search

ashawkey / RAD-NeRF

Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition
MIT License
862 stars 151 forks source link

How to generate .pth file? #49

Open xionghaoo opened 1 year ago

xionghaoo commented 1 year ago

./data/ ├──.mp4 # original video ├──ori_imgs # original images from video │ ├──0.jpg │ ├──0.lms # 2D landmarks │ ├──... ├──gt_imgs # ground truth images (static background) │ ├──0.jpg │ ├──... ├──parsing # semantic segmentation │ ├──0.png │ ├──... ├──torso_imgs # inpainted torso images │ ├──0.png │ ├──... ├──aud.wav # original audio ├──aud_eo.npy # audio features (wav2vec) ├──aud.npy # audio features (deepspeech) ├──bc.jpg # default background ├──track_params.pt # raw head tracking results ├──transforms_train.json # head poses (train split) ├──transforms_val.json # head poses (test split)

not found obama_eo.pth and obama.json file after training

sunmingyang666 commented 1 year ago

me too

davidspicy commented 1 year ago

should be in trial_filename/checkpoints/ ex: trial_obama/checkpoints/

weihaigang commented 1 year ago

应该在 trial_filename/checkpoints/ 例如：trial_obama/checkpoints/

I couldn't find it. Can you provide a screenshot

Marvinified commented 1 year ago

I also couldn't find it using the notebook file explorer at first, but it was there when I did ls /notebooks/RAD-NeRF/trial_gary/checkpoints in the notebook.

xionghaoo commented 1 year ago

can try scripts/train_obama_eo.sh