Update app.py

app.py

@@ -21,21 +21,6 @@ vit_feature_extractor = ViTImageProcessor.from_pretrained("nlpconnect/vit-gpt2-i
 
 tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
 
-#url = 'https://d2gp644kobdlm6.cloudfront.net/wp-content/uploads/2016/06/bigstock-Shocked-and-surprised-boy-on-t-113798588-300x212.jpg'
-
-#with Image.open(requests.get(url, stream=True).raw) as img:
- #    pixel_values = vit_feature_extractor(images=img, return_tensors="pt").pixel_values
-
-#encoder_outputs = model.generate(pixel_values.to('cpu'),num_beams=5)
-
-#generated_sentences = tokenizer.batch_decode(encoder_outputs, skip_special_tokens=True)
-
-#generated_sentences
-
-#naive text processing 
-#generated_sentences[0].split('.')[0]
-
-# inference function
 
 def vit2distilgpt2(img):
   pixel_values = vit_feature_extractor(images=img, return_tensors="pt").pixel_values
@@ -44,7 +29,6 @@ def vit2distilgpt2(img):
 
   return(generated_sentences[0].split('.')[0])
 
-#!wget https://media.glamour.com/photos/5f171c4fd35176eaedb36823/master/w_2560%2Cc_limit/bike.jpg
 
 import gradio as gr
 
@@ -56,11 +40,11 @@ outputs = [
     gr.outputs.Textbox(label = 'Caption')
 ]
 
-title = "Image Captioning using ViT + GPT2 + nlpconnect"
+title = "Image Captioning with Visual Transformer using nlpconnect"
 description = "ViT and GPT2 are used to generate Image Caption for the uploaded image. COCO Dataset was used for training."
 article = " <a href='https://huggingface.co/nlpconnect/vit-gpt2-image-captioning'>Model Repo on Hugging Face Model Hub</a>"
 examples = [
-    ["people-walking-street-pedestrian-crossing-traffic-light-city.jpeg"],
+    ["Img_3.jpg"],
     ["Img_1.jpg"],
     ["Img_2.jpg"]
 ]