Update app.py

app.py

@@ -3,9 +3,9 @@ import requests
 from PIL import Image
 from transformers import BlipProcessor, BlipForConditionalGeneration
 import gradio as gr
-
+device="cpu"
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
-model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base", torch_dtype=torch.float16).to("cuda")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base", torch_dtype=torch.float16).to(device)
 
 # Function to process the image and generate captions
 def generate_caption(image, caption_type, text):
@@ -20,14 +20,14 @@ def generate_caption(image, caption_type, text):
 
 # Conditional image captioning
 def conditional_image_captioning(raw_image, text):
-    inputs = processor(raw_image, text, return_tensors="pt").to("cuda", torch.float16)
+    inputs = processor(raw_image, text, return_tensors="pt").to(device, torch.float16)
     out = model.generate(**inputs)
     caption = processor.decode(out[0], skip_special_tokens=True)
     return caption
 
 # Unconditional image captioning
 def unconditional_image_captioning(raw_image):
-    inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16)
+    inputs = processor(raw_image, return_tensors="pt").to(device, torch.float16)
     out = model.generate(**inputs)
     caption = processor.decode(out[0], skip_special_tokens=True)
     return caption