Update README.md

README.md

@@ -28,6 +28,15 @@ This code reads data from .txt files where each line contains the paths for imag
 
 Then update the train/val/test list paths in the config files.
 
+#### [Update] We have uploaded the lists we use in our paper.
++ The train/val lists for COCO contains 82081 and 40137 images respectively. They are generated by the default scripts provided by COCO.
++ The train/val lists for PASCAL5i contains 5953 and 1449 images respectively. The train list should be **voc_sbd_merge_noduplicate.txt** and the val list is the original val list of pascal voc (**val_fixed.txt**).
++ We do not use the augmented images of voc as the training data.
+
+##### To get voc_sbd_merge_noduplicate.txt:
++ we first merge the original VOC (voc_original_train.txt) and SBD (sbd_data.txt) training data. 
++ The merged list (voc_sbd_merge.txt) is then processed by the script (duplicate_removel.py) to remove the duplicate images and labels.
+
 ### Run Demo / Test with Pretrained Models
 + Please download the pretrained models.
 + We provide **8 pre-trained models**: 4 ResNet-50 based [**models**](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155122171_link_cuhk_edu_hk/EW20i_eiTINDgJDqUqikNR4Bo-7kVFkLBkxGZ2_uorOJcw?e=4%3aSIRlwD&at=9) for PASCAL-5i and 4 VGG-16 based [**models**](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155122171_link_cuhk_edu_hk/EYS498D4TOZMtIb3WbQDGSQBsqxJHLSiMEAa49Iym0NO0A?e=4%3apRTPnj&at=9) for COCO.