Update app.py

app.py

@@ -1,33 +1,30 @@
-from tensorflow.keras.models import load_model
-from tensorflow.keras.preprocessing.image import load_img, img_to_array
-from tensorflow.keras.applications.efficientnet_v2 import preprocess_input
+import gradio as gr
+import tensorflow as tf
 import numpy as np
-from google.colab import files
-
-# Step 1: Upload the model to Colab (run this in a Colab cell)
-uploaded = files.upload()  # Upload the .h5 model file
+from tensorflow.keras.preprocessing import image
+from tensorflow.keras.applications.efficientnet_v2 import preprocess_input
+from PIL import Image
 
-# Step 2: Load the trained model
-MODEL_PATH = "setosys_dogs_model.h5"  # Adjust if needed
-model = load_model(MODEL_PATH)
+# Load the trained model
+MODEL_PATH = "setosys_dogs_model.h5"
+model = tf.keras.models.load_model(MODEL_PATH)
 
-# Step 3: Define the class labels manually (as per your model's training setup)
-# You need to know the classes that were used during model training
-class_labels = ["Labrador Retriever", "German Shepherd", "Golden Retriever", "Bulldog", "Poodle"]  # Example, update this list
+# Get class labels from the model (assuming the model has a 'class_indices' attribute)
+class_labels = list(model.class_indices.keys())  # Fetch class labels from the model
 
-# Step 4: Define image preprocessing function for EfficientNetV2
-def preprocess_image(image_path):
+# Image preprocessing function using EfficientNetV2S
+def preprocess_image(img: Image.Image) -> np.ndarray:
     """Preprocess the image to match the model's input requirements."""
-    img = load_img(image_path, target_size=(224, 224))  # Resize image to model input size
-    img_array = img_to_array(img)
+    img = img.resize((224, 224))  # Resize image to model input size
+    img_array = np.array(img)
     img_array = preprocess_input(img_array)  # EfficientNetV2 preprocessing
     img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
     return img_array
 
-# Step 5: Define prediction function
-def predict_dog_breed(image_path):
+# Prediction function
+def predict_dog_breed(img: Image.Image) -> dict:
     """Predict the breed of the dog in the uploaded image."""
-    img_array = preprocess_image(image_path)
+    img_array = preprocess_image(img)
     predictions = model.predict(img_array)
     
     # Check the shape of the predictions to make sure the output is correct
@@ -39,12 +36,17 @@ def predict_dog_breed(image_path):
     # Get predicted breed and its confidence score
     predicted_breed = class_labels[class_idx] if class_idx < len(class_labels) else "Unknown"
     
-    return predicted_breed, confidence
+    return {predicted_breed: confidence}
 
-# Step 6: Upload and test with an image
-uploaded_image = files.upload()  # Upload a test image
-image_path = list(uploaded_image.keys())[0]  # Get the filename of the uploaded image
+# Create Gradio interface
+interface = gr.Interface(
+    fn=predict_dog_breed,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Label(),
+    title="Dog Breed Classifier",
+    description="Upload an image of a dog to predict its breed."
+)
 
-# Step 7: Run prediction
-breed, confidence = predict_dog_breed(image_path)
-print(f"Predicted Breed: {breed}, Confidence: {confidence:.2f}")
+# Launch the Gradio app
+if __name__ == "__main__":
+    interface.launch()