New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
ModuleNotFoundError: No module named 'upsnet.bbox.bbox' #9
Comments
From your information you only compile bbox cython module with python 3.7, make sure you also use python 3.7 when you run experiments. |
Also please note that config files w/o 4gpu suffix are with horovod in distributed setting |
�We only have 1 GPU in our environment now. Is it still compatible with the distributed setting? |
Then please edit the 4gpu config, reduce lr by 4x / enlarge #iter by 4x, etc. BTW I don't think you can run coco dataset w/ 1 GPU in a acceptable time, please try cityscapes instead. |
I am not so sure to make the setting upsnet_resnet50_cityscapes_4gpu.yaml to fit my current environment with only 1 GPU. I have done the change below. ==== train:
==== test: ==== Did I miss anything? Thanks. |
looks good to me |
I know training takes a long time. Could you please give me a rough time how long it may take to finish training a model using only 1 GPU based on the above setting? Thank you! |
It will take ~3 days to train on 1 1080Ti GPU |
I see. What if I don't need a model as accurate as your best one? Could I trade off performance for less training time? For example, I can decrease the iteration numbers in order to get a trained model more quickly, which may have lower accuracy. If this is acceptable, what parameters I can try first, iteration number or else? Thank you! |
You can reduce #iter, e.g. 72k/96k rather than 144k/192k |
兄弟请问怎么自定义自己的coco panoptic格式的数据集 |
Did I miss any step to get this error?
This is what I got in the route: upsnet/bbox
Thanks.
The text was updated successfully, but these errors were encountered: