Update app.py

app.py

@@ -1,82 +1,3 @@
-# import gradio as gr
-# import tensorflow as tf
-# from tensorflow.keras.models import load_model
-# from tensorflow.keras.preprocessing import image
-# import numpy as np
-# import requests
-# import os
-# import random
-# from huggingface_hub import from_pretrained_keras
-
-# model = from_pretrained_keras("diabolic6045/indian_cities_image_classification")
-
-# # # Model URL and path
-# # model_url = "https://huggingface.co/diabolic6045/indian_cities_image_classification/resolve/main/model.h5"
-# # model_path = "my_model.h5"
-
-# # # Download the model if it doesn't exist
-# # if not os.path.exists(model_path):
-# #     print("Downloading the model...")
-# #     response = requests.get(model_url)
-# #     with open(model_path, "wb") as f:
-# #         f.write(response.content)
-# #     print("Model downloaded.")
-
-# # # Load the model once at the start
-# # try:
-# #     print("Loading the model...")
-# #     model = load_model(model_path)
-# #     print("Model loaded successfully.")
-# # except Exception as e:
-# #     print(f"Failed to load model: {str(e)}")
-# #     model = None
-
-# # Define class labels
-# class_labels = ['Ahmedabad', 'Delhi', 'Kerala', 'Kolkata', 'Mumbai']
-# threshold = 0.5  # Minimum accuracy threshold
-
-# # Function to process and predict the image
-# def process_image(img):
-#     if model is None:
-#         return "Error: Model could not be loaded. Please check the logs for more information."
-
-#     # Preprocess the input image
-#     img = image.img_to_array(img)
-#     img = np.expand_dims(img, axis=0)
-#     img = img / 255.0  # Normalize
-
-#     try:
-#         # Make predictions
-#         predictions = model.predict(img)
-#         predicted_class_index = np.argmax(predictions)
-#         predicted_class_label = class_labels[predicted_class_index]
-#         accuracy = predictions[0][predicted_class_index]
-
-#         # Check if accuracy is below the threshold
-#         if all(acc < threshold for acc in predictions[0]):
-#             return "This location is not in our database."
-#         else:
-#             # Random color for text
-#             color = f"#{random.randint(0, 255):02x}{random.randint(0, 255):02x}{random.randint(0, 255):02x}"
-#             output = f"<span style='font-size: 24px; color: {color};'>Predicted city: <strong>{predicted_class_label}</strong></span>"
-#             acc = f"<span style='font-size: 24px; color: {color};'>Confidence: <strong>{accuracy*100:.02f}%</strong></span>"
-#             return output + "<br>" + acc
-#     except Exception as e:
-#         return f"Error during prediction: {str(e)}"
-
-# # Define the Gradio interface
-# iface = gr.Interface(
-#     fn=process_image,
-#     inputs=gr.Image(type="pil", label="Upload an image of an Indian city"),
-#     outputs=gr.HTML(label="Prediction"),
-#     title="Indian Cities Image Classification",
-#     description="Upload an image of a city in India, and the model will predict which of the five cities it is: Ahmedabad, Delhi, Kerala, Kolkata, or Mumbai.",
-#     theme=gr.themes.Soft()
-# )
-
-# # Launch the Gradio app
-# iface.launch()
-
 import gradio as gr
 import numpy as np
 import os
@@ -112,9 +33,10 @@ class_labels = ['Ahmedabad', 'Delhi', 'Kerala', 'Kolkata', 'Mumbai']
 # Function to preprocess the image and predict the city
 def classify_city(img):
     # Preprocess the image
+    img = img.resize((175, 175))
     img = image.img_to_array(img)
     img = np.expand_dims(img, axis=0)
-    img = img / 255.0  # Normalize the image
+    img = img / 175.0  # Normalize the image
     
     # Make predictions
     predictions = model.predict(img)