Update app.py

app.py

@@ -1,100 +1,35 @@
 import gradio as gr
-import tensorflow as tf
-from tensorflow import keras
 import numpy as np
+import tensorflow as tf
 from PIL import Image
 
-# --- Configuration ---
+# --- Config ---
 MODEL_PATH = "cats-vs-dogs-finetuned.keras"
-IMAGE_SIZE = (180, 180) # Adjust this to match the input size your model expects!
-CLASS_LABELS = ['Cat', 'Dog']
-
-# --- Load the Model ---
-# We load the Keras model. Hugging Face Spaces will automatically find this file
-# if you upload it to your repository.
-try:
-    model = keras.models.load_model(MODEL_PATH)
-    print(f"Model loaded successfully from {MODEL_PATH}")
-except Exception as e:
-    # If the model fails to load (e.g., during initial setup before it's uploaded),
-    # we use a placeholder function. This helps the app start.
-    print(f"Error loading model: {e}. Using a placeholder function.")
-    model = None
-
-# --- Prediction Function ---
-def predict_image(input_img_pil):
-    
-
-     # WRAP ENTIRE LOGIC IN TRY/EXCEPT FOR MAXIMUM ERROR CAPTURE
-    try:
-        # 0. Crucial check: ensure an image was actually uploaded
-        if input_img_pil is None:
-            # Return a simple dictionary indicating missing input
-            return {"Please upload an image first.": 1.0}
-
-        if model is None:
-            # Model loading failed during initialization
-            return {"MODEL NOT FOUND": 1.0, "Please check if cat-vs-dog.keras exists.": 0.0}
-
-        # 1. Preprocessing: Resize and convert to NumPy array
-        print(f"Original image size: {input_img_pil.size}")
-        img_resized = input_img_pil.resize(IMAGE_SIZE)
-        img_array = keras.preprocessing.image.img_to_array(img_resized)
-        
-        # 2. Rescaling and Batch dimension:
-        img_array = img_array / 255.0  # Common normalization step
-        img_array = np.expand_dims(img_array, axis=0) # Add batch dimension
-
-        # 3. Prediction
-        print(f"Array shape for model input: {img_array.shape}")
-        predictions = model.predict(img_array) # Get the single prediction result
-        print(f"Raw model predictions: {predictions}")
-
-        # 4. Format the output for Gradio's Label component
-        # Assuming predictions is a 2-element array: [prob_cat, prob_dog]
-        pdog=float(predictions[0][0])
-        return {"dog":pdog,"cat":1-pdog}
-    
-    except Exception as e:
-        # Catch any error, log it, and return it to the user in a visible format
-        error_message = f"CRITICAL RUNTIME ERROR: {str(e)}"
-        detailed_trace = traceback.format_exc()
-        
-        print("\n--- DETAILED RUNTIME ERROR LOG ---")
-        print(error_message)
-        print(detailed_trace)
-        print("------------------------------------\n")
-        
-        # This format should force Gradio to display the specific error message
-        return {f"💥 {error_message}": 1.0}
-
+IMAGE_SIZE = (180, 180)  # change if your model expects a different size
 
+# Load model once
+model = tf.keras.models.load_model(MODEL_PATH)
 
-# --- Gradio Interface Setup ---
+def predict_image(img: Image.Image):
+    if img is None:
+        return {"Cat": 0.5, "Dog": 0.5}
 
-# Define the input component (Image) and output component (Label)
-image_input = gr.Image(type="pil", label="Upload a Cat or Dog Image")
-label_output = gr.Label(num_top_classes=2, label="Prediction")
+    # Preprocess
+    x = img.convert("RGB").resize(IMAGE_SIZE)
+    x = np.asarray(x, dtype=np.float32) / 255.0
+    x = np.expand_dims(x, 0)  # (1, H, W, 3)
 
-# Example images for users to try (place these in your Space if you use them)
-examples = [
-    # To use these, you would need to upload files named 'example_cat.jpg' and 'example_dog.jpg'
-    # 'example_cat.jpg', 
-    # 'example_dog.jpg'
-]
+    # Predict: model outputs shape (1,1) with sigmoid for "Dog" probability
+    p_dog = float(model.predict(x, verbose=0)[0, 0])  # cast to Python float
+    return {"Cat": 1.0 - p_dog, "Dog": p_dog}
 
-# Create the Gradio interface
 demo = gr.Interface(
     fn=predict_image,
-    inputs=image_input,
-    outputs=label_output,
-    title="Keras Cat vs Dog Classifier",
-    description="Upload an image of a cat or dog to see the model's prediction. The model is loaded from cat-vs-dog.keras.",
-    theme=gr.themes.Soft(),
-    # Optional: Add examples if you upload them
-    # examples=examples
+    inputs=gr.Image(type="pil", label="Upload a Cat or Dog"),
+    outputs=gr.Label(num_top_classes=2, label="Prediction"),
+    title="Cats vs Dogs (Keras, single-logit)",
+    description="keras image classification model for cat-vs-dog images"
 )
 
-# Launch the app
 if __name__ == "__main__":
     demo.launch()