aehrc
/

cxrmate-rrg24

Feature Extraction

vision-encoder-decoder

Model card Files Files and versions Community

anicolson commited on May 16

Commit

858d464

•

1 Parent(s): 7c82fd0

Update README.md

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -42,9 +42,11 @@ transforms = v2.Compose(
         v2.Normalize(mean=model.config.encoder.image_mean, std=model.config.encoder.image_std),
     ]
 )
-image = transforms(image)
 output_ids = model.generate(
-    pixel_values=images,
     max_length=512,
     bad_words_ids=[[tokenizer.convert_tokens_to_ids('[NF]')], [tokenizer.convert_tokens_to_ids('[NI]')]],
     num_beams=4,

         v2.Normalize(mean=model.config.encoder.image_mean, std=model.config.encoder.image_std),
     ]
 )
+image = transforms(image)  # Fix.
 output_ids = model.generate(
+    pixel_values=images,  # Fix.
     max_length=512,
     bad_words_ids=[[tokenizer.convert_tokens_to_ids('[NF]')], [tokenizer.convert_tokens_to_ids('[NI]')]],
     num_beams=4,