Error with Data Preparation

[ghost]

Any help with this guys? I am using my custom dataset;

export CUDA_VISIBLE_DEVICES=0 Path already exists. Rename it to [/home/christophermasafu/EDVR_m/experiments/001_EDVR_OURS_archived_200805-134700] 20-08-05 13:47:00.664 - INFO: name: 001_EDVR_OURS use_tb_logger: True model: video_base distortion: sr scale: 4 gpu_ids: [0] datasets:[ train:[ name: REDS mode: REDS interval_list: [1] random_reverse: False border_mode: False dataroot_GT: ../home/christophermasafu/EDVR_m/datasets/train_GT.lmdb dataroot_LQ: ../home/christophermasafu/EDVR_m/datasets/train_LR.lmdb cache_keys: meta_info.pkl N_frames: 5 use_shuffle: True n_workers: 3 batch_size: 5 GT_size: 750 LQ_size: 750 use_flip: True use_rot: True color: RGB phase: train scale: 4 data_type: lmdb ] ] network_G:[ which_model_G: EDVR nf: 64 nframes: 5 groups: 8 front_RBs: 5 back_RBs: 10 predeblur: False HR_in: False w_TSA: False scale: 4 ] path:[ pretrain_model_G: None strict_load: True resume_state: None root: /home/christophermasafu/EDVR_m experiments_root: /home/christophermasafu/EDVR_m/experiments/001_EDVR_OURS models: /home/christophermasafu/EDVR_m/experiments/001_EDVR_OURS/models training_state: /home/christophermasafu/EDVR_m/experiments/001_EDVR_OURS/training_state log: /home/christophermasafu/EDVR_m/experiments/001_EDVR_OURS val_images: /home/christophermasafu/EDVR_m/experiments/001_EDVR_OURS/val_images ] train:[ lr_G: 0.0004 lr_scheme: CosineAnnealingLR_Restart beta1: 0.9 beta2: 0.99 niter: 600000 warmup_iter: -1 T_period: [150000, 150000, 150000, 150000] restarts: [150000, 300000, 450000] restart_weights: [1, 1, 1] eta_min: 1e-07 pixel_criterion: cb pixel_weight: 1.0 val_freq: 5000.0 manual_seed: 0 ] logger:[ print_freq: 100 save_checkpoint_freq: 5000.0 ] is_train: True dist: True

20-08-05 13:47:00.739 - INFO: Random seed: 0 20-08-05 13:47:00.740 - INFO: Temporal augmentation interval list: [1], with random reverse is False. 20-08-05 13:47:00.740 - INFO: Using cache keys: meta_info.pkl 20-08-05 13:47:00.740 - INFO: Using cache keys - meta_info.pkl. Traceback (most recent call last): File "/home/christophermasafu/EDVR_m/codes/train.py", line 310, in main() File "/home/christophermasafu/EDVR_m/codes/train.py", line 104, in main train_set = create_dataset(dataset_opt) File "/home/christophermasafu/EDVR_m/codes/data/init.py", line 44, in create_dataset dataset = D(dataset_opt) File "/home/christophermasafu/EDVR_m/codes/data/REDS_dataset.py", line 53, in init self.paths_GT = pickle.load(open('./data/{}'.format(cache_keys), 'rb'))["keys"] FileNotFoundError: [Errno 2] No such file or directory: './data/meta_info.pkl' Traceback (most recent call last): File "/usr/lib/python3.8/runpy.py", line 193, in _run_module_as_main return _run_code(code, main_globals, None, File "/usr/lib/python3.8/runpy.py", line 86, in _run_code exec(code, run_globals) File "/home/christophermasafu/venv/lib/python3.8/site-packages/torch/distributed/launch.py", line 263, in main() File "/home/christophermasafu/venv/lib/python3.8/site-packages/torch/distributed/launch.py", line 258, in main raise subprocess.CalledProcessError(returncode=process.returncode, subprocess.CalledProcessError: Command '['/home/christophermasafu/venv/bin/python3', '-u', '/home/christophermasafu/EDVR_m/codes/train.py', '--local_rank=0', '-opt', '/home/christophermasafu/EDVR_m/codes/options/train/train_EDVR_OURS_M.yml', '--launcher', 'pytorch']' returned non-zero exit status 1.

[xinntao]

REDS dataset use './data/meta_info.pkl' to store meta information. But your custom dataset may not have such meta info. For your own custom dataset, you may need to write a new dataset to fulfil your needs.

BTW, we have updated the codes, you may try to use the new codes :-)

[ghost]

REDS dataset use './data/meta_info.pkl' to store meta information. But your custom dataset may not have such meta info. For your own custom dataset, you may need to write a new dataset to fulfil your needs.

BTW, we have updated the codes, you may try to use the new codes :-)

Thank you!