Update app.py

app.py

@@ -1,10 +1,10 @@
-from transformers import VisionEncoderDecoderModle, ViTImageProcer, Autotokenizer
+from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer
 import torch
 from PIL import Image
 
-model = VisionEncoderDecoderModle.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
-feature_external = ViTImageProcer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
-tokenizer = Autotokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+feature_extractor = ViTImageProcessor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)
@@ -21,11 +21,10 @@ def predict_caption(image_paths):
             image = image.convert(mode="RGB")
         images.append(image)
 
-    pixel_values = feature_extractor(images=images, return_pixel_values=True).pixel_values
+    pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values
     pixel_values = pixel_values.to(device)
 
     output_ids = model.generate(pixel_values, **gen_kwargs)
 
     preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
     return preds
-