weiwenping-cn
commented
1 year ago process_data.sh > python data_gen/nerf/binarizer.py --config=egs/datasets/videos/$1/lm3d_radnerf.yaml
Refer to the MAY example video to configure your own configuration file in this directory. Normally, you only need to change the video name
tailangjun
How can this be troubleshooted? We have spent more than a week trying to resolve issues with this program. Please let us know.
The MAY example video works correctly, using custom video content mp4 the model cannot complete training...
120 of 121 done params saved [INFO] ===== finished face tracking ===== [INFO] ===== extract background image from data/processed/videos/MTK/ori_imgs ===== 100%|████████████████████████████████████████████████████████████████████████████| 301/301 [01:31<00:00, 3.30it/s][INFO] ===== extracted background image ===== [INFO] ===== extract head images for data/processed/videos/MTK ===== 100%|██████████████████████████████████████████████████████████████████████████| 6003/6003 [01:05<00:00, 92.07it/s][INFO] ===== extracted head images ===== [INFO] ===== extract torso and gt images for data/processed/videos/MTK ===== 100%|██████████████████████████████████████████████████████████████████████████| 6003/6003 [02:29<00:00, 40.20it/s][INFO] ===== extracted torso and gt images ===== [INFO] ===== save transforms ===== [INFO] ===== finished saving transforms ===== Loading the Wav2Vec2 Processor... Loading the HuBERT Model... 2023-08-26 00:17:47.047964: I tensorflow/core/util/port.cc:110] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable
set_hparams()
File "/home/m/GeneFace/utils/commons/hparams.py", line 46, in set_hparams
assert os.path.exists(args.config)
AssertionError
TF_ENABLE_ONEDNN_OPTS=0. 2023-08-26 00:17:47.075708: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2023-08-26 00:17:47.508668: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Hubert extracted at data/processed/videos/MTK/aud_hubert.npy Mel and F0 extracted at data/processed/videos/MTK/aud_mel_f0.npy loading the model from deep_3drecon/checkpoints/facerecon/epoch_20.pth loading video ... extracting 2D facial landmarks ...: 100%|██████████████████████████████████████| 5056/5056 [04:32<00:00, 18.54it/s]start extracting 3DMM...: 0%| | 0/158 [00:00<?, ?it/s]create rasterizer on device cuda:0 start extracting 3DMM...: 100%|██████████████████████████████████████████████████| 158/158 [00:40<00:00, 3.88it/s]3DMM coeff extracted at data/processed/videos/MTK/vid_coeff.npy | Unknow hparams: [] Traceback (most recent call last): File "/home/m/GeneFace/data_gen/nerf/binarizer.py", line 14, in