FileNotFoundError: No such file: 'GeneFacePlusPlus/data/processed/videos/xxxx/inpaint_torso_imgs/00006601.png'

[zhangjunhao-scut]

| set_hparams Unknow hparams: []
| Hparams chains: ['egs/egs_bases/radnerf/base.yaml', 'egs/egs_bases/radnerf/lm3d_radnerf.yaml', 'egs/datasets/person_25_2_cropped/lm3d_radnerf.yaml', 'egs/datasets/person_25_2_cropped/lm3d_radnerf_sr.yaml']
| Hparams: {
"accumulate_grad_batches": 1,
"add_eye_blink_cond": true,
"ambient_coord_dim": 3,
"ambient_loss_mode": "mae",
"amp": true,
"base_config": [
"./lm3d_radnerf.yaml"
],
"binary_data_dir": "data/binary/videos",
"bound": 1,
"camera_offset": [
0,
0,
0
],
"camera_scale": 4.0,
"clip_grad_norm": 0.0,
"clip_grad_value": 0,
"cond_dropout_rate": 0.0,
"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": "motion2video_nerf/person_25_2_cropped_head",
"eye_blink_dim": 2,
"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": 1.5,
"infer_lm3d_lle_percent": 0.25,
"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,
"init_method": "tcp",
"lambda_ambient": null,
"lambda_dual_fm": 0.0,
"lambda_lap_ambient_loss": 0.0,
"lambda_lpips_loss": 0.001,
"lambda_weights_entropy": 0.0001,
"load_ckpt": "",
"load_imgs_to_memory": false,
"log2_hashmap_size": 16,
"lpips_mode": "vgg19_v2",
"lpips_start_iters": 200000,
"lr": 0.0005,
"lr_lambda_ambient": 0.01,
"max_ray_batch": 4096,
"max_steps": 16,
"max_updates": 250000,
"min_near": 0.05,
"n_rays": 65536,
"near": 0.3,
"nerf_keypoint_mode": "lm68",
"not_save_modules": [
"criterion_lpips",
"dual_disc"
],
"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,
"polygon_face_mask": true,
"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": 3,
"smooth_lips": false,
"sr_start_iters": 0,
"start_rank": 0,
"target_ambient_loss": 1e-08,
"task_cls": "tasks.radnerfs.radnerf_sr.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": "person_25_2_cropped",
"warmup_updates": 0,
"weight_decay": 0,
"with_att": true,
"with_sr": true,
"work_dir": "checkpoints/motion2video_nerf/person_25_2_cropped_head",
"world_size": -1,
"zero_dummy": true
}
09/06 09:40:11 AM GPU available: True, GPU used: [1], world_size: 1, multi-machine training: False
/mnt/sdc1/jhzhang/GeneFacePlusPlus/tasks/radnerfs/dataset_utils.py:266: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
self.lm68s = torch.tensor(self.lm2ds[:, index_lm68_from_lm478, :])
val: Smooth head trajectory (rotation and translation) with a window size of 7
| Copied codes to checkpoints/motion2video_nerf/person_25_2_cropped_head/codes/20240906094026.
| cond_prenet Trainable Parameters: 0.050M
| blink_embedding Trainable Parameters: 0.000M
| blink_encoder Trainable Parameters: 0.001M
| cond_att_net Trainable Parameters: 0.004M
| position_embedder Trainable Parameters: 1.807M
| ambient_net Trainable Parameters: 0.029M
| ambient_embedder Trainable Parameters: 1.807M
| sigma_net Trainable Parameters: 0.041M
| direction_embedder Trainable Parameters: 0.000M
| color_net Trainable Parameters: 0.019M
| dropout Trainable Parameters: 0.000M
| sr_net Trainable Parameters: 0.271M
Sanity Val: 0%| | 0/2 [00:00<?, ?step/s]
Traceback (most recent call last):
File "/mnt/sdc1/jhzhang/GeneFacePlusPlus/utils/commons/trainer.py", line 236, in run_single_process
self.train()
File "/mnt/sdc1/jhzhang/GeneFacePlusPlus/utils/commons/trainer.py", line 314, in train
self.evaluate(self.task, False, 'Sanity Val', max_batches=self.num_sanity_val_steps)
File "/mnt/sdc1/jhzhang/GeneFacePlusPlus/utils/commons/trainer.py", line 276, in evaluate
for batch_idx, batch in enumerate(pbar):
File "/mnt/sdc1/jhzhang/anaconda3/envs/geneface/lib/python3.9/site-packages/tqdm/std.py", line 1181, in iter
for obj in iterable:
File "/mnt/sdc1/jhzhang/anaconda3/envs/geneface/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 633, in next
data = self._next_data()
File "/mnt/sdc1/jhzhang/anaconda3/envs/geneface/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 677, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "/mnt/sdc1/jhzhang/anaconda3/envs/geneface/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/mnt/sdc1/jhzhang/anaconda3/envs/geneface/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 51, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/mnt/sdc1/jhzhang/GeneFacePlusPlus/tasks/radnerfs/dataset_utils.py", line 316, in getitem
torso_img = load_image_as_uint8_tensor(self.samples[idx]['torso_img_fname'])
File "/mnt/sdc1/jhzhang/GeneFacePlusPlus/utils/commons/image_utils.py", line 46, in load_image_as_uint8_tensor
img = torch.as_tensor(imageio.imread(fname))
File "/mnt/sdc1/jhzhang/anaconda3/envs/geneface/lib/python3.9/site-packages/imageio/init.py", line 97, in imread
return imread_v2(uri, format=format, **kwargs)
File "/mnt/sdc1/jhzhang/anaconda3/envs/geneface/lib/python3.9/site-packages/imageio/v2.py", line 359, in imread
with imopen(uri, "ri", **imopen_args) as file:
File "/mnt/sdc1/jhzhang/anaconda3/envs/geneface/lib/python3.9/site-packages/imageio/core/imopen.py", line 113, in imopen
request = Request(uri, io_mode, format_hint=format_hint, extension=extension)
File "/mnt/sdc1/jhzhang/anaconda3/envs/geneface/lib/python3.9/site-packages/imageio/core/request.py", line 247, in init
self._parse_uri(uri)
File "/mnt/sdc1/jhzhang/anaconda3/envs/geneface/lib/python3.9/site-packages/imageio/core/request.py", line 407, in _parse_uri
raise FileNotFoundError("No such file: '%s'" % fn)
FileNotFoundError: No such file: '/mnt/sdc1/jhzhang/GeneFacePlusPlus/data/processed/videos/person_25_2_cropped/inpaint_torso_imgs/00006601.png'

---

数据处理的步骤一步步走完了，训练头部模型的时候反馈如下错误：
FileNotFoundError: No such file: '/mnt/sdc1/jhzhang/GeneFacePlusPlus/data/processed/videos/person_25_2_cropped/inpaint_torso_imgs/00006601.png'
找不到00006601.png，可是我的训练视频处理成图片集的时候，只有5610张，为什么程序会寻找不存在的图片。而且，训练头部模型的命令行我试了好几次，每次反馈同样的错误，都是找不到00006321.png，00006511,png这种不存在的图片。

[madonghui0329]

@zhangjunhao-scut 你的视频帧率不是25

[zhangjunhao-scut]

ok，我再去试试，感谢感谢