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
RuntimeWarning: invalid value encountered in sqrt #36
Comments
Maybe this is the main cause instead of runtime warning from
|
I also met this question. But it wouldn't happen when I use multi-gpu. |
When you change # gpu from 4 to 1 you also need to reduce lr by 4x and increase # iter by 4x. |
With the below change, I was able to run after my post. And you confirmed it, thank you for the quick update.
|
changing #iter/lr by 2x may not match the result I reported as you changed batch size from 4 to 1, and they (batch size/lr/#iter) should be matched. |
Right, thank you and updated with by 4
|
Hi I encounter a similar error.
It is because the propose rois has x1>x2 or y1>y2 which cause the w<0 or h<0. np.log2(negative number ) cause nan. I have tried smaller learning rate. 0.0025 or 0.00125. But it still happen. |
I also met the same issue. After I change the backbone to ResNeXT-101, RPN will produces negative width or height and causes NaN. |
@andyhahaha @weixianghong Please notice that we used pretrained weights converted from caffe, which are expecting different image preprocessing comparing to torchvision model. Please set |
It works, thank you! |
Hi,
I have ran to this error while I was running (
upsnet_resnet50_coco_1gpu.yaml
is just a number of gpu change based on4gpu.yaml
96b7b5172b7b76446f637f4922b7a2054e46703b
and this PR change (update the pythonpath forinit_coco.sh
#35)The text was updated successfully, but these errors were encountered: