huangjun12
commented
1 year ago frame_dir, frames_len, labels = line_split 这一行报错 标注文件可能是video格式的，但使用的配置文件是针对frame格式的，换成video格式的配置文件就好了https://github.com/PaddlePaddle/PaddleVideo/blob/develop/configs/recognition/tsm/tsm_ucf101_videos.yaml
报错： Traceback (most recent call last): File "main.py", line 143, in
main()
File "main.py", line 139, in main
profiler_options=args.profiler_options)
File "F:\PaddleVideo-develop\paddlevideo\tasks\train.py", line 111, in train_model
train_dataset = build_dataset((cfg.DATASET.train, cfg.PIPELINE.train))
File "F:\PaddleVideo-develop\paddlevideo\loader\builder.py", line 49, in build_dataset
dataset = build(cfg_dataset, DATASETS, key="format")
File "F:\PaddleVideo-develop\paddlevideo\utils\build_utils.py", line 35, in build
return obj_cls(**cfg_copy)
File "F:\PaddleVideo-develop\paddlevideo\loader\dataset\frame.py", line 58, in init
super().init(file_path, pipeline, data_prefix, test_mode)
File "F:\PaddleVideo-develop\paddlevideo\loader\dataset\base.py", line 48, in init
self.info = self.load_file()
File "F:\PaddleVideo-develop\paddlevideo\loader\dataset\frame.py", line 66, in load_file
frame_dir, frames_len, labels = line_split
ValueError: not enough values to unpack (expected 3, got 2)
INFO 2023-03-19 16:28:41,692 launch_utils.py:343] terminate all the procs
INFO 2023-03-19 16:28:41,692 launch_utils.py:343] terminate all the procs
ERROR 2023-03-19 16:28:41,693 launch_utils.py:642] ABORT!!! Out of all 1 trainers, the trainer process with rank=[0] was aborted. Please check its log.
ERROR 2023-03-19 16:28:41,693 launch_utils.py:642] ABORT!!! Out of all 1 trainers, the trainer process with rank=[0] was aborted. Please check its log.
INFO 2023-03-19 16:28:44,708 launch_utils.py:343] terminate all the procs
INFO 2023-03-19 16:28:44,708 launch_utils.py:343] terminate all the procs
INFO 2023-03-19 16:28:44,708 launch.py:402] Local processes completed.
INFO 2023-03-19 16:28:44,708 launch.py:402] Local processes completed.
报错位置： def load_file(self): """Load index file to get video information.""" info = [] with open(self.file_path, 'r') as fin: for line in fin: line_split = line.strip().split() frame_dir, frames_len, labels = line_split if self.data_prefix is not None: frame_dir = osp.join(self.data_prefix, frame_dir) info.append( dict(frame_dir=frame_dir, suffix=self.suffix, frames_len=frames_len, labels=int(labels))) return info