Contribute: Vehicles Classification using CNN

Neural Networks/Vehicle Classifier/README.md

@@ -0,0 +1,58 @@
+# Vehicle Classifier AI
+
+## Description
+
+- Developed a high-performance **Vehicle Image Recognizer** web app using **deep learning techniques**.
+- Designed and implemented a **Convolutional Neural Network (CNN)** with **TensorFlow** and **Keras** to classify various vehicle types.
+- Integrated a **Flask** server for backend functionality, allowing users to upload vehicle images and receive real-time predictions.
+- Supports recognition of vehicles including **bus, family sedan, fire engine, heavy truck, jeep, minibus, racing car, SUV, taxi, and truck**.
+
+## Features
+
+- **Real-Time Predictions:** Utilized Flask to manage image uploads and provide on-the-fly predictions for the type of vehicle.
+- **Interactive Web App:** Designed an intuitive web interface where users can easily upload images and get immediate classification results.
+- **Highly Accurate Model:** Trained the CNN on a dataset of 1,400 images for training and 200 images for validation, leading to a highly performant model.
+
+## Tech Stack
+
+- **Programming Language:** Python
+- **Machine Learning Libraries:** TensorFlow, Keras
+- **Web Framework:** Flask
+- **Frontend Technologies:** HTML5, CSS3, JavaScript
+- **Dataset:** 
+  - Vehicle classification dataset from Kaggle: [Kaggle Dataset](https://www.kaggle.com/datasets/marquis03/vehicle-classification)
+
+## Installation Instructions
+
+`Run all the cells in jupyter, you will have vehicle_model.h5. Now follow the instructions`
+
+1. Clone the GitHub repository:
+   ```bash
+   git clone https://github.com/UppuluriKalyani/ML-Nexus.git
+   ```
+
+2. Navigate to the project directory:
+   ```bash
+   cd Neural Networks
+   cd Vehicle Classifier
+   ```
+
+3. Install the required Python packages:
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+4. Run the Flask app:
+   ```bash
+   python app.py
+   ```
+
+5. Open your web browser and go to `http://127.0.0.1:5000` to use the app.
+
+## Screenshot
+
+![Screenshot 2024-10-18 204728](https://github.com/user-attachments/assets/4706df55-48be-4aca-a606-2c7546318a00)
+
+## Demo Video
+
+https://github.com/user-attachments/assets/c9c5d5f9-ba2c-4969-8685-beed10b1e39a

Neural Networks/Vehicle Classifier/app.py

@@ -0,0 +1,62 @@
+from flask import Flask, render_template, request, redirect, url_for
+from tensorflow.keras.preprocessing.image import ImageDataGenerator # type: ignore
+from tensorflow.keras.models import load_model # type: ignore
+from tensorflow.keras.preprocessing import image # type: ignore
+import tensorflow as tf
+import numpy as np
+import os
+
+app = Flask(__name__)
+
+train_dir = 'dataset/train'
+
+model = load_model('vehicle_model.h5')
+
+batch_size = 32
+
+train_datagen = ImageDataGenerator(rescale=1/255)
+
+classes =['bus', 'family sedan', 'fire engine', 'heavy truck', 'jeep', 'minibus', 'racing car', 'SUV', 'taxi', 'truck']
+
+train_generator = train_datagen.flow_from_directory(
+        train_dir,  
+        target_size=(600, 600),  
+        batch_size=batch_size,
+        classes = classes,
+        class_mode='categorical'
+)
+
+loaded_model = tf.keras.models.load_model('vehicle_model.h5')
+
+def predict_vehicle_with_loaded_model(img_path):
+    img = image.load_img(img_path, target_size=(600, 600))
+    img_array = image.img_to_array(img)
+    img_array = np.expand_dims(img_array, axis=0)
+    img_array /= 255.0
+
+    predictions = loaded_model.predict(img_array)
+    class_idx = np.argmax(predictions[0])
+    class_label = list(train_generator.class_indices.keys())[class_idx]
+    return class_label
+
+@app.route('/', methods=['GET', 'POST'])
+def upload_file():
+    if request.method == 'POST':
+        print("Received POST request")
+        if 'file' not in request.files:
+            print("No file part in request")
+            return redirect(request.url)
+        file = request.files['file']
+        if file.filename == '':
+            print("No selected file")
+            return redirect(request.url)
+        if file:
+            file_path = os.path.join('static', file.filename)
+            print(f"Saving file to {file_path}")
+            file.save(file_path)
+            label = predict_vehicle_with_loaded_model(file_path)
+            return render_template('app.html', label=label, file_path=file.filename)
+    return render_template('app.html')
+
+if __name__ == '__main__':
+    app.run(debug=True)

Neural Networks/Vehicle Classifier/requirements.txt

@@ -0,0 +1,4 @@
+Flask
+tensorflow
+numpy
+keras