# Preparing your AI Model

Your model should have the following structure:

* *Input* (Directory)
* *Output* (Directory)
* *requirements.txt* (File)
* *README.md* (File)
* *src* (Directory)
* *src / run.py* (File)
* *stats* (Directory)

**Input** - 'Input' directory contains sample source images / Videos for inference.

**Output** - 'Output' directory contains sample outputs which were generated by inference on 'Input' directory.

**requirements.txt** - 'requirements.txt' should list all the python dependencies with versions. You can use: `pip freeze > requirements.txt` to generate this file.

**README.md** - This file tells other people why your project is useful, what they can do with your project, and how they can use it.

**src** - 'src' directory contains all the source code for I/O, pre-processing and post-processing along with the trained model.

**src/run.py** - This is the main python file that the user calls. It should be able to take at least 'input' (Input path) and 'output' (Output path) as arguments. Example -

`python src/run.py --input Input --output Output`

**stats** - This directory may contain one or more files. Each file stores inference time taken on particular hardware. Example - 'cpu.txt' stores inference time on CPU.

{% hint style="warning" %}
Above mentioned are the necessary files/directories which your model should have. It may contain additional files if your model requires.
{% endhint %}

Once you have structured your model according to the above template, compress the folder as a zip file.