Update main.py

main.py

@@ -43,6 +43,7 @@ def generate_caption(processor, model, image, tokenizer=None):
    
     return generated_caption
 
+
 def generate_captions(image):
     caption_git_base = generate_caption(git_processor_base, git_model_base, image)
 
@@ -56,56 +57,21 @@ def generate_captions(image):
 
     return caption_git_base, caption_git_large, caption_blip_base, caption_blip_large, caption_vitgpt
 
-examples = [["cat.jpg"], ["dog.jpg"], ["horse.jpg"]]
-outputs = [gr.outputs.Textbox(label="Caption generated by GIT-base"), gr.outputs.Textbox(label="Caption generated by GIT-large"), gr.outputs.Textbox(label="Caption generated by BLIP-base"), gr.outputs.Textbox(label="Caption generated by BLIP-large"), gr.outputs.Textbox(label="Caption generated by ViT+GPT-2")]
+   
+#examples = [["cats.jpg"], ["stop_sign.png"], ["astronaut.jpg"]]
+outputs = [gr.outputs.Textbox(label="Caption generated by GIT-base"), gr.outputs.Textbox(label="Caption generated by GIT-large"), gr.outputs.Textbox(label="Caption generated by BLIP-base"), gr.outputs.Textbox(label="Caption generated by BLIP-large"), gr.outputs.Textbox(label="Caption generated by ViT+GPT-2")] 
 
 title = "Interactive demo: comparing image captioning models"
 description = "Gradio Demo to compare GIT, BLIP and ViT+GPT2, 3 state-of-the-art vision+language models. To use it, simply upload your image and click 'submit', or click one of the examples to load them. Read more at the links below."
 article = "<p style='text-align: center'><a href='https://huggingface.co/docs/transformers/main/model_doc/blip' target='_blank'>BLIP docs</a> | <a href='https://huggingface.co/docs/transformers/main/model_doc/git' target='_blank'>GIT docs</a></p>"
 
-css = """
-body {
-    background-color: #f2f2f2;
-    font-family: Arial, sans-serif;
-}
-
-.title {
-    color: #333333;
-    font-size: 24px;
-    font-weight: bold;
-    margin-bottom: 20px;
-}
-
-.description {
-    color: #666666;
-    font-size: 16px;
-    margin-bottom: 20px;
-}
-
-.article {
-    color: #666666;
-    font-size: 14px;
-    margin-bottom: 20px;
-    text-align: center;
-}
-
-.input {
-    margin-bottom: 20px;
-}
-
-.output {
-    margin-bottom: 20px;
-}
-"""
-
-iface = gr.Interface(fn=generate_captions,
+iface = gr.Interface(fn=generate_captions, 
                          inputs=gr.inputs.Image(type="pil"),
                          outputs=outputs,
-                         examples=examples,
+                         examples=examples, 
                          title=title,
                          description=description,
-                         article=article,
-                         css=css,
+                         article=article, 
                          enable_queue=True)
 iface.launch(server_name="0.0.0.0", server_port=7860)