https://github.com/rois2coeurs/prog-multimedia-analyse-image

https://github.com/rois2coeurs/prog-multimedia-analyse-image

Last synced: 16 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/rois2coeurs/prog-multimedia-analyse-image
• Owner: rois2coeurs
• Created: 2024-03-21T13:20:37.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2024-03-31T21:04:41.000Z (10 months ago)
• Last Synced: 2024-11-11T18:07:54.752Z (3 months ago)
• Language: Python
• Size: 25.4 KB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

        
# Python Image Classification Project

This project is a simple image classification application using K-Nearest Neighbors (KNN) algorithm. The project is implemented in Python and uses the scikit-learn library for the KNN classifier.

## Project Structure

The project consists of the following main components:

- `DataManager.py`: This file contains the `DataManager` class which is responsible for handling the image data. It includes methods for reading images from a directory, converting them to grayscale, and resizing them.

- `knn.py`: This file contains the `KNNClassifier` class which is responsible for training the KNN classifier, making predictions, and saving/loading the trained model.

- `network.py`: This file contains the neuronal network which is responsible for training the Network, making predictions, and saving/loading the trained model.

- `main.py`: This is the main entry point of the application. It checks if a trained model exists, if not, it trains a new model and saves it. Then, it uses the model to make predictions on the test data.

## Dependencies

The project has the following dependencies:

- tensorflow

- keras

- seaborn

- scikit-learn

- numpy

- PIL

- matplotlib

These can be installed using pip:

```bash

pip install -r requirements.txt

```

You can add the information about the new command-line arguments to the `Usage` section of your `README.md` file. Here's how you can update it:

## Usage

### Args

- `--train ` : Path to the training dataset

- `--test ` : Path to the testing dataset

- `--no-cache` : Ignore any previously saved classifiers and train a new one

- `--confusion-matrix` : Display confusion matrix after testing the classifier 

- `--knn` : Use the knn algorithm

- `--neuronal ` : Use the neuronal algorithm with the specified epochs

### Exemple

#### KNN

```bash

python main.py --train datas/MNIST/training --test datas/MNIST/testing --confusion-matrix --knn

```

#### Neuronal

```bash

python main.py --train datas/MNIST/training --test datas/MNIST/testing --confusion-matrix --neuronal 10

```

#### Both

```bash

python main.py --train datas/MNIST/training --test datas/MNIST/testing --confusion-matrix --neuronal 10 --knn

```

Replace `path_to_training_dataset` and `path_to_testing_dataset` with the actual paths to your datasets.