Update app.py

app.py

@@ -1,22 +1,23 @@
-import tensorflow as tf
+import cv2
 import numpy as np
-from PIL import Image
+import tensorflow as tf
 import gradio as gr
 
 # Load the EfficientNetB0 model
 model = tf.keras.models.load_model("car_brand_classifier_final.h5")
 
-# EfficientNetB0 preprocessing function
-def preprocess_image(image):
-    image = image.resize((224, 224))  # Resize to match EfficientNetB0 input size
-    image = np.array(image)  # Convert to NumPy array
-    image = tf.keras.applications.efficientnet.preprocess_input(image)  # EfficientNetB0 normalization
+# EfficientNetB0 preprocessing function using OpenCV
+def preprocess_image(image_path):
+    image = cv2.imread(image_path)  # Load image using OpenCV
+    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)  # Convert BGR to RGB
+    image = cv2.resize(image, (224, 224))  # Resize to (224, 224)
+    image = image.astype(np.float32) / 255.0  # Normalize pixel values (0-1)
     image = np.expand_dims(image, axis=0)  # Add batch dimension
     return image
 
 # Define the prediction function
-def predict(image):
-    processed_image = preprocess_image(image)  # Preprocess image
+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
 
@@ -25,7 +26,7 @@ def predict(image):
 # Create the Gradio interface
 iface = gr.Interface(
     fn=predict,
-    inputs="image",
+    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."