Update app.py

app.py

@@ -1,38 +1,35 @@
 import gradio as gr
 import tensorflow as tf
-from tensorflow.keras.preprocessing import image
 import numpy as np
 from huggingface_hub import hf_hub_download
-import os
 
+# Function to load model from H5 file
 def load_model_from_hub(repo_id, filename):
     model_path = hf_hub_download(repo_id=repo_id, filename=filename)
     return tf.keras.models.load_model(model_path)
 
-# Load the models
-model1 = load_model_from_hub("arsath-sm/face_classification_model1", "face_classification_model1.h5")
-model2 = load_model_from_hub("arsath-sm/face_classification_model2", "face_classification_model2.h5")
+# Load models from Hugging Face Hub
+model1 = load_model_from_hub("arsath-sm/face_classification_model1", "model.h5")
+model2 = load_model_from_hub("arsath-sm/face_classification_model2", "model.h5")
 
-# Preprocess the image
-def preprocess_image(img):
-    img = img.resize((224, 224))  # Adjust size as needed
-    img = image.img_to_array(img)
-    img = np.expand_dims(img, axis=0)
+def preprocess_image(image):
+    img = tf.convert_to_tensor(image)
+    img = tf.image.resize(img, (150, 150))
     img = img / 255.0
-    return img
+    return tf.expand_dims(img, 0)
 
-# Make predictions
-def predict(img):
-    preprocessed_img = preprocess_image(img)
+def predict_image(image):
+    preprocessed_image = preprocess_image(image)
     
-    prediction1 = model1.predict(preprocessed_img)[0][0]
-    prediction2 = model2.predict(preprocessed_img)[0][0]
+    # Make predictions using both models
+    pred1 = model1.predict(preprocessed_image)[0][0]
+    pred2 = model2.predict(preprocessed_image)[0][0]
     
-    result1 = "Real" if prediction1 > 0.5 else "Fake"
-    result2 = "Real" if prediction2 > 0.5 else "Fake"
-    
-    confidence1 = prediction1 if result1 == "Real" else 1 - prediction1
-    confidence2 = prediction2 if result2 == "Real" else 1 - prediction2
+    # Prepare results for each model
+    result1 = "Real" if pred1 > 0.5 else "Fake"
+    confidence1 = pred1 if pred1 > 0.5 else 1 - pred1
+    result2 = "Real" if pred2 > 0.5 else "Fake"
+    confidence2 = pred2 if pred2 > 0.5 else 1 - pred2
     
     return {
         "Model 1 Prediction": f"{result1} (Confidence: {confidence1:.2f})",
@@ -41,8 +38,8 @@ def predict(img):
 
 # Create the Gradio interface
 iface = gr.Interface(
-    fn=predict,
-    inputs=gr.Image(type="pil"),
+    fn=predict_image,
+    inputs=gr.Image(),
     outputs={
         "Model 1 Prediction": gr.Textbox(),
         "Model 2 Prediction": gr.Textbox()