image_data ?

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 # from transformers import pipeline
 from deepface import DeepFace
+import numpy as np
 from PIL import Image
 
 # pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
@@ -20,13 +21,15 @@ if file_name is not None:
     # to display in in column 1
     col1.image(image, use_column_width=True)
 
-    # capture predictions
-    predictions = DeepFace.analyze(file_name, actions=['emotion'])
+    # capture image data for deepface
+    image_data = np.array(image)
+    # capture predictions from deepface
+    predictions = DeepFace.analyze(image_data, actions=['emotion'])['emotion']
     # predictions = pipeline(image)
 
     # to display in column 2
     col2.header("Emotion Probabilities")
     # for p in predictions:
-    for emotion in predictions['emotion']:
+    for emotion in predictions:
         # col2.subheader(f"{ p['label'] }: { round(p['score'] * 100, 1)}%")
-        col2.subheader(f"{emotion.keys()}: {emotion.values()}")
+        col2.subheader(f"{emotion}")