[Reimplementation] After the SODA-A dataset is split, there is a lot of JSON data of annotations in the train. Do they need to be integrated? - Githubissues

shaunyuan22 / CFINet

The official implementation for ICCV'23 paper "Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning"

Apache License 2.0

132 stars 7 forks source link

[Reimplementation] After the SODA-A dataset is split, there is a lot of JSON data of annotations in the train. Do they need to be integrated? #38

Open 1339630594 opened 2 months ago

1339630594 commented 2 months ago

Prerequisite

[X] I have searched Issues and Discussions but cannot get the expected help.
[X] I have read the FAQ documentation but cannot get the expected help.
[X] The bug has not been fixed in the latest version (master) or latest version (3.x).

💬 Describe the reimplementation questions

After the SODA-A dataset is split, there is a lot of JSON data of annotations in the train. Do they need to be integrated?

Environment

pip install pytorch

Expected results

No response

Additional information

No response

shaunyuan22 commented 2 months ago

nope, please refer to here for data preparation of SODA-A dataset.