Fetch the repository succeeded.
Detection identifies objects as axis-aligned boxes in an image. Most successful object detectors enumerate a nearly exhaustive list of potential object locations and classify each. This is wasteful, inefficient, and requires additional post-processing. In this paper, we take a different approach. We model an object as a single point --- the center point of its bounding box. Our detector uses keypoint estimation to find center points and regresses to all other object properties, such as size, 3D location, orientation, and even pose. Our center point based approach, CenterNet, is end-to-end differentiable, simpler, faster, and more accurate than corresponding bounding box based detectors. CenterNet achieves the best speed-accuracy trade-off on the MS COCO dataset, with 28.1% AP at 142 FPS, 37.4% AP at 52 FPS, and 45.1% AP with multi-scale testing at 1.4 FPS. We use the same approach to estimate 3D bounding box in the KITTI benchmark and human pose on the COCO keypoint dataset. Our method performs competitively with sophisticated multi-stage methods and runs in real-time.
git clone https://github.com/PaddlePaddle/PaddleDetection.git
cd PaddleDetection
pip install -r requirements.txt
python3 setup.py install
python3 dataset/coco/download_coco.py
# GPU多卡训练
export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
python3 -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/centernet/centernet_r50_140e_coco.yml --eval
# GPU单卡训练
export CUDA_VISIBLE_DEVICES=0
python3 tools/train.py -c configs/centernet/centernet_r50_140e_coco.yml --eval
# finetune
export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
python3 -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/centernet/centernet_r50_140e_coco.yml -o pretrain_weights=https://bj.bcebos.com/v1/paddledet/models/centernet_r50_140e_coco.pdparams --eval
# 注：默认学习率是适配多GPU训练(8x GPU)，若使用单GPU训练，须对应调整config中的学习率（例如，除以8）
| GPUs | learning rate | FPS | Train Epochs | mAP |
|---|---|---|---|---|
| 1x8 | 0.00005 | 10.85 | 3 | 38.5 |
此处可能存在不合适展示的内容，页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容，可点击提交进行申诉，我们将尽快为您处理。