A minimal tensorflow implementation of YOLOv3, with support for multibackbone Resnet, VGG, Darknet53, mobilenetv2, mobilenetv3, training, inference and evaluation.

• Resnet
• VGG
• Darknet53
• mobilenetv2
• mobilenetv3

Installation

---

Install requirements and download pretrained weights

$ pip3 install -r ./docs/requirements.txt
$ wget https://pjreddie.com/media/files/yolov3.weights

Quick start

---

In this part, we will use pretrained weights to make predictions on both image and video.

$ python image_demo.py
$ python video_demo.py # if use camera, set video_path = 0

Train yymnist

---

you can train it and then evaluate your model

$ python train.py
$ tensorboard --logdir ./data/log
$ python test.py
$ cd ../mAP
$ python main.py        # Detection images are expected to save in `YOLOV3/data/detection`

Track training progress in Tensorboard and go to http://localhost:6006/

$ tensorboard --logdir ./data/log