run demo report error

Question

run demo report error

gpsherry opened this issue 4 years ago · 9 comments

Hi
I run the demo and report one problem as the follow picture and my environment is follow:
cuda=10.1
pytorch=1.5
mmdetection=2.6
mmcv-full=1.15
Do you know the problem?

Answer 1 · 2020-11-11T09:49:05.000Z

I guess this problem may be caused by the incompatibility of your mmcv and pytorch. If you have used this command pip install mmcv-full==latest+torch1.6.0+cu101 -f https://download.openmmlab.com/mmcv/dist/index.html to install mmcv, then your pytorch version should be 1.6.0. Alternatively, you can change the command to pip install mmcv-full==latest+torch1.5.0+cu101 -f https://download.openmmlab.com/mmcv/dist/index.html to be compatible with your version of pytorch. By the way, if you reinstall mmcv, you need first uninstall the installed one.

Answer 2 · 2020-11-11T10:59:20.000Z

Hi
The method of you say is not useful, the same error is report. but i modify the mmdet/api/inference.py of device = next(model.parameters()).device to device = 0 ,then the problem is not occur.why??The code is have bug?

Answer 3 · 2020-11-11T11:56:24.000Z

Hi, the problem is fixed. Please see the commit. It is caused by one bug of MMDetection.

Answer 4 · 2020-11-11T12:07:30.000Z

Hi
I meet a new problem during the train model process, the train information of Loss is not print.

Answer 5 · 2020-11-11T12:29:15.000Z

Hi
I meet a new problem during the train model process, the train information of Loss is not print.

I have no experience of using TensorBoard to view the training process. You may use dict(type='TextLoggerHook') instead of dict(type='TensorboardLoggerHook') to monitor the training.

Answer 6 · 2020-11-11T12:35:50.000Z

I have used dict(type='TextLoggerHook') in the first time, but i can not see the train log, so i use dict(type='TensorboardLoggerHook') and can not see train log. now, i don't know my train problem that the mode is convergent or not.

Answer 7 · 2020-11-11T12:46:17.000Z

Are you running the training on a very small dataset? If it is, setting interval=1 should print the log. By the way, I do not think it will work to train such big a network on a that small dataset.

Answer 8 · 2020-11-11T13:24:32.000Z

I test in original mmdetection code in my dataset is no problem and i debug your code find you train_pipeline load trian data len is 1 but test_pipeline is no problem.

Answer 9 · 2020-11-12T02:03:26.000Z

Hi
The train log problem is over, the coco.py add the filter of CLASSNAME and modify the classname is execute no matter.