论文标题
BEVPOOLV2：BEVDET对部署的尖端实施
BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deployment
论文作者
论文摘要
我们发布了BevDet的新代码库版本，称为Branch Dev2.0。使用DEV2.0，我们建议BevPoolV2从工程优化的角度升级视图转换过程，从而使其在计算和存储方面都不承担巨大负担。它通过省略了大型易曲线特征的计算和预处理来实现这一目标。结果，即使大量输入分辨率为640x1600，也可以在0.82毫秒内处理，这是先前最快实现的15.1倍。此外，与先前的实现相比，它自然而然地不需要存储大型Froustum功能，因此它的缓存消耗量也较低。最后但并非最不重要的一点是，这也使部署到另一个后端方便。我们提供了一个部署到分支Dev2.0中的Tensorrt后端的示例，并显示BEVDET范式可以在其上处理的速度。除了BevPoolV2之外，我们还选择并整合了过去一年中提出的一些实质性进展。作为示例配置，BEVDET4D-R50-DEPTH-CBGS在Nuscenes验证集上得分为52.3 nds，并且可以在Pytorch后端以16.4 fps的速度处理。该代码已发布是为了促进在https://github.com/huangjunjie2017/bevdet/tree/tree/dev2.0上进行研究。
We release a new codebase version of the BEVDet, dubbed branch dev2.0. With dev2.0, we propose BEVPoolv2 upgrade the view transformation process from the perspective of engineering optimization, making it free from a huge burden in both calculation and storage aspects. It achieves this by omitting the calculation and preprocessing of the large frustum feature. As a result, it can be processed within 0.82 ms even with a large input resolution of 640x1600, which is 15.1 times the previous fastest implementation. Besides, it is also less cache consumptive when compared with the previous implementation, naturally as it no longer needs to store the large frustum feature. Last but not least, this also makes the deployment to the other backend handy. We offer an example of deployment to the TensorRT backend in branch dev2.0 and show how fast the BEVDet paradigm can be processed on it. Other than BEVPoolv2, we also select and integrate some substantial progress that was proposed in the past year. As an example configuration, BEVDet4D-R50-Depth-CBGS scores 52.3 NDS on the NuScenes validation set and can be processed at a speed of 16.4 FPS with the PyTorch backend. The code has been released to facilitate the study on https://github.com/HuangJunJie2017/BEVDet/tree/dev2.0.
