A tensorflow2.x implementation of CenterNet.
- Python >= 3.6
- TensorFlow == 2.2.0rc3
- numpy
- opencv-python
The following are the detection results of some pictures in the PASCAL VOC 2012 dataset.
- Download the PASCAL VOC 2012 dataset.
- Unzip the file and place it in the 'data/datasets' folder, make sure the directory is like this :
|——data
|——datasets
|——VOCdevkit
|——VOC2012
|——Annotations
|——ImageSets
|——JPEGImages
|——SegmentationClass
|——SegmentationObject
- Run write_to_txt.py to generate data.txt.
- Run train.py to start training, before that, you can change the value of the parameters in configuration.py.
- Change the test_single_image_dir in configuration.py.
- Run test.py to test on single picture.
- Official PyTorch implementation of CenterNet: https://github.com/xingyizhou/CenterNet
- A TensorFlow implementation of CenterNet: https://github.com/MioChiu/TF_CenterNet