GeneFace
GeneFace copied to clipboard
yerfor
处理自己的视频数据出现问题
params saved
[INFO] ===== finished face tracking =====
[INFO] ===== extract background image from data/processed/videos/jys1/ori_imgs =====
100%|███████████████████████████████████████████████████████████████████████| 339/339 [03:18<00:00, 1.70it/s]
[INFO] ===== extracted background image =====
[INFO] ===== extract head images for data/processed/videos/jys1 =====
100%|█████████████████████████████████████████████████████████████████████| 6767/6767 [01:41<00:00, 66.71it/s]
[INFO] ===== extracted head images =====
[INFO] ===== extract torso and gt images for data/processed/videos/jys1 =====
100%|█████████████████████████████████████████████████████████████████████| 6767/6767 [04:38<00:00, 24.26it/s]
[INFO] ===== extracted torso and gt images =====
[INFO] ===== save transforms =====
[INFO] ===== finished saving transforms =====
Loading the Wav2Vec2 Processor...
Loading the HuBERT Model...
2023-07-29 10:57:59.376227: 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 TF_ENABLE_ONEDNN_OPTS=0.
2023-07-29 10:57:59.421377: 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 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-07-29 10:58:00.117671: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Hubert extracted at data/processed/videos/jys1/aud_hubert.npy
Mel and F0 extracted at data/processed/videos/jys1/aud_mel_f0.npy
loading the model from deep_3drecon/checkpoints/facerecon/epoch_20.pth
loading video ...
extracting 2D facial landmarks ...: 100%|█████████████████████████████████| 5143/5143 [02:33<00:00, 33.60it/s]
start extracting 3DMM...: 0%| | 0/160 [00:00<?, ?it/s]create rasterizer on device cuda:0
start extracting 3DMM...: 100%|█████████████████████████████████████████████| 160/160 [00:39<00:00, 4.06it/s]
3DMM coeff extracted at data/processed/videos/jys1/vid_coeff.npy
| Unknow hparams: []
| Hparams chains: ['egs/egs_bases/radnerf/base.yaml', 'egs/egs_bases/radnerf/lm3d_radnerf.yaml', 'egs/datasets/videos/jys1/lm3d_radnerf.yaml']
| Hparams:
accumulate_grad_batches: 1, ambient_out_dim: 2, amp: True, base_config: ['egs/egs_bases/radnerf/lm3d_radnerf.yaml'], binary_data_dir: data/binary/videos,
bound: 1, camera_offset: [0, 0, 0], camera_scale: 4.0, clip_grad_norm: 0, clip_grad_value: 0,
cond_out_dim: 64, cond_type: idexp_lm3d_normalized, cond_win_size: 1, cuda_ray: True, debug: False,
density_thresh: 10, density_thresh_torso: 0.01, desired_resolution: 2048, dt_gamma: 0.00390625, eval_max_batches: 100,
exp_name: , far: 0.9, finetune_lips: True, finetune_lips_start_iter: 200000, geo_feat_dim: 128,
grid_interpolation_type: linear, grid_size: 128, grid_type: tiledgrid, gui_fovy: 21.24, gui_h: 512,
gui_max_spp: 1, gui_radius: 3.35, gui_w: 512, hidden_dim_ambient: 128, hidden_dim_color: 128,
hidden_dim_sigma: 128, individual_embedding_dim: 4, individual_embedding_num: 13000, infer: False, infer_audio_source_name: ,
infer_bg_img_fname: , infer_c2w_name: , infer_cond_name: , infer_lm3d_clamp_std: 2.5, infer_lm3d_lle_percent: 0.0,
infer_lm3d_smooth_sigma: 0.0, infer_out_video_name: , infer_scale_factor: 1.0, infer_smo_std: 0.0, infer_smooth_camera_path: True,
infer_smooth_camera_path_kernel_size: 7, lambda_ambient: 0.1, lambda_lpips_loss: 0.01, lambda_weights_entropy: 0.0001, load_ckpt: ,
load_imgs_to_memory: False, log2_hashmap_size: 16, lr: 0.0005, max_ray_batch: 4096, max_steps: 16,
max_updates: 250000, min_near: 0.05, n_rays: 65536, near: 0.3, num_ckpt_keep: 1,
num_layers_ambient: 3, num_layers_color: 2, num_layers_sigma: 3, num_sanity_val_steps: 2, num_steps: 16,
num_valid_plots: 5, optimizer_adam_beta1: 0.9, optimizer_adam_beta2: 0.999, print_nan_grads: False, processed_data_dir: data/processed/videos,
raw_data_dir: data/raw/videos, resume_from_checkpoint: 0, save_best: True, save_codes: ['tasks', 'modules', 'egs'], save_gt: True,
scheduler: exponential, seed: 9999, smo_win_size: 5, smooth_lips: False, task_cls: tasks.radnerfs.radnerf.RADNeRFTask,
tb_log_interval: 100, torso_head_aware: False, torso_individual_embedding_dim: 8, torso_shrink: 0.8, update_extra_interval: 16,
upsample_steps: 0, use_window_cond: True, val_check_interval: 2000, valid_infer_interval: 10000, valid_monitor_key: val_loss,
valid_monitor_mode: min, validate: False, video_id: jys1, warmup_updates: 0, weight_decay: 0,
with_att: True, work_dir: ,
loading deepspeech ...
loading Esperanto ...
loading hubert ...
loading Mel and F0 ...
loading 3dmm coeff ...
calculating lm3d ...
loading train_val.json ...
data_gen/nerf/binarizer.py:136: DeprecationWarning: Starting with ImageIO v3 the behavior of this function will switch to that of iio.v3.imread. To keep the current behavior (and make this warning disappear) use import imageio.v2 as imageio or call imageio.v2.imread directly.
bg_img = imageio.imread(background_img_name)
Binarizing train set: 84%|████████████████████████████████████▊ | 5143/6151 [00:00<00:00, 22210.18it/s]
Traceback (most recent call last):
File "data_gen/nerf/binarizer.py", line 277, in
解决了
且行且珍惜 @.***
------------------ 原始邮件 ------------------ 发件人: "Bingliang @.>; 发送时间: 2023年8月7日(星期一) 下午2:46 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [yerfor/GeneFace] 处理自己的视频数据出现问题 (Issue #172)
请问解决了吗
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
就自己处理的视频帧率为50，而提供的视频帧率为25，需要对帧率进行调整
且行且珍惜 @.***
------------------ 原始邮件 ------------------ 发件人: "Bingliang @.>; 发送时间: 2023年8月7日(星期一) 下午2:52 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [yerfor/GeneFace] 处理自己的视频数据出现问题 (Issue #172)
请问是怎么解决的呀
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>