Update README.md

README.md

@@ -99,6 +99,11 @@ The data from our multi-level description generation method is now open-sourced
     <img src="images/detailed_caption.png" width="1000"/>
 <p>
 <br>
+You can download train images from [Train](https://pan.baidu.com/s/1svSjXTxWpI-3boALgSeLlw). Extraction code: 4hdh
+
+You can download test images and jsonls from [Test](https://pan.baidu.com/s/1ABrQKeE9QBeKvtGzXfM8Eg). Extraction code: 5h71
+
+The images are from CC3M, COCO Caption, TextCaps, VQAV2, OKVQA, GQA, ScienceQA, VizWiz, TextVQA, OCRVQA, ESTVQA, STVQA, AI2D and DUE_Benchmark. These data are for academic purposes only. When using the data, it is necessary to comply with the protocols of the original dataset.
 
 ## Evaluate
 
@@ -141,13 +146,6 @@ ds_collections = {
 bash eval/eval.sh 'EVAL_PTH' 'SAVE_NAME'
 ```
 
-You can download train images from [Train](https://pan.baidu.com/s/1svSjXTxWpI-3boALgSeLlw). Extraction code: 4hdh
-
-You can download test images and jsonls from [Test](https://pan.baidu.com/s/1ABrQKeE9QBeKvtGzXfM8Eg). Extraction code: 5h71
-
-The images are from CC3M, COCO Caption, TextCaps, VQAV2, OKVQA, GQA, ScienceQA, VizWiz, TextVQA, OCRVQA, ESTVQA, STVQA, AI2D and DUE_Benchmark. These data are for academic purposes only. When using the data, it is necessary to comply with the protocols of the original dataset.
-
-
 ## Train
 
 We also offer Monkey's model definition and training code, which you can explore above. You can execute the training code through executing `finetune_ds_debug.sh`.