Update app.py

app.py

@@ -1,33 +1,33 @@
+import streamlit as st
 import tensorflow as tf
 import numpy as np
-import gradio as gr
+from PIL import Image
 
 # Load the model
 model = tf.keras.models.load_model("vgg19_binary_nonbinary.h5")
 
-# Define the preprocessing function
+# Preprocess the image
 def preprocess_image(image):
-    image = image.resize((224, 224))  # Resize to match model input size
-    image = np.array(image) / 255.0   # Normalize pixel values
-    image = np.expand_dims(image, axis=0)  # Add batch dimension
+    image = image.resize((224, 224))
+    image = np.array(image) / 255.0
+    image = np.expand_dims(image, axis=0)
     return image
 
-# Define the prediction function
-def classify_image(image):
+# Streamlit app
+st.title("Binary vs Non-Binary Image Classification")
+st.write("Upload an image to classify it as 'binary' or 'non-binary'.")
+
+uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+if uploaded_file is not None:
+    image = Image.open(uploaded_file)
+    st.image(image, caption="Uploaded Image", use_column_width=True)
+    st.write("Classifying...")
+
+    # Preprocess and predict
     processed_image = preprocess_image(image)
     predictions = model.predict(processed_image)
     class_names = ["binary", "non-binary"]
     confidence = {class_names[i]: float(predictions[0][i]) for i in range(2)}
-    return confidence
-
-# Create a Gradio interface
-interface = gr.Interface(
-    fn=classify_image,
-    inputs=gr.Image(type="pil"),  # Input is an image
-    outputs=gr.Label(num_top_classes=2),  # Output is a label with confidence scores
-    title="Binary vs Non-Binary Image Classification",
-    description="Upload an image to classify it as 'binary' or 'non-binary'.",
-)
 
-# Launch the app
-interface.launch()
+    st.write("Prediction:")
+    st.write(confidence)