clean code

app.py

@@ -23,22 +23,6 @@ model = blip_decoder(pretrained=model_url, image_size=384, vit='large')
 model.eval()
 model = model.to(device)
 
-
-from models.blip_vqa import blip_vqa
-
-image_size_vq = 480
-transform_vq = transforms.Compose([
-    transforms.Resize((image_size_vq,image_size_vq),interpolation=InterpolationMode.BICUBIC),
-    transforms.ToTensor(),
-    transforms.Normalize((0.48145466, 0.4578275, 0.40821073), (0.26862954, 0.26130258, 0.27577711))
-    ]) 
-
-model_url_vq = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model*_vqa.pth'
-    
-model_vq = blip_vqa(pretrained=model_url_vq, image_size=480, vit='base')
-model_vq.eval()
-model_vq = model_vq.to(device)
-
 def inference_image_caption(raw_image):
     image = transform(raw_image).unsqueeze(0).to(device)   
     with torch.no_grad():