DAMO-NLP-SG / Video-LLaMA

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
BSD 3-Clause "New" or "Revised" License
2.7k stars 243 forks source link

训练获取Dataloader中 的数据出错 #124

Closed Junphy-Jan closed 10 months ago

Junphy-Jan commented 10 months ago

报错信息: Train: data epoch: [0] [ 0/1000] eta: 1:00:53 lr: 0.000001 loss: 0.8702 time: 3.6535 data: 0.0000 max mem: 61442 Traceback (most recent call last): File "/code/Video-LLaMA/video_llama/datasets/datasets/dataloader_utils.py", line 147, in next data = next(self.iter_loader) StopIteration

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None, File "/usr/lib/python3.8/runpy.py", line 87, in _run_code exec(code, run_globals) File "/home/root/.vscode-server/extensions/ms-python.python-2023.19.12891009/pythonFiles/lib/python/debugpy/adapter/../../debugpy/launcher/../../debugpy/main.py", line 39, in cli.main() File "/home/root/.vscode-server/extensions/ms-python.python-2023.19.12891009/pythonFiles/lib/python/debugpy/adapter/../../debugpy/launcher/../../debugpy/../debugpy/server/cli.py", line 430, in main run() File "/home/root/.vscode-server/extensions/ms-python.python-2023.19.12891009/pythonFiles/lib/python/debugpy/adapter/../../debugpy/launcher/../../debugpy/../debugpy/server/cli.py", line 284, in run_file runpy.run_path(target, run_name="main") File "/home/root/.vscode-server/extensions/ms-python.python-2023.19.12891009/pythonFiles/lib/python/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 321, in run_path return _run_module_code(code, init_globals, run_name, File "/home/root/.vscode-server/extensions/ms-python.python-2023.19.12891009/pythonFiles/lib/python/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 135, in _run_module_code _run_code(code, mod_globals, init_globals, File "/home/root/.vscode-server/extensions/ms-python.python-2023.19.12891009/pythonFiles/lib/python/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 124, in _run_code exec(code, run_globals) File "/code/Video-LLaMA/train.py", line 107, in main() File "/code/Video-LLaMA/train.py", line 103, in main runner.train() File "/code/Video-LLaMA/video_llama/runners/runner_base.py", line 378, in train train_stats = self.train_epoch(cur_epoch) File "/code/Video-LLaMA/video_llama/runners/runner_base.py", line 438, in train_epoch return self.task.train_epoch( File "/code/Video-LLaMA/video_llama/tasks/base_task.py", line 114, in train_epoch return self._train_inner_loop( File "/code/Video-LLaMA/video_llama/tasks/base_task.py", line 205, in _train_inner_loop samples = next(data_loader) File "/code/Video-LLaMA/video_llama/datasets/datasets/dataloader_utils.py", line 43, in next return next(self.loaders[loader_idx]) File "/code/Video-LLaMA/video_llama/datasets/datasets/dataloader_utils.py", line 154, in next data = next(self.iter_loader) StopIteration

训练配置

model: arch: video_llama model_type: pretrain_llama_v2 freeze_vit: True freeze_qformer: True

查看 IterLoader 中 self._dataloader 发现 length 为0