VarifocalNet
VarifocalNet copied to clipboard
hyz-xmaster
run demo report error
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?
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.
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?
Hi, the problem is fixed. Please see the commit. It is caused by one bug of MMDetection.
Hi I meet a new problem during the train model process, the train information of Loss is not print.
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.
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.
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.
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.
Hi The train log problem is over, the coco.py add the filter of CLASSNAME and modify the classname is execute no matter.