Went-Liang / UnSniffer

[CVPR 2023] Official Pytorch code for Unknown Sniffer for Object Detection: Don’t Turn a Blind Eye to Unknown Objects
https://arxiv.org/pdf/2303.13769v1.pdf
Apache License 2.0
67 stars 9 forks source link

How to set Dataset? #4

Open jinweiisgreat opened 1 year ago

jinweiisgreat commented 1 year ago

Hi, Thank you for your work. I am confused with the dataset setting. where is VOC_0712_converted? and the data_root name is data? like:

data └── VOC0712 | ├── JPEGImages ├── voc0712_train_all.json ├── voc0712_train_completely_annotation200.json └── val_coco_format.json

└── COCO2017 | ├── annotations ├── xxx (the original json files) ├── instances_val2017_coco_ood.json ├── instances_val2017_mixed_ID.json └── instances_val2017_mixed_OOD.json ├── train2017 └── val2017

Should I download both VOC2007 and VOC2012, and extract JPEGImages and Annotations files into VOC0712 ?

Went-Liang commented 1 year ago

Thank you for your attention. I have addressed the issues with the readme and scripts. I apologize for any inconvenience caused. You can download the dataset from the following link: https://drive.google.com/file/d/1n9C4CiBURMSCZy2LStBQTzR17rD_a67e/view?usp=sharing