Update app.py

app.py

@@ -4,6 +4,8 @@ from tensorflow.keras.applications.resnet import ResNet152, preprocess_input, de
 from tensorflow.keras.preprocessing.image import img_to_array
 from PIL import Image
 import numpy as np
+import base64
+from io import BytesIO
 
 # Load the pre-trained ResNet152 model
 MODEL_PATH = "resnet152-image-classifier.h5"  # Path to the saved model
@@ -13,11 +15,25 @@ except Exception as e:
     print(f"Error loading model: {e}")
     exit()
 
+def decode_image_from_base64(base64_str):
+    """
+    Decodes a base64 string to a PIL image.
+    """
+    # Decode the base64 string to bytes
+    image_data = base64.b64decode(base64_str)
+    # Convert the bytes into a PIL image
+    image = Image.open(BytesIO(image_data))
+    return image
+
 def predict_image(image):
     """
     Process the uploaded image and return the top 3 predictions.
     """
     try:
+        # If the image is base64 encoded, decode it
+        if isinstance(image, str):
+            image = decode_image_from_base64(image)
+        
         # Preprocess the image
         image = image.resize((224, 224))  # ResNet152 expects 224x224 input
         image_array = img_to_array(image)
@@ -38,7 +54,7 @@ def predict_image(image):
 # Create the Gradio interface
 interface = gr.Interface(
     fn=predict_image,
-    inputs=gr.Image(type="pil"),  # Accepts an image input
+    inputs=gr.Image(type="pil", tool="editor"),  # Accepts an image input
     outputs=gr.Label(num_top_classes=3),  # Shows top 3 predictions with confidence
     title="ResNet152 Image Classifier",
     description="Upload an image, and the model will predict what's in the image.",
@@ -47,4 +63,4 @@ interface = gr.Interface(
 
 # Launch the Gradio app
 if __name__ == "__main__":
-    interface.launch()
+    interface.launch()