Davis - Final submission

app.py

@@ -1,39 +1,57 @@
-import torch
-import gradio as gr
-from transformers import BlipProcessor, BlipForQuestionAnswering
+# -*- coding: utf-8 -*-
+"""App_Travis_Davis.ipynb
 
-model_name = "Salesforce/blip-vqa-base"
+Automatically generated by Colab.
 
-processor = BlipProcessor.from_pretrained(model_name)
-model = BlipForQuestionAnswering.from_pretrained(model_name)
+Original file is located at
+    https://colab.research.google.com/drive/1TYz_SpHIzdYoqG_5OfIbIohXmcZTo77j
+"""
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model.to(device)
+import torch
+from transformers import pipeline
+import gradio as gr
 
+# Load BLIP VQA pipeline
+if torch.cuda.is_available():
+    vqa = pipeline(
+        task="visual-question-answering",
+        model="Salesforce/blip-vqa-base",
+        torch_dtype=torch.float16,
+        device=0,
+        use_fast=False,)
+else:
+    vqa = pipeline(
+        task="visual-question-answering",
+        model="Salesforce/blip-vqa-base",
+        device=-1,
+        use_fast=False,)
+
+# Function to answer questions about uploaded images
 def answer_question(image, question):
     if image is None:
         return "Please upload an image."
+
     if not question:
         return "Please type a question about the image."
 
-    inputs = processor(image, question, return_tensors="pt").to(device)
-
-    with torch.no_grad():
-        output = model.generate(**inputs, max_new_tokens=20)
+    # Run Visual Question Answering pipeline
+    result = vqa(question=question, image=image)
 
-    answer = processor.decode(output[0], skip_special_tokens=True)
-    return answer
+    # Return generated answer
+    return result[0]["answer"]
 
+# Build Gradio interface
 demo = gr.Interface(
     fn=answer_question,
     inputs=[
         gr.Image(type="pil", label="Upload an image"),
-        gr.Textbox(label="Question", placeholder="e.g. What animal is this?"),
-    ],
+        gr.Textbox(
+            label="Question",
+            placeholder="Example: What is in this image?"),],
     outputs=gr.Textbox(label="Answer"),
     title="BLIP Visual Question Answering",
-    description="Ask a question about an uploaded image using Salesforce/blip-vqa-base.",
-)
+    description="Upload an image and ask a question about it using Salesforce/blip-vqa-base.",)
 
+# Launch application
 if __name__ == "__main__":
     demo.launch()