@fei

原始论文题目：Continuous Batching — ORCA: a distributed serving system for Transformer-based generative models关键词：Continuous Batching， iteration-level scheduling， selective batchingOrca系统又由几个关键组件组成：Endpoint，Scheduler，Execution Engine，Request Pool不同于那些通过多次迭代直到所

原始论文中废话太多，文章主要参考csdn以及知乎上等博主的优秀博文总结得到参考：https://blog.csdn.net/qq_37541097/article/details/81214953https://zhuanlan.zhihu.com/p/76802514https://zhuanlan.zhihu.com/p/337383661backboneyolo v3的backbone 使用的是darknet53，如下图：其中每个convolutional层是由 conv + bn +

摘要部分real-time object detection system that can detect over 9000 object categories.之所以叫yolo 9000 是因为可以检测9000个目标。Using a novel, multi-scale training method the same YOLOv2 model can run at varying sizes, offering an easy tradeoff between speed and accura

yolov1参考这篇文章https://zhuanlan.zhihu.com/p/46691043摘要we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities.作者将目标检测问题变成一个回归问题，包括bounding boxes的计算和目标类别的概率。A single neural network predic

摘要We present a method for detecting objects in images using a single deep neural network. Our approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location.

摘要Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But recent deep learning object detectors have avoided pyramid representations, in part because they are compute and memory intensive. In this paper

摘要Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions w