Bienqq
/
car-detection-bayes
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

updates

This commit is contained in:
Glenn Jocher 2018-12-22 12:58:59 +01:00
parent a0ab4916fd
commit ffd45ebf0c
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -49,6 +49,7 @@ Run `detect.py` to apply trained weights to an image and visualize results, such
![Alt](https://github.com/ultralytics/yolov3/blob/master/data/zidane_result.jpg "inference example") ![Alt](https://github.com/ultralytics/yolov3/blob/master/data/zidane_result.jpg "inference example")
# Pretrained Weights # Pretrained Weights
Download official YOLOv3 weights: Download official YOLOv3 weights:
**Darknet** format: **Darknet** format:
@ -59,7 +60,6 @@ Download official YOLOv3 weights:
- https://storage.googleapis.com/ultralytics/yolov3.pt - https://storage.googleapis.com/ultralytics/yolov3.pt
- https://storage.googleapis.com/ultralytics/yolov3-tiny.pt - https://storage.googleapis.com/ultralytics/yolov3-tiny.pt
# Validation mAP # Validation mAP
Run `test.py` to validate the official YOLOv3 weights `weights/yolov3.weights` against the 5000 validation images. You should obtain a .584 mAP at `--img-size 416`, or .586 at `--img-size 608` using this repo, compared to .579 at 608 x 608 reported in darknet (https://arxiv.org/abs/1804.02767). Run `test.py` to validate the official YOLOv3 weights `weights/yolov3.weights` against the 5000 validation images. You should obtain a .584 mAP at `--img-size 416`, or .586 at `--img-size 608` using this repo, compared to .579 at 608 x 608 reported in darknet (https://arxiv.org/abs/1804.02767).