Alexander Hustinx

Thank you very much for your fast and detailed reply! I'm going to implement these changes and get back to you with results. For now I'll close the issue. Thanks...

Hey there, Sorry for the delay. I worked out all the math for the other coordinates and ran multiple different training sessions and experiments. As a result I once in...

Intuitively the algorithm makes sense; using the actual IoU instead of the predicted localization confidence should return good results, I agree. I feel like the problem is mainly the higher...

Sadly I still haven't been able to reproduce the results. For now I'll leave it as is, so we can close the issue soon. I do have a few other...

I understand the confusion there. It took me a while to figure it out as well, but I believe it works because the gt_boxes that are used as input are...

Hey @chenchr, It's been a while since I've looked through this code. But I can see they do pass `num_boxes` to the RPN too. As they calculate the RPN anchor...

Which CUDA and GCC version do you use? EDIT: If you're using pytorch-1.0 you should use the pytorch-1.0 branch as well (`git checkout pytorch-1.0`) and follow the instructions on that...

> yes,I clone the faster-rcnn.pytorch-1.0 and run python step.py build develop, and follow the 1.0 instruction My previous comment was directed at @Amazingren @dongzhi0312, which version of CUDA and GCC...

Do you experience the same error when training on a single GPU, and then when resuming training on a single GPU?

I haven't been able to recreate your issue. Could you please send me the errors you get for 1 GPU and multiple GPUs? Can you send me a snippet of...