if you wan use pretrained darknet-53 on IMAGENET weights, please download darknet53.conv.74,and put it into checkpoints/
if you just want a pretrained weights on kitti dataset for test or detect, please download pretrained weights file, and put it into weights folder, the path: weights/yolov3-kitti.weights
and you should transfrom kitti lable to coco label, by using label_transform
Inference
Uses pretrained weights to make predictions on images. weights/yolov3-kitti.weights was trained by kitti data set. python3 detect.py --image_folder /data/samples
Small objects detection
Detect
rundetect.py to detect objects, and please put samples into data/samples defult weights files is weights/kitti.weights
Video
run video.py to detect objects from a webcam or a video file. On I7 7700 8G GTX1070 FPS is 22 cause some problems, test resized images is really faster than resizeing images and then inference.
Test
run test.py
Train
Please run python3 -m visdom.server first to vislizer your training loss.
Data augmentation as well as additional training tricks remains to be implemented. PRs are welcomed!
Abstract 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/.