yjh0410 3da5d6bb53 update		2 yıl önce
..
README.md	3da5d6bb53 update	2 yıl önce
build.py	73011ee555 debug YOLOX-style Transform with Rotation	2 yıl önce
loss.py	efa0bed448 debug YOLOX-style Transform with Rotation	2 yıl önce
matcher.py	2727b6adb1 debug trainer	2 yıl önce
yolox.py	73011ee555 debug YOLOX-style Transform with Rotation	2 yıl önce
yolox_backbone.py	8f4509bd61 modify YOLOX	2 yıl önce
yolox_basic.py	3246f3efdd update	2 yıl önce
yolox_head.py	311a9b89b7 fix a unknown bug in YOLOX	2 yıl önce
yolox_neck.py	8f4509bd61 modify YOLOX	2 yıl önce
yolox_pafpn.py	3246f3efdd update	2 yıl önce

YOLOX:

For training, we train YOLOX series with 300 epochs on COCO.
For data augmentation, we use the large scale jitter (LSJ), Mosaic augmentation and Mixup augmentation.
For optimizer, we use SGD with weight decay 0.0005 and base per image lr 0.01 / 64,.
For learning rate scheduler, we use Cosine decay scheduler.
I am trying to retrain YOLOX-M and YOLOX-L with more GPUs, and I will update the AP of YOLOX-M and YOLOX-L in the table in the future.

Model	Backbone	Batch	Scale	AP^val 0.5:0.95	AP^val 0.5	FLOPs ^(G)	Params ^(M)	Weight
YOLOX-N	CSPDarkNet-N	8xb8	640	30.4	48.9	7.5	2.3	ckpt
YOLOX-S	CSPDarkNet-S	8xb8	640	39.0	58.8	26.8	8.9	ckpt
YOLOX-M	CSPDarkNet-M	8xb8	640	44.6	63.8	74.3	25.4	ckpt
YOLOX-L	CSPDarkNet-L	8xb8	640	48.7	68.0	155.4	54.2	ckpt