-
Thanks for your great work.
Could you please show your loss curve in traing? Or could you let me know the loss value of PixPro at the end of training?
-
Thank you very much for your work and code sharing. In the Pixpro.py, I found that in "pixpro_instance_loss", 'pred_instance_1' has one more predictor layer than 'proj_instance_1_ng'. I don’t quite un…
-
Thank you very much for your work. After reading the code, I have a question.
In the paper, the final loss consists of $l_{pixcontrast}, l_{pixpro} and l_{instance}$.
But In the Pixpro.py, I just …
-
When I try to run openvslam on my own video, filmed with a kodak pixpro sp360, it shows points on the video, but doesnt show anything in pangolin.
The tutorial i used was https://openvslam.readthedo…
-
Hello,
Thank you for your work. Amazing results on both classification and dense prediction tasks!
You have opened the evaluation code for the classification task. Are you planning to open your …
-
The pre-training losses are always negative (like -199.03), is that normal?
-
Hi, I am very interested in using this source code for my robotics research. I wonder if this source code is compatible with other Kodak cameras with lower prices such as Kodak PIXPRO SP360 Action Cam…
-
Hello,
This is likely a YouTube issue but as I can't be sure something else went wrong, I wanted to post here.
I first edited the video with Kodak PIXPRO_SP360_4K tool. (Input fisheye, output was…
-
Hi,
I am trying to execute the repo with my own data and the loss values are not reducing as expected. Here's the code I modified (just added 2 lines)
```
epoch_loss = []
no_of_batches = len(s…
-
Any one successfully reproduce the results?