Extend CenterNet++-RT to replace backbone ResNet-50 with DLA-34.

Extend CenterNet++ to work with KITTI dataset

mkdir data && cd data

mkdir coco && cd coco

mkdir images && cd images

wget http://images.cocodataset.org/zips/train2017.zip http://images.cocodataset.org/zips/val2017.zip http://images.cocodataset.org/zips/test2017.zip

unzip train2017.zip && unzip val2017.zip && unzip test2017.zip

cd ..

wget http://images.cocodataset.org/annotations/annotations_trainval2017.zip

unzip annotations_trainval2017.zip

mkdir kitti && cd kitti && mkdir images && cd images

wget https://s3.eu-central-1.amazonaws.com/avg-kitti/data_object_image_2.zip https://s3.eu-central-1.amazonaws.com/avg-kitti/data_object_calib.zip https://s3.eu-central-1.amazonaws.com/avg-kitti/data_object_label_2.zip

unzip data_object_image_2.zip && unzip data_object_label_2.zip && unzip data_object_calib.zip

The dataset directory should be like this:

├── data
│   ├── coco
│   │   ├── annotations
│   │   ├── images
            ├── train2017
            ├── val2017
            ├── test2017
│   ├── kitti
│   │   ├── annotations
│   │   ├── images
            ├── training
            ├── testing

• conda install pytorch==1.11.0 torchvision==0.12.0 torchaudio==0.11.0 cudatoolkit=11.3 -c pytorch

• python -m pip install matplotlib mmpycocotools tqdm mmcv-full terminaltables

• python setup.py develop