Jeethesh Pai Umesh

Hi Eric, I was training for descriptor + detector after two homographic adaptations for detector. But after some epochs, I get nan loss. When I see traceback it says that...

https://github.com/eric-yyjau/pytorch-superpoint/blob/4ff74df8fa3c10ce9eb9fdc561f787d9e8bc9691/datasets/patches_dataset.py#L85 Hello Eric, I am getting a value of more than 1 after scaling using the above code. Isn't this supposed to normalize the scaling in the homography matrix? Thanks...

Hi I was trying to train on one of my dataset for a student research project. Can you please tell me if you applied NMS while homographic adaptation phase ....

Did you encounter negative loss during training. I am seeing a negative loss after a few iteration for my Pascal VOC train set. I think it might be beacuse of...

Descriptor training

2

Hallo @rpautrat, I am very grateful for your repository. It helped me a lot to understand the implementation of the paper Superpoint. I am currently doing a student project on...

Multiplication of prior with log likelihood - Code not found !!

4

@BlackHC Can you please tell me where you are multiplying the prior with the log_prob of the logits during evaluation.  As mentioned in the line 12: We have to...

Debugging the Custom Plugins

13

Thank you so much for this wonderful repository. This helped to create custom plugin library in the most efficient way. Is there a way to test the enqueue function because...