Deep3DFaceRecon_pytorch
Deep3DFaceRecon_pytorch copied to clipboard
sicxu
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.
Hi `Deep3DFaceRecon_pytorch` creator and contributors, In this branch I added a script `detect_landmarks.py` to batch detect landmarks of custom images using MTCNN. For further informations please read the messages added...
When I run the test script: # get reconstruction results of example images python test.py --name= --epoch=20 --img_folder=./datasets/examples I faced this issue, Can you give any solution, please?
2022-04-26 10:53:11.630608: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0 WARNING:tensorflow:Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them. Traceback (most recent call last): File "/data/ywj/Anaconda3/envs/torch/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 3343, in run_code...
When images only contain face part, there is no point to crop again. Maybe add option to export cropped face image for later texture projection.
Running the following problems: May I ask how to solve it, the pain? Traceback (most recent call last): File "test.py", line 75, in main(0, opt,opt.img_folder) File "test.py", line 64, in...
It takes 50ms to use 3D mesh without 2D effect, which is very good. It can be driven by real-time 3D animation. However, I don't know how to turn onnx,...
Hi， when I run “python test.py --name= --epoch=20 --img_folder=./datasets/examples”, I meet a trouble. the problem is list below: Traceback (most recent call last): File "/root/anaconda3/envs/deep3d_pytorch/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1515, in _run_ninja_build env=env)...
Hello How are you? Thanks for contributing to this project. Did u try to deploy this method on a mobile device? What problems are there in deploying on a mobile...
All res is with img size 224. If I use original image size mesh. How can I inverse the transform mat
When I run the test script: I faced this problem. Can you help me with handling it, please?