| Model |
Batch |
Scale |
APval
0.5:0.95
| APval
0.5
| FLOPs
(G)
| Params
(M)
| Weight |
| YOLOX2-N |
8xb16 |
640 |
|
|
|
|
|
| YOLOX2-T |
8xb16 |
640 |
|
|
|
|
|
| YOLOX2-S |
8xb16 |
640 |
|
|
|
|
|
| YOLOX2-M |
8xb16 |
640 |
|
|
|
|
|
| YOLOX2-L |
8xb16 |
640 |
|
|
|
|
|
| YOLOX2-X |
8xb16 |
640 |
|
|
|
|
|
| <!-- |
YOLOX2-S |
8xb16 |
640 |
42.0 |
60.2 |
27.6 |
9.2 |
- For training, we train YOLOX2 series with 300 epochs on COCO.
- For data augmentation, we use the large scale jitter (LSJ), Mosaic augmentation and Mixup augmentation, following the YOLOX.
- For optimizer, we use AdamW with weight decay 0.05 and base per image lr 0.001 / 64,.
- For learning rate scheduler, we use Linear decay scheduler.
Train YOLOX2
Single GPU
Taking training YOLOX2-S on COCO as the example,
python train.py --cuda -d coco --root path/to/coco -m yolox2_s -bs 16 -size 640 --wp_epoch 3 --max_epoch 300 --eval_epoch 10 --no_aug_epoch 20 --ema --fp16 --multi_scale
Multi GPU
Taking training YOLOX2-S on COCO as the example,
python -m torch.distributed.run --nproc_per_node=8 train.py --cuda -dist -d coco --root /data/datasets/ -m yolox2_s -bs 128 -size 640 --wp_epoch 3 --max_epoch 300 --eval_epoch 10 --no_aug_epoch 20 --ema --fp16 --sybn --multi_scale --save_folder weights/
Test YOLOX2
Taking testing YOLOX2-S on COCO-val as the example,
python test.py --cuda -d coco --root path/to/coco -m yolox2_s --weight path/to/yolox2_s.pth -size 640 -vt 0.4 --show
Evaluate YOLOX2
Taking evaluating YOLOX2-S on COCO-val as the example,
python eval.py --cuda -d coco-val --root path/to/coco -m yolox2_s --weight path/to/yolox2_s.pth
Demo
Detect with Image
python demo.py --mode image --path_to_img path/to/image_dirs/ --cuda -m yolox2_s --weight path/to/weight -size 640 -vt 0.4 --show
Detect with Video
python demo.py --mode video --path_to_vid path/to/video --cuda -m yolox2_s --weight path/to/weight -size 640 -vt 0.4 --show --gif
Detect with Camera
python demo.py --mode camera --cuda -m yolox2_s --weight path/to/weight -size 640 -vt 0.4 --show --gif
