update README

README.md

@@ -97,6 +97,7 @@ For example:
 ```Shell
 python train.py --cuda -d coco --root path/to/COCO -v yolov1 -bs 16 --max_epoch 150 --wp_epoch 1 --eval_epoch 10 --fp16 --ema --multi_scale
 ```
+* Detectors reproduced in my book
 
 | Model         |   Backbone         | Scale | Epoch |  FPS  | AP<sup>val<br>0.5:0.95 | AP<sup>val<br>0.5 | FLOPs<br><sup>(G) | Params<br><sup>(M) | Weight |
 |---------------|--------------------|-------|-------|-------|------------------------|-------------------|-------------------|--------------------|--------|
@@ -104,17 +105,24 @@ python train.py --cuda -d coco --root path/to/COCO -v yolov1 -bs 16 --max_epoch
 | YOLOv2        | DarkNet-19         |  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        | DarkNet-53         |  640  |  250  |       |        42.9            |       63.5        |   167.4           |   54.9             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolov3_coco.pth) |
 | YOLOv4        | CSPDarkNet-53      |  640  |  250  |       |        46.6            |       65.8        |   162.7           |   61.5             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolov4_coco.pth) |
+| YOLOX-L       | CSPDarkNet-L       |  640  |  300  |       |        46.6            |       66.1        |   155.4           |   54.2             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolox_coco.pth) |
+| YOLOv7-Tiny   | ELANNet-Tiny       |  640  |  300  |       |                        |                   |   22.9            |   8.1              |  |
+| YOLOv7-Large  | ELANNet-Large      |  640  |  300  |       |                        |                   |   144.6           |   44.0             |  |
+
+* Reproduced YOLOv5:
+
+| Model         |   Backbone         | Scale | Epoch |  FPS  | AP<sup>val<br>0.5:0.95 | AP<sup>val<br>0.5 | FLOPs<br><sup>(G) | Params<br><sup>(M) | Weight |
+|---------------|--------------------|-------|-------|-------|------------------------|-------------------|-------------------|--------------------|--------|
 | YOLOv5-N      | CSPDarkNet-N       |  640  |  250  |       |                        |                   |   7.7             |   2.4              |  |
 | YOLOv5-S      | CSPDarkNet-S       |  640  |  250  |       |                        |                   |   27.1            |   9.0              |  |
 | YOLOv5-M      | CSPDarkNet-M       |  640  |  250  |       |                        |                   |   74.3            |   25.4             |  |
 | YOLOv5-L      | CSPDarkNet-L       |  640  |  250  |       |                        |                   |   155.6           |   54.2             |  |
-| YOLOX-L       | CSPDarkNet-L       |  640  |  300  |       |        46.6            |       66.1        |   155.4           |   54.2             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolox_coco.pth) |
-| YOLOv7-Tiny   | ELANNet-Tiny       |  640  |  300  |       |                        |                   |   22.9            |   8.1              |  |
-| YOLOv7-Large  | ELANNet-Large      |  640  |  300  |       |                        |                   |   144.6           |   44.0             |  |
 
-*All models are trained with ImageNet pretrained weight (IP). All FLOPs are measured with a 640x640 image size on COCO val2017. The FPS is measured with batch size 1 on 3090 GPU from the model inference to the NMS operation.*
+- *All models are trained with ImageNet pretrained weight (IP). All FLOPs are measured with a 640x640 image size on COCO val2017. The FPS is measured with batch size 1 on 3090 GPU from the model inference to the NMS operation.*
+
+- *The reproduced YOLOv5's head is the **Decoupled Head**, which is why the FLOPs and Params are higher than the official YOLOv5.*
 
-*Due to my limited computing resources, I had to abandon training on other YOLO detectors, including YOLOv7-Huge and YOLOv8-Nano~Large. If you are interested in these models and have trained them using the code from this project, I would greatly appreciate it if you could share the trained weight files with me.*
+- *Due to my limited computing resources, I had to abandon training on other YOLO detectors, including YOLOv7-Huge and YOLOv8-Nano~Large. If you are interested in these models and have trained them using the code from this project, I would greatly appreciate it if you could share the trained weight files with me.*
 
