Update app.py

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 import tensorflow as tf
 from tensorflow.keras.models import load_model
 from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
-from tensorflow.keras.preprocessing.image import img_to_array,load_img
+from tensorflow.keras.preprocessing.image import img_to_array
 import numpy as np
 from PIL import Image
 import os
@@ -16,64 +16,31 @@ labels = {
     'amphibia': ['American Bullfrog', 'American Toad', 'Green Frog', 'Northern Leopard Frog']
 }
 
+# Preprocess the image
 def preprocess_image(image):
     img = image.resize((224, 224))  # MobileNet requires 224x224 input size
     img_array = img_to_array(img)
     img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
     img_array = preprocess_input(img_array)  # Preprocess the image
-    
-    return img_array
+    return img_array, image  # Return both the preprocessed array and resized image for display
 
 # Function to perform inference
-def predict(img_path):
-    img = preprocess_image(img_path)
+def predict(img):
+    img_array, resized_img = preprocess_image(img)
     model = load_model(r"inceptionv3_classs.h5")
-    preds = model.predict(img)  # Get the model predictions
-    decoded_preds = np.argmax(preds) 
-    print(decoded_preds, labels['class'][decoded_preds])
-    return labels['class'][decoded_preds]
-    
-
+    preds = model.predict(img_array)  # Get the model predictions
+    decoded_preds = np.argmax(preds)
     
-   
-    # results = {}
-    # image_array = load_and_preprocess_image(image)
-    # print(image_array)
-    # # Predict class level
-    # class_preds = hierarchical_models['class'].predict(image_array)
-    # print(class_preds)
-    # class_idx = np.argmax(class_preds)
-    # print(class_idx)
-    # class_label = labels['class'][class_idx]
-    # class_confidence = class_preds[0][class_idx]
-    # class_level = f"{class_label} ({class_confidence*100:.2f}%)"
-    
-    # # Predict species level
-    # hierarchical_models[class_label] = load_model(f"inceptionv3_{class_label}.h5")
-    # species_preds = hierarchical_models[class_label].predict(image_array)
-    # species_idx = np.argmax(species_preds)
-    # species_label = labels[class_label][species_idx]
-    # species_confidence = species_preds[0][species_idx]
-    # species_level = f"{species_label} ({species_confidence*100:.2f}%)"
-    # return class_level,species_level
-
-# Sample images (you can add paths to images here)
-# sample_images = [
-#     ("Sample Amphibia", "path/to/amphibia.jpg"),
-#     ("Sample Aves", "path/to/aves.jpg"),
-#     ("Sample Mammalia", "path/to/mammalia.jpg"),
-#     # Add more sample images as needed
-# ]
+    # Return the prediction and the resized image for display
+    return resized_img, labels['class'][decoded_preds]
 
-# Create Gradio interface
+# Create the Gradio interface
 iface = gr.Interface(
-    fn=predict,
-    inputs=gr.Image(type="pil"),
-    outputs=[gr.Label(label="class_label")],
-    # examples=sample_images,
-    title="Image Classification",
-    description="Upload an image to classify it into species and class level.",
+    fn=predict,  # The prediction function
+    inputs=gr.inputs.Image(type="pil"),  # Input as a PIL image
+    outputs=[gr.outputs.Image(type="pil"), gr.outputs.Textbox()],  # Output the resized image and prediction
+    title="Animal Classifier"
 )
 
-# Launch the interface
+# Launch the Gradio interface
 iface.launch()