leegang79

Results 5 comments of leegang79

Is video cropping directly scaled or recognizing cropped facial regions?

My understanding: You need to crop out the face area with tools like Capcut, as sqaure(height/width ratio 1:1). If your already got square video, but with different FPS and w/h...

File "/home/anuj/GeneFacePlusPlus/./modules/radnerfs/encoders/gridencoder/grid.py", line 62, in forward _backend.grid_encode_forward(inputs, embeddings, offsets, outputs, B, D, C, L, S, H, dy_dx, gridtype, align_corners, interpolation) RuntimeError: inputs must be a CUDA tensor

I encountered the same error, found that CUDA version to high, try down-grade to CUDA11.7, now can infer successfully. 1. export CUDA_HOME=/usr/local/cuda-11.7 2. down-grade pytorch to compatiable with CUDA11.7 ---...

Audio2Motion Training Code Release

check another repo of the author, just updated https://github.com/yerfor/Real3DPortrait [2024.07.02] We release the training code of the whole system, including audio-to-motion model... The Pre-trained audio-to-motion model of these two repo...

the Training Code of Audio2Motion

check another repo of the author, just updated https://github.com/yerfor/Real3DPortrait [2024.07.02] We release the training code of the whole system, including audio-to-motion model... The Pre-trained audio-to-motion model of these two repo...

Audio2Motion and Post-Net.

同问，求发布