added git-base-coco model

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-from transformers import AutoProcessor, BlipForConditionalGeneration
+from transformers import AutoProcessor, BlipForConditionalGeneration, AutoModelForCausalLM
 
 # from transformers import AutoProcessor, AutoTokenizer, AutoImageProcessor, AutoModelForCausalLM, BlipForConditionalGeneration, Blip2ForConditionalGeneration, VisionEncoderDecoderModel
 import torch
@@ -11,8 +11,8 @@ torch.hub.download_url_to_file('http://images.cocodataset.org/val2017/0000000397
 torch.hub.download_url_to_file('https://huggingface.co/datasets/nielsr/textcaps-sample/resolve/main/stop_sign.png', 'stop_sign.png')
 torch.hub.download_url_to_file('https://cdn.openai.com/dall-e-2/demos/text2im/astronaut/horse/photo/0.jpg', 'astronaut.jpg')
 
-# git_processor_base = AutoProcessor.from_pretrained("microsoft/git-base-coco")
-# git_model_base = AutoModelForCausalLM.from_pretrained("microsoft/git-base-coco")
+git_processor_base = AutoProcessor.from_pretrained("microsoft/git-base-coco")
+git_model_base = AutoModelForCausalLM.from_pretrained("microsoft/git-base-coco")
 
 # git_processor_large_coco = AutoProcessor.from_pretrained("microsoft/git-large-coco")
 # git_model_large_coco = AutoModelForCausalLM.from_pretrained("microsoft/git-large-coco")
@@ -76,7 +76,7 @@ def generate_caption_coca(model, transform, image):
 
 
 def generate_captions(image):
-    # caption_git_base = generate_caption(git_processor_base, git_model_base, image)
+    caption_git_base = generate_caption(git_processor_base, git_model_base, image)
 
     # caption_git_large_coco = generate_caption(git_processor_large_coco, git_model_large_coco, image)
 
@@ -101,7 +101,7 @@ def generate_captions(image):
    
 examples = [["cats.jpg"], ["stop_sign.png"], ["astronaut.jpg"]]
 # outputs = [gr.outputs.Textbox(label="Caption generated by GIT-large fine-tuned on COCO"), gr.outputs.Textbox(label="Caption generated by GIT-large fine-tuned on TextCaps"), gr.outputs.Textbox(label="Caption generated by BLIP-large"), gr.outputs.Textbox(label="Caption generated by CoCa"), gr.outputs.Textbox(label="Caption generated by BLIP-2 OPT 6.7b")] 
-outputs = [gr.outputs.Textbox(label="Caption generated by BLIP-base"),] 
+outputs = [gr.outputs.Textbox(label="Caption generated by GIT-base fine-tuned on COCO"), gr.outputs.Textbox(label="Caption generated by BLIP-base")] 
 
 title = "Interactive demo: comparing image captioning models"
 description = "Gradio Demo to compare GIT, BLIP, CoCa, and BLIP-2, 4 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."