fix

README.md

@@ -87,10 +87,10 @@ image_path = "CLIP.png"
 
 image = Image.open(image_path)
 input_pixels = processor(images=image, return_tensors="pt").pixel_values.to('cuda')
+text_features = l2v.encode(captions, convert_to_tensor=True).to('cuda')
 
 with torch.no_grad(), torch.cuda.amp.autocast():
     image_features = model.get_image_features(input_pixels)
-    text_features = l2v.encode(captions, convert_to_tensor=True).to('cuda')
     text_features = model.get_text_features(text_features)
 
     image_features /= image_features.norm(dim=-1, keepdim=True)