retrain YOLOX-S

models/detectors/yolox/README.md

@@ -4,7 +4,7 @@
 |---------|--------------|-------|-------|------------------------|-------------------|-------------------|--------------------|--------|
 | YOLOX-N | CSPDarkNet-N | 8xb8  |  640  |         30.4           |       48.9        |   7.5             |   2.3              | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolox_n_coco.pth) |
 | YOLOX-S | CSPDarkNet-S | 8xb8  |  640  |         39.0           |       58.8        |   26.8            |   8.9              | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolox_s_coco.pth) |
-| YOLOX-M | CSPDarkNet-M | 8xb8 |  640  |         44.6           |       63.8        |   74.3            |   25.4             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolox_m_coco.pth) |
+| YOLOX-M | CSPDarkNet-M | 8xb8 |  640  |         46.2           |       66.0        |   74.3            |   25.4             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolox_m_coco.pth) |
 | YOLOX-L | CSPDarkNet-L | 8xb8 |  640  |         48.7           |       68.0        |   155.4           |   54.2             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolox_l_coco.pth) |
 
 - For training, we train YOLOX series with 300 epochs on COCO.

train_multi_gpus.sh

@@ -4,7 +4,7 @@ python -m torch.distributed.run --nproc_per_node=8 train.py \
                                                     -dist \
                                                     -d coco \
                                                     --root /data/datasets/ \
-                                                    -m yolox_m\
+                                                    -m yolox_s\
                                                     -bs 64 \
                                                     -size 640 \
                                                     --wp_epoch 3 \

train_single_gpu.sh

@@ -3,7 +3,7 @@ python train.py \
         --cuda \
         -d coco \
         --root /mnt/share/ssd2/dataset/ \
-        -m yolox_l \
+        -m yolox_s \
         -bs 8 \
         -size 640 \
         --wp_epoch 3 \