Update pages/Captionize.py

pages/Captionize.py

@@ -1,5 +1,7 @@
 import torch 
-import re 
+import re
+from PIL import Image
+import requests
 import streamlit as st
 from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel 
 
@@ -33,9 +35,9 @@ feature_extractor = ViTFeatureExtractor.from_pretrained(encoder_checkpoint)
 tokenizer = AutoTokenizer.from_pretrained(decoder_checkpoint)
 model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint).to(device)
 
-
 def predict(image,max_length=64, num_beams=4):
-  image = image.convert('RGB')
+  #image = image.convert('RGB')
+  image = Image.open(requests.get(image, stream=True).raw).convert("RGB")
   image = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
   clean_text = lambda x: x.replace('<|endoftext|>','').split('\n')[0]
   caption_ids = model.generate(image, max_length = max_length)[0]