# Example README

*English translation by SOTA – AI Community of the Russian original ([README.md in baseline.zip](https://disk.yandex.ru/d/t6YCFGkgodFOCA/baseline.zip)). Organisers who would like this translation removed can email sota.ai.community@gmail.com.*

Team: ######

The solution is based on the OML(open-metric-learning) library.
Python version 3.11.11
conda create -n test_nto python=3.11

Datasets used:
- The tiger dataset provided by the organisers.

Preparing the dataset for training:
    Use the environment with requirements.txt
    Run baseline_prepare_data_1.ipynb

Training the Re-ID model:
    Use the environment with requirements.txt
    Run baseline_train_2.ipynb


Producing the file to submit to the platform:
    Use the environment with requirements.txt
    Run baseline_create_submission_3.ipynb

> *Attention!* Do not forget to include all the weights of all the models used for inference, not only those for creating the feature vectors. If you have several stages, do not forget the weights for all the stages, even if they were pretrained (out of the box).

To produce an up-to-date requirements.txt:
```    
    pip freeze > requirements.txt
```

To find out the Python version:
```
python --version
``` 

For each solution that you consider final, create separate corresponding folders: this will make it easier to reproduce your solution, and for you to choose what to send to the organisers.