Skip to content
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

Error message after running demo #12

Open
deism opened this issue Feb 20, 2019 · 2 comments
Open

Error message after running demo #12

deism opened this issue Feb 20, 2019 · 2 comments

Comments

@deism
Copy link

deism commented Feb 20, 2019

Now demo can load new pre-trained file in Pytorch 1.01 and Window 10 environment, thanks for upgrading!

But there is a error message as: "invalid argument 12: dilation should be greater than zero, but got dilationH: 508814473 dilationW: 0 at c:\a\w\1\s\windows\pytorch\aten\src\thcunn\generic/SpatialDilatedMaxPooling.cu:20"

The error is from:
auto [detections, mrcnn_mask] = model->Detect(molded_images, image_metas); => PredictInference(images, image_metas); => PredictRPN(images, config_->post_nms_rois_inference); => fpn_->forward(images); =>x = c1_->forward(x);

I use demo code as is, it seems model and weights are not matched, any clues?

@Kolkir
Copy link
Owner

Kolkir commented Mar 3, 2019

Sorry, I've tested demo on Linux and everything works in my environment. But I don't have Windows environment to test, it will be nice if you can send a patch to fix this problem.

@ahasan016
Copy link

@deism Could yo make it work on windows?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants