https://github.com/luisfelipepoma/draw_detector
An application to classify a hand drawing into different classes.
https://github.com/luisfelipepoma/draw_detector
computer-vision django flask-application ia python
Last synced: 25 days ago
JSON representation
An application to classify a hand drawing into different classes.
- Host: GitHub
- URL: https://github.com/luisfelipepoma/draw_detector
- Owner: LuisFelipePoma
- License: mit
- Created: 2023-10-18T21:43:25.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-10-24T04:04:24.000Z (over 1 year ago)
- Last Synced: 2025-02-11T14:46:23.423Z (3 months ago)
- Topics: computer-vision, django, flask-application, ia, python
- Language: Jupyter Notebook
- Homepage: https://drawdetector-production.up.railway.app/
- Size: 2.82 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# DevicePredictor
## How to set up the enviroment
- First we create the enviroment `.env`
```bash
python -m venv .env
```
- Then install the `requirements.txt`
```bash
pip install -r requirements.txt
```
## How to train the model
- Once you have the enviroment created and the requirements installed, you can run the command `python`
```bash
python addData.py
```
> Then you can add the data to the model
- Now for get the dataset you can add to the url the parameter `/prepare`
> This will save the dataset in `X.npy` and `y.npy` in the folder `model` that you can use to train the model
- Finally run the notebook `model_train` in the folder `model`
> This will save a file `model.h5` that you can use to predict the device
## How to use
- Once you have the model trained you can run the command `python`
```bash
python main.py
```
> For add new data `repulsive-square-production.up.railway.app`