Update app.py

app.py

@@ -1,4 +1,3 @@
-import cv2
 import numpy as np
 from PIL import Image
 import streamlit as st
@@ -11,9 +10,6 @@ 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 = np.asarray(image)
-    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|>"
@@ -50,9 +46,10 @@ def main():
     if uploaded_file is not None:
         # load the image
         image = Image.open(uploaded_file).convert("RGB")
+        image = image.resize((224, 224))
         
         # context as prompt
-        prompt = generate_captions(uploaded_file)
+        prompt = generate_captions(image)
         st.write("The Context is:", prompt)
 
         # display the image