train YOLOX-N on COCO

README.md

@@ -129,7 +129,7 @@ I have provided a bash file `train_ddp.sh` that enables DDP training. I hope som
 |---------------|--------------------|-------|-------|------------------------|-------------------|-------------------|--------------------|--------|
 | YOLOv5-N      | CSPDarkNet-N       |  640  |  250  |         29.8           |       47.1        |   7.7             |   2.4              | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolov5_n_coco.pth) |
 | YOLOv5-S      | CSPDarkNet-S       |  640  |  250  |         37.8           |       56.5        |   27.1            |   9.0              | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolov5_s_coco.pth) |
-| YOLOv5-M      | CSPDarkNet-M       |  640  |  250  |                        |                   |   74.3            |   25.4             |  |
+| YOLOv5-M      | CSPDarkNet-M       |  640  |  250  |         43.5           |       62.5        |   74.3            |   25.4             |  |
 | YOLOv5-L      | CSPDarkNet-L       |  640  |  250  |         46.7           |       65.5        |   155.6           |   54.2             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolov5_l_coco.pth) |
 
 *For **YOLOv5-L**, increasing the batch size may improve performance. Due to my computing resources, I can only set the batch size to 16.*

config/yolox_config.py

@@ -43,7 +43,7 @@ yolox_cfg = {
         'loss_box_weight': 5.0,
         # ---------------- Train config ----------------
         ## close strong augmentation
-        'no_aug_epoch': 20,
+        'no_aug_epoch': 10,
         ## optimizer
         'optimizer': 'sgd',        # optional: sgd, AdamW
         'momentum': 0.937,         # SGD: 0.937;    AdamW: None
@@ -101,7 +101,7 @@ yolox_cfg = {
         'loss_box_weight': 5.0,
         # ---------------- Train config ----------------
         ## close strong augmentation
-        'no_aug_epoch': 20,
+        'no_aug_epoch': 10,
         ## optimizer
         'optimizer': 'sgd',        # optional: sgd, AdamW
         'momentum': 0.937,         # SGD: 0.937;    AdamW: None
@@ -159,7 +159,7 @@ yolox_cfg = {
         'loss_box_weight': 5.0,
         # ---------------- Train config ----------------
         ## close strong augmentation
-        'no_aug_epoch': 20,
+        'no_aug_epoch': 10,
         ## optimizer
         'optimizer': 'sgd',        # optional: sgd, AdamW
         'momentum': 0.937,         # SGD: 0.937;    AdamW: None
@@ -217,7 +217,7 @@ yolox_cfg = {
         'loss_box_weight': 5.0,
         # ---------------- Train config ----------------
         ## close strong augmentation
-        'no_aug_epoch': 20,
+        'no_aug_epoch': 10,
         ## optimizer
         'optimizer': 'sgd',        # optional: sgd, AdamW
         'momentum': 0.937,         # SGD: 0.937;    AdamW: None
@@ -275,7 +275,7 @@ yolox_cfg = {
         'loss_box_weight': 5.0,
         # ---------------- Train config ----------------
         ## close strong augmentation
-        'no_aug_epoch': 20,
+        'no_aug_epoch': 10,
         ## optimizer
         'optimizer': 'sgd',        # optional: sgd, AdamW
         'momentum': 0.937,         # SGD: 0.937;    AdamW: None