-
Notifications
You must be signed in to change notification settings - Fork 33
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
share .pth.tar file #33
Comments
In case you are interested in road detection methods: |
Thank you so much for your work! I find it really hard to train the model whose IOU is as high as the paper showed, usually less than 5%. I wonder could you share the model file 'xxx.pth', thanks a lot! |
@XinlingQiu I have the same problem with you. The IOU is 5-6% less than that in the paper. Did you solve the question? |
Hi @XinlingQiu, @kangkau Thank you for using the work to explore your research. I assume you are using the similar splits for train/valid on DeepGlobe (available in the repo: link). I have reported the number on the valid set. Regards |
Thank you for your advice! I used the same splits for train/valid on DG, but the result on DG homepage is still less than 0.6. So I wonder if your iou result is derived from your own splited valid set. |
Hi @kangkau, The IoU mentioned in the paper is on my splits which are available in the repo. Thanks |
How can I fuse the results of the orientation task and the segmentation task to enhance the final result? Thank you! Looking forward to your reply! |
Thank you very much for your work! I trained the deepglobe dataset with your train_mtl.py , but the prediction is not very good, even worse than using segmentation network like unet or linknet. Could you share your model file? And other question,How the orientation task enhance the final result,add two tasks result?Thanks a lot!
The text was updated successfully, but these errors were encountered: