Hi everyone, MMdetection resources are now released. It has been the library with the most demand in Food Benchmark’s community.
- We are releasing pre-trained models for making it easier to get started with your first submission!
- The training notebook now has submission interfaces as well (for both quick & active participation directly from Colab)
Thanks for the contributions by @jyot_makadiya 
Getting Started Notebook 
https://www.aicrowd.com/showcase/mmdetection-training-and-submissions-quick-active
Model Zoo
| Type | AP | AR | Dataset | |
|---|---|---|---|---|
| htc_without_semantic_r50_fpn_1x | 0.113 | 0.319 | Round 1 (v2.0) |  Download |
| htc_without_semantic_r50_fpn_1x | 0.113 | 0.319 | Round 2 (v2.1) | Download |
Already have your privately trained models? 
- Clone the official starter kit (or rebase your existing repository)
- Check the instructions available in
predict_mmdetection.py. - Make your submission.
New to the competition?
- Make your first submission! Try out sample predictions.json for Quick Submission Interface. [1 min]
- Explore the dataset and play with the training code: MMdetection training and submissions (Quick, Active) [
mins, but lot more fun!]
- Want to use Detection2? Check out the previous release post.