modify README

README.md

@@ -87,13 +87,6 @@ For example:
 python train.py --cuda -d coco --root path/to/COCO -m yolov1 -bs 16 --max_epoch 150 --wp_epoch 1 --eval_epoch 10 --fp16 --ema --multi_scale
 ```
 
-#### Redesigned YOLOv1~v2:
-
-| Model  |  Backbone  | Batch | Scale | Epoch | AP<sup>val<br>0.5:0.95 | AP<sup>val<br>0.5 | FLOPs<br><sup>(G) | Params<br><sup>(M) | Weight |
-|--------|------------|-------|-------|-------|------------------------|-------------------|-------------------|--------------------|--------|
-| YOLOv1 | ResNet-18  | 1xb16 |  640  |  150  |        27.9            |       47.5        |   37.8            |   21.3             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolov1_coco.pth) |
-| YOLOv2 | DarkNet-19 | 1xb16 |  640  |  150  |        32.7            |       50.9        |   53.9            |   30.9             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolov2_coco.pth) |
-
 #### YOLOv3:
 
 | Model       |  Backbone    | Batch | Scale | Epoch | AP<sup>val<br>0.5:0.95 | AP<sup>val<br>0.5 | FLOPs<br><sup>(G) | Params<br><sup>(M) | Weight |
@@ -124,8 +117,8 @@ python train.py --cuda -d coco --root path/to/COCO -m yolov1 -bs 16 --max_epoch
 | Model   |   Backbone    | Batch | Scale | Epoch | AP<sup>val<br>0.5:0.95 | AP<sup>val<br>0.5 | FLOPs<br><sup>(G) | Params<br><sup>(M) | Weight |
 |---------|---------------|-------|-------|-------|------------------------|-------------------|-------------------|--------------------|--------|
 | YOLOX-N | CSPDarkNet-N  | 8xb8  |  640  |  300  |         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  |  300  |         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  | 1xb16 |  300  |         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-S | CSPDarkNet-S  | 8xb8  |  640  |  300  |         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  | 1xb16 |  640  |  300  |         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-L | CSPDarkNet-L  | 1xb16 |  640  |  300  |         46.9           |       65.9        |   155.4           |   54.2             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolox_l_coco.pth) |
 
 *For **YOLOX-M** and **YOLOX-L**, increasing the batch size may improve performance. Due to my computing resources, I can only set the batch size to 16.*

models/detectors/yolov1/README.md

@@ -0,0 +1,10 @@
+# Redesigned YOLOv1:
+
+| Model  |  Backbone  | Batch | Scale | AP<sup>val<br>0.5:0.95 | AP<sup>val<br>0.5 | FLOPs<br><sup>(G) | Params<br><sup>(M) | Weight |
+|--------|------------|-------|-------|------------------------|-------------------|-------------------|--------------------|--------|
+| YOLOv1 | ResNet-18  | 1xb16 |  640  |        27.9            |       47.5        |   37.8            |   21.3             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolov1_coco.pth) |
+
+- For training, we train redesigned YOLOv1 with 150 epochs on COCO.
+- For data augmentation, we only use the large scale jitter (LSJ), no Mosaic or Mixup augmentation.
+- For optimizer, we use SGD with momentum 0.937, weight decay 0.0005 and base lr 0.01.
+- For learning rate scheduler, we use linear decay scheduler.

models/detectors/yolov2/README.md

@@ -0,0 +1,10 @@
+# Redesigned YOLOv2:
+
+| Model  |  Backbone  | Batch | Scale | AP<sup>val<br>0.5:0.95 | AP<sup>val<br>0.5 | FLOPs<br><sup>(G) | Params<br><sup>(M) | Weight |
+|--------|------------|-------|-------|------------------------|-------------------|-------------------|--------------------|--------|
+| YOLOv2 | DarkNet-19 | 1xb16 |  640  |        32.7            |       50.9        |   53.9            |   30.9             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolov2_coco.pth) |
+
+- For training, we train redesigned YOLOv2 with 150 epochs on COCO.
+- For data augmentation, we only use the large scale jitter (LSJ), no Mosaic or Mixup augmentation.
+- For optimizer, we use SGD with momentum 0.937, weight decay 0.0005 and base lr 0.01.
+- For learning rate scheduler, we use linear decay scheduler.