @reshow , Thanks for sharing the reimplementation of PRNet. I used your pre-trained model to test the model by running torchrun.py and got the attached 3D Mesh displayed via...
Hi, thanks for the fantanstic work, I want to ask about the **Illumination model** used in the **data.py**, what is every parameter mean in the color_Para and illum_Para? 
I had this error when I set --isVisualize=1，how do I solve this problem？
Hi @reshow , Thank you for the source codes you released. I'm just wondering how did yo evaluate PRNet on AFLW2000 dataset? Coz the PRNet's outputs have 43K vertices while...
Hi @reshow . Thank you for sharing the pytoch version of PRNet. I had a question regarding calculating NME. using PRNet we would have 43k vertices in our predicted 3D...
Hey, thanks for your code. I just want to ask how to show the results of the alignment like the example that you show? Because i use the "--is visualize=...
I had this error when I set --isVisualize=true, No such file or directory: 'tmp/light/test.obj', what is test.obj? how can I get it?
