Update README.md

README.md

@@ -169,7 +169,7 @@ Below we provide methods for pretraining OFA.
             <li><b>vision_language_examples.tsv</b>:
     Each line contains uniq-id, image (base64 string), caption, question, answer, ground-truth objects (objects appearing in the caption or question), dataset name (source of the data) and task type (caption, qa or visual gronunding). Prepared for the pretraining tasks of visual grounding, grounded captioning, image-text matching, image captioning and visual question answering. </li>
             <li><b>text_examples.tsv</b>: Each line contains uniq-id and text. Prepared for the pretraining task of text infilling. </li> 
-            <li><b>image_examples.tsv</b>: Each line contains uniq-id, image (base64 string) and image-code (generated by VQ-GAN). Prepared for the pretraining task of image infilling. </li>
+            <li><b>image_examples.tsv</b>: Each line contains uniq-id, image (base64 string, should be resized to 256*256 resolution) and image-code (generate the sparse codes for the central part of image through VQ-GAN). Prepared for the pretraining task of image infilling. </li>
             <li><b>detection_examples.tsv</b>: Each line contains uniq-id, image (base64 string) and bounding box annotations (contains the top-left and bottom-right coordinates of the bounding box, object_id and object_name, seperated by commas). Prepared for the pretraining task of detection. </li>
         </ul>
         In addition, the folder negative_sample in pretrain_data_examples.zip contains three files <code>all_captions.txt</code>, <code>object.txt</code> and <code>type2ans.json</code>. The data in these files are used as negative samples for the image-text matching (ITM) task.