train YOLOv3 on COCO

README.md

@@ -64,7 +64,7 @@ python train.py --cuda -d voc --root path/to/VOCdevkit -v yolov1 -bs 16 --max_ep
 | YOLOv1 |  640  |  √   |  150  | 76.7 |                          |   37.8            |   21.3             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpy/yolov1_voc.pth) |
 | YOLOv2 |  640  |  √   |  150  | 79.8 |                          |   53.9            |   30.9             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpy/yolov2_voc.pth) |
 | YOLOv3 |  640  |  √   |  150  | 82.0 |                          |   167.4           |   54.9             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpy/yolov3_voc.pth) |
-| YOLOv4 |  640  |  √   |  150  |      |                          |                   |                    |  |
+| YOLOv4 |  640  |  √   |  150  | 83.6 |                          |   162.7           |   61.5             | [ckpt](https://github.com/yjh0410/PyTorch_YOLO_Tutorial/releases/download/yolo_tutorial_ckpy/yolov4_voc.pth) |
 | YOLOX  |  640  |  √   |  150  |      |                          |                   |                    |  |
 
 *All models are trained with ImageNet pretrained weight (IP). All FLOPs are measured with a 640x640 image size on VOC2007 test. The FPS is measured with batch size 1 on 3090 GPU from the model inference to the NMS operation.*

train.sh

@@ -3,7 +3,7 @@ python train.py \
         --cuda \
         -d coco \
         --root /mnt/share/ssd2/dataset/ \
-        -m yolov2 \
+        -m yolov1 \
         -bs 16 \
         -size 640 \
         --wp_epoch 1 \