Add files via upload

Author: srujana-16

Image Classification/README.md

@@ -0,0 +1,19 @@
+# **Multi Stack Games**
+This script performs image classification using the MobileNetV2 pre-trained model provided by TensorFlow. It allows you to classify images into different categories based on the ImageNet dataset.
+
+## Prerequisites
+Before running the script, ensure you have the following dependencies installed:
+
+- TensorFlow (version 2.x)
+- NumPy
+- Pillow
+
+## Usage 
+1. Prepare your image: Ensure you have an image file that you want to classify. Supported image formats include JPEG, PNG, and BMP.
+
+2. Update the image path: In the script, locate the image_path variable and replace "image.jpg" with the path to your image file.
+
+3. Run the script: Execute the script using the following command: `python image_classification.py`
+
+4. View the predictions: The script will display the top 3 predictions for the image, along with their respective labels and confidence scores.
+

Image Classification/image_classification.py

@@ -0,0 +1,30 @@
+import tensorflow as tf
+import tensorflow.keras.applications.mobilenet_v2 as mobilenet
+from tensorflow.keras.preprocessing import image
+from tensorflow.keras.applications.mobilenet_v2 import preprocess_input, decode_predictions
+import numpy as np
+
+def classify_image(image_path):
+    # Load the pre-trained MobileNetV2 model
+    model = mobilenet.MobileNetV2(weights='imagenet')
+
+    # Load and preprocess the image
+    img = image.load_img(image_path, target_size=(224, 224))
+    img_array = image.img_to_array(img)
+    img_array = np.expand_dims(img_array, axis=0)
+    processed_img = preprocess_input(img_array)
+
+    # Perform image classification
+    predictions = model.predict(processed_img)
+    decoded_predictions = decode_predictions(predictions, top=3)[0]
+
+    return decoded_predictions
+
+# Example usage
+image_path = "image.jpg"
+predictions = classify_image(image_path)
+
+# Print the top 3 predictions
+for prediction in predictions:
+    print(f"{prediction[1]}: {prediction[2]*100:.2f}%")
+