Update app.py

app.py

@@ -1,3 +1,4 @@
+import cv2
 import numpy as np
 from PIL import Image
 import streamlit as st
@@ -10,7 +11,8 @@ extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-capti
 tokeniser = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
 
 def generate_captions(image):
-    image = Image.open(image).convert("RGB")
+    #image = Image.open(image).convert("RGB")
+    image = cv2.resize(image, (224, 224))
     generated_caption = tokeniser.decode(model.generate(extractor(image, return_tensors="pt").pixel_values.to("cpu"))[0])
     sentence = generated_caption
     text_to_remove = "<|endoftext|>"