Update README.md

fix "device" and "pixel_values" not defined

README.md

@@ -42,9 +42,9 @@ inferred_token = [text]
 with torch.no_grad():
     for i in range(tl):
         encoded = processor.tokenizer(inferred_token)
-        input_ids = torch.tensor(encoded.input_ids).to(device)
+        input_ids = torch.tensor(encoded.input_ids)
         encoded = encoded["input_ids"][0][1:-1]
-        outputs = model(input_ids=input_ids, pixel_values=pixel_values)
+        outputs = model(input_ids=input_ids, pixel_values=encoding.pixel_values)
         mlm_logits = outputs.logits[0]  # shape (seq_len, vocab_size)
         # only take into account text features (minus CLS and SEP token)
         mlm_logits = mlm_logits[1 : input_ids.shape[1] - 1, :]