tensorflow
[Help wanted] FCOS: Fully Convolutional One-Stage Object Detection
Help wanted: Research paper code and models
Please help us to implement the following research paper using TensorFlow 2.
If you want to contribute, please leave a comment to express your interest.
Awesome external contributors will be nominated for Google Open Source Peer Bonus.
Research papers
Status
- In progress
Contributor(s)
- @paxbun
Tasks
- Implement a paper in TensorFlow 2
- Reproduce the paper results
- Publish documentation
- Publish pre-trained SavedModel files at TensorFlow Hub
Development environment
- Branch: https://github.com/tensorflow/models/tree/fcos
Requirements
- Follow our contribution guidelines
License
By contributing, you agree that your contributions will be licensed under Apache License 2.0.
Hey @jaeyounkim, my friends @nithinsubbiah, @stwinata and I are interested in contributing and implementing this paper. It's our first time contributing to tensorflow/models (typically we play around MLIR land HLO/Linalg for nextgen tf compilers), Would the project be structured in this manner? Thanks in advance!
Hi @raikonenfnu, I'm already working on this paper (I've just finished reading this paper now and this is the first time for me too!), so we need some rearrangements if you and your friends want to implement this paper.
hi @paxbun, thanks for letting me know. that's alright, we can look for other papers to implement! Goodluck on this implementation, hope you have a lot of fun! :)
@Tanishq-01 I have failed to complete the implementation; for some reason, it successfully converges on Google Colab but not on my GPU server with A100. As far as I know, I'm no longer participating in the program. I apologize for all the extra costs for waiting for me.
Hello,
I have started reading this paper and will start working on implementing it, it is my first time fully implementing a paper from the beginning to the end. and I wanted to let you know.
Kind regards Samer
