CenterNet (Objects as Points) implementation in Keras and Tensorflow
This is an implementation of CenterNet for object detection on keras and Tensorflow. The project is based on fizyr/keras-retinanet and the official implementation xingyizhou/CenterNet. Thanks for their hard work.
The network is anchor-free. It is quite simple, fast and accurate.
| backbone | mAP50 | | ---- | ---- | | resnet50 | 0.7290 |
python3 inference.pyto test your image by specifying image path and model path there.
python3 train.py --freeze-backbone --gpu 0 --random-transform --compute-val-loss --batch-size 32 --steps 1000 pascal datasets/VOC2012to start training. The init lr is 1e-3 and decays to 1e-4 when loss stops dropping down.
python3 train.py --snapshot xxx.h5 --gpu 0 --random-transform --compute-val-loss --batch-size 32 --steps 1000 pascal datasets/VOC2012to start training when val mAP can not increase during STEP1. The init lr is 1e-4 and decays to 1e-5 when loss stops dropping down. ## Evaluate
python3 eval/common.pyto evaluate by specifying model path there.
This project is released under the Apache License. Some parts are borrowed from fizyr/keras-retinanet and xingyizhou/CenterNet. Please take their licenses into consideration too when use this project.