 ## Train
 ### Single GPU

README_CN.md

@@ -99,25 +99,33 @@ For example:
 python train.py --cuda -d coco --root path/to/COCO -v yolov1 -bs 16 --max_epoch 150 --wp_epoch 1 --eval_epoch 10 --fp16 --ema --multi_scale
 ```
 
-**P5-Model on COCO:**
+* 本书所实现的YOLO检测的性能：
+
+| Model         |   Backbone         | Scale | Epoch |  FPS  | 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          |  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         |  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        | DarkNet-53         |  640  |  250  |       |        42.9            |       63.5        |   167.4           |   54.9             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolov3_coco.pth) |
+| YOLOv4        | CSPDarkNet-53      |  640  |  250  |       |        46.6            |       65.8        |   162.7           |   61.5             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolov4_coco.pth) |
+| YOLOX-L       | CSPDarkNet-L       |  640  |  300  |       |        46.6            |       66.1        |   155.4           |   54.2             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolox_coco.pth) |
+| YOLOv7-Tiny   | ELANNet-Tiny       |  640  |  300  |       |                        |                   |   22.9            |   8.1              |  |
+| YOLOv7-Large  | ELANNet-Large      |  640  |  300  |       |                        |                   |   144.6           |   44.0             |  |
+
+* R我们复现的YOLOv5:
+
+| Model         |   Backbone         | Scale | Epoch |  FPS  | AP<sup>val<br>0.5:0.95 | AP<sup>val<br>0.5 | FLOPs<br><sup>(G) | Params<br><sup>(M) | Weight |
+|---------------|--------------------|-------|-------|-------|------------------------|-------------------|-------------------|--------------------|--------|
+| YOLOv5-N      | CSPDarkNet-N       |  640  |  250  |       |                        |                   |   7.7             |   2.4              |  |
+| YOLOv5-S      | CSPDarkNet-S       |  640  |  250  |       |                        |                   |   27.1            |   9.0              |  |
+| YOLOv5-M      | CSPDarkNet-M       |  640  |  250  |       |                        |                   |   74.3            |   25.4             |  |
+| YOLOv5-L      | CSPDarkNet-L       |  640  |  250  |       |                        |                   |   155.6           |   54.2             |  |
+
+- *所有的模型都使用了ImageNet预训练权重（IP），所有的FLOPs都是在COCO-val数据集上以640x640或1280x1280的输入尺寸来测试的。FPS指标是在一张3090型号的GPU上以batch size=1的输入来测试的，请注意，测速的内容包括模型前向推理、后处理以及NMS操作。*
+
+- *我们实现的YOLOv5的检测头是**解耦检测头**，所以FLOPs和参数量要高于官方的.*
+
+- *受限于我贫瘠的计算资源，更多的YOLO检测器被放弃训练了，包括YOLOv7-Huge、YOLOv8-Small~Large。如果您对他们感兴趣，并使用本项目的代码训练了他们，我很真诚地希望您能分享训练好的权重文件，那将会令我感激不尽。*
 
-| Model         |   Backbone         | Scale |  IP  | Epoch |  FPS  | 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          |  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         |  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        | DarkNet-53         |  640  |  √   |  250  |       |        42.9            |       63.5        |   167.4           |   54.9             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolov3_coco.pth) |
-| YOLOv4        | CSPDarkNet-53      |  640  |  √   |  250  |       |        46.6            |       65.8        |   162.7           |   61.5             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolov4_coco.pth) |
-| YOLOv5-N      | CSPDarkNet-N       |  640  |  √   |  250  |       |                        |                   |   7.7             |   2.4              |  |
-| YOLOv5-S      | CSPDarkNet-S       |  640  |  √   |  250  |       |                        |                   |   27.1            |   9.0              |  |
-| YOLOv5-M      | CSPDarkNet-M       |  640  |  √   |  250  |       |                        |                   |   74.3            |   25.4             |  |
-| YOLOv5-L      | CSPDarkNet-L       |  640  |  √   |  250  |       |                        |                   |   155.6           |   54.2             |  |
-| YOLOX-L       | CSPDarkNet-L       |  640  |  √   |  300  |       |        46.6            |       66.1        |   155.4           |   54.2             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpt/yolox_coco.pth) |
-| YOLOv7-Tiny   | ELANNet-Tiny       |  640  |  √   |  300  |       |                        |                   |   22.9            |   8.1              |  |
-| YOLOv7-Large  | ELANNet-Large      |  640  |  √   |  300  |       |                        |                   |   144.6           |   44.0             |  |
-
-*所有的模型都使用了ImageNet预训练权重（IP），所有的FLOPs都是在COCO-val数据集上以640x640或1280x1280的输入尺寸来测试的。FPS指标是在一张3090型号的GPU上以batch size=1的输入来测试的，请注意，测速的内容包括模型前向推理、后处理以及NMS操作。*
-
-*受限于我贫瘠的计算资源，更多的YOLO检测器被放弃训练了，包括YOLOv7-Huge、YOLOv8-Small~Large。如果您对他们感兴趣，并使用本项目的代码训练了他们，我很真诚地希望您能分享训练好的权重文件，那将会令我感激不尽。*
 
 ## 训练
 ### 使用单个GPU来训练