IndexError: list index out of range

报错描述

Traceback (most recent call last):
  File "tools/train.py", line 164, in <module>
    main()
  File "tools/train.py", line 156, in main
    train_model(model, datasets, cfg, validate=args.validate, test=test_option, timestamp=timestamp, meta=meta)
  File "/root/pyskl/pyskl/apis/train.py", line 144, in train_model
    runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
  File "/root/miniconda3/envs/pyskl/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 127, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "/root/miniconda3/envs/pyskl/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 54, in train
    self.call_hook('after_train_epoch')
  File "/root/miniconda3/envs/pyskl/lib/python3.7/site-packages/mmcv/runner/base_runner.py", line 309, in call_hook
    getattr(hook, fn_name)(self)
  File "/root/miniconda3/envs/pyskl/lib/python3.7/site-packages/mmcv/runner/hooks/evaluation.py", line 267, in after_train_epoch
    self._do_evaluate(runner)
  File "/root/miniconda3/envs/pyskl/lib/python3.7/site-packages/mmcv/runner/hooks/evaluation.py", line 507, in _do_evaluate
    key_score = self.evaluate(runner, results)
  File "/root/miniconda3/envs/pyskl/lib/python3.7/site-packages/mmcv/runner/hooks/evaluation.py", line 364, in evaluate
    results, logger=runner.logger, **self.eval_kwargs)
  File "/root/pyskl/pyskl/datasets/base.py", line 138, in evaluate
    if isinstance(results[0], list) or isinstance(results[0], tuple):
IndexError: list index out of range

 

问题描述

生成list文件的时候，由于只考虑了训练集，导致最终生成的ann_file注释文件就只有训练集

于是执行下面命令行的时候

bash tools/dist_train.sh configs/rgbpose_conv3d/pose_only.py 1 --validate --test-last --test-best

就会报错

解决方案

生成list文件的时候，需要考虑训练集测试集都包括进去，然后生成最终的ann_file注释文件

这样就不报错了。命令行就可以正常执行