Update app.py

app.py

@@ -1,36 +1,36 @@
 import gradio as gr
 import numpy as np
-from tensorflow.keras.applications.efficientnet import EfficientNetB0, preprocess_input, decode_predictions
+from tensorflow.keras.applications import EfficientNetB0
+from tensorflow.keras.applications.efficientnet import preprocess_input, decode_predictions
+from tensorflow.keras.preprocessing import image
 
-# Load pretrained EfficientNetB0 model
-model = EfficientNetB0(weights="imagenet")
+# Load pretrained EfficientNetB0
+model = EfficientNetB0(weights="imagenet", include_top=True, input_shape=(224, 224, 3))
 
 def predict(img):
-    # Convert to RGB and resize
-    img = img.convert("RGB")
-    img = img.resize((224, 224))
+    # Ensure image is RGB
+    if img.mode != "RGB":
+        img = img.convert("RGB")
 
-    # Preprocess
-    x = np.array(img)
+    img = img.resize((224, 224))
+    x = image.img_to_array(img)
     x = np.expand_dims(x, axis=0)
     x = preprocess_input(x)
 
-    # Predict
     preds = model.predict(x)
-    decoded = decode_predictions(preds, top=3)[0]
-
-    # Format results with percentages
-    results = {label: f"{score * 100:.2f}%" for (_, label, score) in decoded}
-    return results
+    decoded = decode_predictions(preds, top=1)[0][0]
+    label = decoded[1]
+    confidence = float(decoded[2])
+    return f"🔍 Prediction: {label} ({confidence:.2f} confidence)"
 
-# Gradio interface
-iface = gr.Interface(
+# Gradio Interface
+demo = gr.Interface(
     fn=predict,
     inputs=gr.Image(type="pil"),
-    outputs=gr.Label(num_top_classes=3),
-    title="🐾 Smart Animal & Insect Identifier",
-    description="Upload an image of an animal or insect, and the model will try to identify it."
+    outputs="text",
+    title="🐾 Animal & Insect Identifier",
+    description="Upload an image of an animal or insect, and the model will identify it."
 )
 
 if __name__ == "__main__":
-    iface.launch()
+    demo.launch()