How do you test once preprocessed?

[G-force78]

Namespace(path='/content/SyncTalk/data/runwayandroid', O=True, test=True, test_train=True, data_range=[0, -1], workspace='model/trial_may', seed=0, iters=200000, lr=0.01, lr_net=0.001, ckpt='latest', num_rays=65536, cuda_ray=True, max_steps=16, num_steps=16, upsample_steps=0, update_extra_interval=16, max_ray_batch=4096, warmup_step=10000, amb_aud_loss=1, amb_eye_loss=1, unc_loss=1, lambda_amb=0.1, pyramid_loss=0, fp16=True, bg_img='', fbg=False, exp_eye=True, fix_eye=-1, smooth_eye=False, bs_area='upper', torso_shrink=0.8, color_space='srgb', preload=0, bound=1, scale=4, offset=[0, 0, 0], dt_gamma=0.00390625, min_near=0.05, density_thresh=10, density_thresh_torso=0.01, patch_size=1, init_lips=False, finetune_lips=False, smooth_lips=False, torso=False, head_ckpt='', gui=False, W=450, H=450, radius=3.35, fovy=21.24, max_spp=1, att=2, aud='/content/SyncTalk/04Label-2.wav', emb=False, portrait=True, ind_dim=4, ind_num=20000, ind_dim_torso=8, amb_dim=2, part=False, part2=False, train_camera=False, smooth_path=False, smooth_path_window=7, asr=False, asr_wav='', asr_play=False, asr_model='ave', asr_save_feats=False, fps=50, l=10, m=50, r=10)

Setting up [LPIPS] perceptual loss: trunk [alex], v[0.1], spatial [off]
/usr/local/lib/python3.10/dist-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
warnings.warn(
/usr/local/lib/python3.10/dist-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=AlexNet_Weights.IMAGENET1K_V1. You can also use weights=AlexNet_Weights.DEFAULT to get the most up-to-date weights.
warnings.warn(msg)

Loading model from: /usr/local/lib/python3.10/dist-packages/lpips/weights/v0.1/alex.pth
Setting up [LPIPS] perceptual loss: trunk [alex], v[0.1], spatial [off]
Loading model from: /usr/local/lib/python3.10/dist-packages/lpips/weights/v0.1/alex.pth
[INFO] Trainer: ngp | 2024-05-06_08-50-24 | cuda | fp16 | model/trial_may
[INFO] #parameters: 768165
[INFO] Loading latest checkpoint ...
[WARN] No checkpoint found, model randomly initialized.
[INFO] load 108 train frames.
[INFO] load /content/SyncTalk/04Label-2.wav aud_features: torch.Size([101, 1, 512])

Loading train data: 53% 57/108 [00:00<00:00, 2772.56it/s]
Traceback (most recent call last):
File "/content/SyncTalk/main.py", line 186, in
test_set = NeRFDataset(opt, device=device, type='train')
File "/content/SyncTalk/nerf_triplane/provider.py", line 354, in init
area = bs[f['img_id']]
IndexError: index 57 is out of bounds for axis 0 with size 57

[G-force78]

OK so my training data was not good enough for some reason, had better results with another video but still have a lot of errors, what is best practice for starting video size and resolution, aspect etc?

ngp_ep0095a.mp4