Google AI Open Images - Object Detection Track: Open Solution
This is an open solution to the Google AI Open Images - Object Detection Track
Check collection of public projects
We are building entirely open solution to this competition. Specifically:
- Learning from the process - updates about new ideas, code and experiments is the best way to learn data science. Our activity is especially useful for people who wants to enter the competition, but lack appropriate experience.
- Encourage more Kagglers to start working on this competition.
- Deliver open source solution with no strings attached. Code is available on our GitHub repository
💻. This solution should establish solid benchmark, as well as provide good base for your custom ideas and experiments. We care about clean code 😃
- We are opening our experiments as well: everybody can have live preview on our experiments, parameters, code, etc. Check: Google-AI-Object-Detection-Challenge
📈and images below:
|UNet training monitor
||Predicted bounding boxes
In this open source solution you will find references to the neptune.ml. It is free platform for community Users, which we use daily to keep track of our experiments. Please note that using neptune.ml is not necessary to proceed with this solution. You may run it as plain Python script
How to start?
Learn about our solutions
- Check Kaggle forum and participate in the discussions.
- Check our Wiki pages
🐬, where we describe our work. Below are link to specific solutions:
|link to code||link to description|
Dataset for this competition
This competition is special, because it used Open Images Dataset V4, which is quite large:
>1.8M images and
Start experimenting with ready-to-use code
You can jump start your participation in the competition by using our starter pack. Installation instruction below will guide you through the setup.
- Clone repository, install requirements (check _requirements.txt)
pip3 install -r requirements.txt
- Register to the neptune.ml (if you wish to use it) and create your project, for example Google-AI-Object-Detection-Challenge.
- Train RetinaNet:
neptune send --worker m-4p100 \ --environment pytorch-0.3.1-gpu-py3 \ --config configs/neptune.yaml \ main.py train --pipeline_name retinanet
neptune run main.py train --pipeline_name retinanet
python main.py -- train --pipeline_name retinanet
- Evaluate/Predict RetinaNet:
Note in case of memory trouble go to
neptune.yaml and change
GAI-14. You should go to
neptune.yaml and change:
experiment_dir: /output/experiment clone_experiment_dir_from: /input/GAI-14/output/experiment
neptune send --worker m-4p100 \ --environment pytorch-0.3.1-gpu-py3 \ --config configs/neptune.yaml \ --input /GAI-14 \ main.py evaluate_predict --pipeline_name retinanet --chunk_size 100
neptune run main.py train --pipeline_name retinanet --chunk_size 100
python main.py -- train --pipeline_name retinanet --chunk_size 100
You are welcome to contribute your code and ideas to this open solution. To get started:
- Check competition project on GitHub to see what we are working on right now.
- Express your interest in particular task by writing comment in this task, or by creating new one with your fresh idea.
- We will get back to you quickly in order to start working together.
- Check CONTRIBUTING for some more information.
There are several ways to seek help: