YOLOv3
Model description
We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that’s pretty swell. It’s a little bigger than last time but more accurate. It’s still fast though, don’t worry. At 320 × 320 YOLOv3 runs in 22 ms at 28.2 mAP, as accurate as SSD but three times faster. When we look at the old .5 IOU mAP detection metric YOLOv3 is quite good. It achieves 57.9 AP50 in 51 ms on a Titan X, compared to 57.5 AP50 in 198 ms by RetinaNet, similar performance but 3.8× faster. As always, all the code is online at https://pjreddie.com/yolo/.
Prepare
bash init_tf.sh
Download dataset and checkpoint
Download VOC PASCAL trainval and test data
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar
Extract all of these tars into one directory and rename them, which should have the following basic structure.
VOC # path: /home/yang/dataset/VOC
├── test
| └──VOCdevkit
| └──VOC2007 (from VOCtest_06-Nov-2007.tar)
└── train
└──VOCdevkit
└──VOC2007 (from VOCtrainval_06-Nov-2007.tar)
└──VOC2012 (from VOCtrainval_11-May-2012.tar)
Download checkpoint
Exporting loaded COCO weights as TF checkpoint(yolov3_coco.ckpt)BaiduCloud
Run training
bash ./run_training.sh
Result
|
mAP |
fps |
multi_card |
33.67% |
4.34it/s |