Update README.md

README.md

@@ -89,7 +89,7 @@ inputs = processor(text='Find me an everyday image that matches the given captio
 qry_output = last_pooling(model(**inputs, return_dict=True, output_hidden_states=True).hidden_states[-1], inputs['attention_mask'])
 
 string = '<|image|><|begin_of_text|> Represent the given image.'
-tgt_inputs = processor(text=string, images=[Image.open('figures/example.jpg')], return_tensors="pt").to("cuda")
+tgt_inputs = processor(text=string, images=[image], return_tensors="pt").to("cuda")
 tgt_output = last_pooling(model(**tgt_inputs, return_dict=True, output_hidden_states=True).hidden_states[-1], tgt_inputs['attention_mask'])
 print(string, '=', compute_similarity(qry_output, tgt_output))
 ## <|image|><|begin_of_text|> Represent the given image. = tensor([[0.4219]], device='cuda:0', dtype=torch.bfloat16)
@@ -97,7 +97,7 @@ print(string, '=', compute_similarity(qry_output, tgt_output))
 inputs = processor(text='Find me an everyday image that matches the given caption: A cat and a tiger.', return_tensors="pt").to("cuda")
 qry_output = last_pooling(model(**inputs, return_dict=True, output_hidden_states=True).hidden_states[-1], inputs['attention_mask'])
 string = '<|image|><|begin_of_text|> Represent the given image.'
-tgt_inputs = processor(text=string, images=[Image.open('figures/example.jpg')], return_tensors="pt").to("cuda")
+tgt_inputs = processor(text=string, images=[image], return_tensors="pt").to("cuda")
 tgt_output = last_pooling(model(**tgt_inputs, return_dict=True, output_hidden_states=True).hidden_states[-1], tgt_inputs['attention_mask'])
 print(string, '=', compute_similarity(qry_output, tgt_output))
 ## <|image|><|begin_of_text|> Represent the given image. = tensor([[0.3887]], device='cuda:0', dtype=torch.bfloat16)