This repository is an official implementation of the ICCV 2021 paper "Conditional DETR for Fast Training Convergence". (https://arxiv.org/abs/2108.06152)
Apache License 2.0
358
stars
48
forks
source link
How to finetune ConditionalDETR on custom dataset? #7
Sorry for the late reply.
you need to prepare your custom dataset to COCO format, and then you can replace the coco-path, and the annotation file path https://github.com/Atten4Vis/ConditionalDETR/blob/0b04a859c7fac33a866fcdea06f338610ba6e9d8/datasets/coco.py#L159 with your own.