How to evaluate accuracy and speed of YOLOv4

How to evaluate accuracy and speed of YOLOv4

How to evaluate AP of YOLOv4 on the MS COCO evaluation server

0. Set width=608 height=608 (or 512x512, or 416x416) in the [net] section of cfg/yolov4.cfg file https://github.com/AlexeyAB/darknet/blob/6f718c257815a984253346bba8fb7aa756c55090/cfg/yolov4.cfg#L8-L9
1. Download and unzip test-dev2017 dataset from MS COCO server: http://images.cocodataset.org/zips/test2017.zip
2. Download list of images for Detection taks and replace the paths with yours (to the unzipped images from test2017.zip): https://raw.githubusercontent.com/AlexeyAB/darknet/master/scripts/testdev2017.txt
3. Download yolov4.weights file: https://drive.google.com/open?id=1cewMfusmPjYWbrnuJRuKhPMwRe_b9PaT
4. Content of the file cfg/coco.data should be

classes= 80
train  = <replace with your path>/trainvalno5k.txt
valid = <replace with your path>/testdev2017.txt
names = data/coco.names
backup = backup
eval=coco

5. Create /results/ folder near with ./darknet executable file
6. Run validation: ./darknet detector valid cfg/coco.data cfg/yolov4.cfg yolov4.weights
7. Rename the file /results/coco_results.json to detections_test-dev2017_yolov4_results.json and compress it to detections_test-dev2017_yolov4_results.zip
8. Submit file detections_test-dev2017_yolov4_results.zip to the MS COCO evaluation server for the test-dev2019 (bbox) https://competitions.codalab.org/competitions/20794#participate

You will get such results (AP=0.435 and AP50=0.657) in the end of file View scoring output log

overall performance
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.435
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.657
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.473
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.267
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.467
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.533
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.342
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.549
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.580
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.403
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.617
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.713
Done (t=334.58s)

How to evaluate FPS of YOLOv4 on GPU

1. Compile Darknet with GPU=1 CUDNN=1 CUDNN_HALF=1 OPENCV=1 in the Makefile (or use the same settings with Cmake)
2. Download yolov4.weights file: https://drive.google.com/open?id=1cewMfusmPjYWbrnuJRuKhPMwRe_b9PaT
3. Get any .avi/.mp4 video file (preferably not more than 1920x1080 to avoid bottlenecks in CPU performance)
4. Run one of two commands and look at the AVG FPS:

• include video_capturing + NMS + drawing_bboxes: ./darknet detector demo cfg/coco.data cfg/yolov4.cfg yolov4.weights test.mp4 -dont_show -ext_output
• exclude video_capturing + NMS + drawing_bboxes: ./darknet detector demo cfg/coco.data cfg/yolov4.cfg yolov4.weights test.mp4 -benchmark

Accuracy and FPS on RTX 2070 (R) and Tesla V100 (V):

• yolov4.cfg - 245 MB: yolov4.weights
  • width=608 height=608 in cfg: 65.7% [email protected] (43.5% [email protected]:0.95) - 34(R) FPS / 62(V) FPS - 128.5 BFlops
  • width=512 height=512 in cfg: 64.9% [email protected] (43.0% [email protected]:0.95) - 45(R) FPS / 83(V) FPS - 91.1 BFlops
  • width=416 height=416 in cfg: 62.8% [email protected] (41.2% [email protected]:0.95) - 55(R) FPS / 96(V) FPS - 60.1 BFlops
  • width=320 height=320 in cfg: 60% [email protected] ( 38% [email protected]:0.95) - 63(R) FPS / 123(V) FPS - 35.5 BFlops

---

Result - paper: https://arxiv.org/abs/2004.10934

---