Update app.py

app.py

@@ -1,37 +1,43 @@
-import cv2
-import numpy as np
 import tensorflow as tf
-import gradio as gr
+import numpy as np
 from PIL import Image
+import gradio as gr
+import os
+
+# Load the model
+model = tf.keras.models.load_model("car_brand_classifier_final.h5", compile=False)
 
-# Load the EfficientNetB0 model
-model = tf.keras.models.load_model("car_brand_classifier_final.h5")
+# Define image directory where car brand images are stored
+IMAGE_DIR = "car_brands"  # Make sure this folder exists with images named as class labels
 
-# EfficientNetB0 preprocessing function using OpenCV
-# Define the preprocessing function
-def preprocess_image(image_path):
-    image = Image.open(image_path)  # Open image from path
-    image = image.resize((299, 299))  # Resize to model input size
-    image = np.array(image) / 255.0  # Normalize pixel values
+# Preprocess image to match EfficientNetB0 input requirements
+def preprocess_image(image):
+    image = image.resize((224, 224))  # Resize to match EfficientNetB0
+    image = np.array(image) / 255.0  # Normalize
     image = np.expand_dims(image, axis=0)  # Add batch dimension
     return image
 
-# Define the prediction function
-def predict(image_path):
-    processed_image = preprocess_image(image_path)  # Preprocess image
-    predictions = model.predict(processed_image)  # Model inference
-    predicted_class = np.argmax(predictions, axis=1)[0]  # Get class with highest probability
+# Prediction function
+def predict(image):
+    processed_image = preprocess_image(image)
+    predictions = model.predict(processed_image)
+    predicted_class = np.argmax(predictions, axis=1)[0]  # Get predicted class index
+
+    # Find corresponding image for predicted class
+    matching_image_path = os.path.join(IMAGE_DIR, f"{predicted_class}.jpg")
 
-    return f"Predicted class: {predicted_class}"
+    if os.path.exists(matching_image_path):
+        return matching_image_path  # Return image file path
+    else:
+        return "No matching image found"
 
-# Create the Gradio interface
+# Gradio Interface
 iface = gr.Interface(
     fn=predict,
-    inputs=gr.components.Image(type="filepath", label="Upload Car Image"),
-    outputs="text",
-    title="Car Brand Classifier",
-    description="Upload an image of a car to classify its brand."
+    inputs="image",
+    outputs="image",  # Change output to "image"
+    title="Car Vision",
+    description="Upload an image of a car, and get a matching brand image.",
 )
 
-# Launch the app
 iface.launch()