Update app.py

app.py

@@ -1,15 +1,12 @@
 import os
-import numpy as np
+import gradio as gr
+import tensorflow as tf
 from tensorflow.keras.models import load_model
-from tensorflow.keras.preprocessing import image as keras_image
-from flask import Flask, request, jsonify
-from PIL import Image
-import io
-
-app = Flask(__name__)
+from tensorflow.keras.preprocessing import image
+import numpy as np
 
 # Ensure the environment is set up correctly (we assume CPU-based execution here)
-os.environ["CUDA_VISIBLE_DEVICES"] = "-1"  # Disable GPU to avoid GPU-related warnings
+os.environ["CUDA_VISIBLE_DEVICES"] = "-1"  # Disable GPU to avoid the GPU-related warnings
 
 # Load the model
 def load_trained_model():
@@ -24,47 +21,40 @@ def load_trained_model():
 
 model = load_trained_model()
 
-# Define preprocessing function to resize and normalize images
-def preprocess_image(image, target_size=(224, 224)):
-    img = Image.open(io.BytesIO(image))
-    img = img.resize(target_size)
-    img_array = np.array(img) / 255.0
-    img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
-    return img_array
-
-# Define a route to classify the uploaded image
-@app.route('/predict', methods=['POST'])
-def predict():
-    if 'image' not in request.files:
-        return jsonify({"error": "No image provided"}), 400
-
-    image = request.files['image']
-    if not image:
-        return jsonify({"error": "No image content"}), 400
-    
+# Define the function to process the image and predict the disease
+def predict_disease(image_file):
     try:
-        # Preprocess the image for prediction
-        image_data = preprocess_image(image.read())
+        # Preprocess the image
+        img = image.load_img(image_file, target_size=(224, 224))  # Adjust size based on model input
+        img_array = image.img_to_array(img)
+        img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
+        img_array /= 255.0  # Normalize the image if required by the model
 
         # Predict the class of the tomato leaf disease
-        predictions = model.predict(image_data)
+        predictions = model.predict(img_array)
+        
+        # Assuming the model returns probabilities, get the class with the highest probability
         predicted_class = np.argmax(predictions, axis=1)[0]
 
-        # Return the prediction result
-        disease_labels = {
-            0: "Tomato Bacterial Spot",
-            1: "Tomato Early Blight",
-            2: "Tomato Late Blight",
-            3: "Tomato Mosaic Virus",
-            4: "Tomato Yellow Leaf Curl Virus"
-        }
+        # You can map the class index to the disease name if required
+        disease_classes = ['Bacterial_spot', 'Early_blight', 'Late_blight', 'Tomato_mosaic_virus', 'Tomato_Yellow_Leaf_Curl_Virus']
+        predicted_disease = disease_classes[predicted_class]
 
-        prediction_result = disease_labels.get(predicted_class, "Unknown disease")
-        
-        return jsonify({"prediction": prediction_result}), 200
+        return predicted_disease
+    
     except Exception as e:
         print(f"Error during prediction: {e}")
-        return jsonify({"error": "Prediction failed"}), 500
-
+        return "Error during prediction"
+
+# Define Gradio interface
+iface = gr.Interface(
+    fn=predict_disease,
+    inputs=gr.inputs.Image(type="file"),
+    outputs="text",
+    title="Tomato Leaf Disease Detection",
+    description="Upload an image of a tomato leaf, and the model will predict the disease."
+)
+
+# Launch the Gradio interface
 if __name__ == '__main__':
-    app.run(debug=True)
+    iface.launch()