DeepTecher comments

Results 7 comments of


                                            DeepTecher

Stereo R-CNN based 3D Object Detection for Autonomous Driving

解读：[知乎|@heryms 文章：Stereo 3D Object Detection](https://zhuanlan.zhihu.com/p/58077936)

Stereo R-CNN based 3D Object Detection for Autonomous Driving

代码已开源：[HKUST-Aerial-Robotics/Stereo-RCNN](https://github.com/HKUST-Aerial-Robotics/Stereo-RCNN)

Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving

代码：[mileyan/pseudo_lidar](https://github.com/mileyan/pseudo_lidar)，暂未公布代码项目链接：[mileyan.github.io/pseudo_lidar/](https://mileyan.github.io/pseudo_lidar/)

In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images

代码：[orsic/swiftnet](https://github.com/orsic/swiftnet)

Neural network vehicle models for high-performance automated driving

官方新闻：https://news.stanford.edu/2019/03/27/autonomous-driving-unknown/

(Ask) why InferInheritedType handle int8 to fp16 out?

Okay. But why do we handle int8 input to fp16 input in the case that some operations forget to handle int8 inputs? However, perhaps some ops may be not quant...

[V1] EP + DP Attention

Will we refer to deepseek and only ep & dp? • Prefilling Phase [Routed Expert EP32, MLA/Shared Expert DP32]: Each deployment unit spans 4 nodes with 32 redundant routed experts,...