Fixed: Re-committing model using Git LFS

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.hdf5 filter=lfs diff=lfs merge=lfs -text

Model.hdf5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd13975286ffab8fa97a7fe189d47190f1e67a89e65ee89d0af313e53e80f59
+size 129105944

app.py

@@ -0,0 +1,74 @@
+import gradio as gr
+import tensorflow as tf
+import numpy as np
+from PIL import Image
+
+# Load your trained model
+model = tf.keras.models.load_model('model.hdf5')
+
+# Define the class names based on your image
+# I created this list from the dictionary you provided
+class_names = [
+    'Apple___Apple_scab', 'Apple___Black_rot', 'Apple___Cedar_apple_rust', 'Apple___healthy',
+    'Blueberry___healthy', 'Cherry_(including_sour)___Powdery_mildew', 'Cherry_(including_sour)___healthy',
+    'Corn_(maize)___Cercospora_leaf_spot Gray_leaf_spot', 'Corn_(maize)___Common_rust', 'Corn_(maize)___Northern_Leaf_Blight',
+    'Corn_(maize)___healthy', 'Grape___Black_rot', 'Grape___Esca_(Black_Measles)', 'Grape___leaf_blight_(Isariopsis_Leaf_Spot)',
+    'Grape___healthy', 'Orange___Haunglongbing_(Citrus_greening)', 'Peach___Bacterial_spot', 'Peach___healthy',
+    'Pepper,_bell___Bacterial_spot', 'Pepper,_bell___healthy', 'Potato___Early_blight', 'Potato___Late_blight',
+    'Potato___healthy', 'Raspberry___healthy', 'Soybean___healthy', 'Squash___Powdery_mildew', 'Strawberry___Leaf_scorch',
+    'Strawberry___healthy', 'Tomato___Bacterial_spot', 'Tomato___Early_blight', 'Tomato___Late_blight',
+    'Tomato___Leaf_Mold', 'Tomato___Septoria_leaf_spot', 'Tomato___Spider_mites Two-spotted_spider_mite',
+    'Tomato___Target_Spot', 'Tomato___Yellow_Leaf_Curl_Virus', 'Tomato___mosaic_virus', 'Tomato___healthy'
+]
+
+
+# Prediction function
+def predict(image):
+    """
+    This function takes an image, preprocesses it, and returns the model's prediction.
+    """
+    # --- PREPROCESSING STEP ---
+    # The input 'image' from Gradio is a NumPy array.
+    # IMPORTANT: You might need to change the resize dimensions to match your model's input shape.
+    # Common shapes are (224, 224) or (256, 256). I'll use (256, 256) as a default.
+    img = Image.fromarray(image).resize((256, 256))
+    img_array = np.array(img)
+    
+    # Normalize the image (if you did this during training)
+    # Common normalization is to scale pixel values to [0, 1]
+    img_array = img_array / 255.0
+    
+    # Add a batch dimension
+    img_batch = np.expand_dims(img_array, axis=0)
+
+    # --- PREDICTION STEP ---
+    prediction = model.predict(img_batch)
+    
+    # Get the index of the highest probability
+    predicted_class_index = np.argmax(prediction[0])
+    
+    # Get the predicted class name
+    predicted_class_name = class_names[predicted_class_index]
+    
+    # Get the confidence score
+    confidence = float(np.max(prediction[0]))
+    
+    # Return a dictionary of labels and their confidences
+    return {predicted_class_name: confidence}
+
+# --- GRADIO INTERFACE ---
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(label="Upload a photo of a crop leaf 🌿"),
+    outputs=gr.Label(num_top_classes=1, label="Prediction Result"),
+    title="Crop Disease Prediction",
+    description="Upload an image of a crop leaf to predict its disease. This model can identify 38 different conditions.",
+    examples=[
+        # You can add paths to example images here if you have any
+        # ["path/to/your/example1.jpg"],
+        # ["path/to/your/example2.jpg"]
+    ]
+)
+
+# Launch the app
+iface.launch()