Update app.py

app.py

@@ -1,7 +1,7 @@
 import streamlit as st
 from transformers import pipeline
 from PIL import Image
-import cv2
+import base64
 
 pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
 
@@ -16,7 +16,13 @@ if st.button("Take an image from camera"):
     cap = cv2.VideoCapture(0)
     ret, frame = cap.read()
     if ret:
-        cv2.imwrite('webcam_image.jpg', frame)
+        # Encode the webcam image as a Base64 string
+        img_encoded = base64.b64encode(cv2.imencode('.jpg', frame)[1]).decode('utf-8')
+
+        # Pass the Base64 encoded image to the pipeline function
+        predictions = pipeline(Image.open('data:image/jpeg;base64,' + img_encoded))
+
+        # Replace file_name with the encoded image
         file_name = 'webcam_image.jpg'
 
 # Add a text bar to add a title
@@ -28,11 +34,17 @@ image_description = st.text_input("Image Description", value="(Optional)")
 if file_name is not None:
     col1, col2 = st.columns(2)
 
-    image = Image.open(file_name)
+    # Check if the file is a webcam image
+    if file_name == 'webcam_image.jpg':
+        # Use the Base64 encoded image
+        image = Image.open('data:image/jpeg;base64,' + img_encoded)
+    else:
+        # Open the uploaded image
+        image = Image.open(file_name)
+
     col1.image(image, use_column_width=True)
     predictions = pipeline(image)
 
     col2.header("Probabilities")
     for p in predictions:
         col2.subheader(f"{ p['label'] }: { round(p['score'] * 100, 1)}%")
-