简述yolo1-yolo3
Object detection is a computer vision task that involves predicting the presence of one or more objects, along with their classes and bounding boxes. YOLO (You Only Look Once) is a state of art Object Detector which can perform object detection in real-time with a good accuracy.
对象检测是一种计算机视觉任务，涉及预测一个或多个对象及其类和边界框的存在。 YOLO(只看一次)是一种先进的对象检测器，可以实时，高精度地执行对象检测。
The first three YOLO versions have been released in 2016, 2017 and 2018 respectively. However, in 2020, within only a few months of period, three major versions of YOLO have been released named YOLO v4, YOLO v5 and PP-YOLO. The release of YOLO v5 has even made a controversy among the people in machine learning community.
YOLO的前三个版本分别于2016年，2017年和2018年发布。 但是，在2020年的短短几个月内，已经发布了YOLO的三个主要版本，分别为YOLO v4，YOLO v5和PP-YOLO。 YOLO v5的发布甚至在机器学习社区的人们中引起了争议。
Additionally, this has caused a dilemma in the minds of people who are going to start their machine learning projects. In this article, we will discuss the reason for these many new YOLO releases, while emphasizing their originality, authorship, performance and the major improvements, helping people to choose the most appropriate version for their project.
此外，这在打算开始机器学习项目的人们的思想中造成了两难境地。 在本文中，我们将讨论发布许多YOLO新版本的原因，同时强调其原创性，作者身份，性能和重大改进，以帮助人们为他们的项目选择最合适的版本。
YOLO如何演变 (How YOLO evolved)
YOLO has been first introduced in 2016 and it was a milestone in object detection research due to its capability of detecting objects in real-time with a better accuracy.
YOLO于2016年首次推出，由于其能够以更高的精度实时检测物体的能力，因此是物体检测研究的一个里程碑。
It was proposed by Joseph Redmon, a graduate from the University of Washington. The paper describing YOLO won the the OpenCV People’s Choice Award at the Conference on Computer Vision and Pattern Recognition (CVPR) in 2016.
它是由华盛顿大学的毕业生Joseph Redmon提出的。 描述YOLO的论文在2016年计算机视觉和模式识别(CVPR)大会上获得了OpenCV人民选择奖 。
约瑟夫·雷德蒙(Joseph Redmon)的YOLO版本 (YOLO versions by Joseph Redmon)
Version 1
版本1
Version 1‘You Only Look Once: Unified, Real-Time Object Detection’ (2016)
版本1 ' 您只看一次：统一的实时对象检测 ' (2016)
Version 2
版本2
Version 2‘YOLO9000: Better, Faster, Stronger’ (2017)
版本2'YOLO9000：更好，更快，更强大 ' (2017)
Version 3
版本3
Version 3‘YOLOv3: An Incremental Improvement’ (2018)
版本3'YOLOv3：增量改进 ' (2018)
The YOLO v2 can process images at 40–90 FPS while YOLO v3 allows us to easily tradeoff between speed and accuracy, just by changing the model size without any retraining.
YOLO v2可以以40–90 FPS的速度处理图像，而YOLO v3则使我们能够轻松地在速度和准确性之间进行权衡，而无需更改任何模型即可进行调整。
YOLO的主要实现 (Major YOLO implementations)
The main implementation of Redmon’s YOLO is based on Darknet, which is an open source neural network framework written in C and CUDA. Darknet sets the underlying architecture of the network and used as the framework for training YOLO. This implementation is introduced by Redmon himself and it is fast, easy to install and supports CPU and GPU computation.
Redmon的YOLO的主要实现基于Darknet ，这是一个用C和CUDA编写的开源神经网络框架。 Darknet设置了网络的基础架构，并用作培训YOLO的框架。 该实现由Redmon本人介绍，它快速，易于安装并支持CPU和GPU计算。
Later, a PyTorch translation for YOLO v3 has been introduced by Glenn Jocher of Ultralytics LLC.
后来，Ultralytics LLC的Glenn Jocher引入了YOLO v3的PyTorch翻译 。
v3之后没有YOLO更新？ (No YOLO updates after v3?)
YOLO quickly become famous among the computer vision community due to its sublime speed along with good accuracy. However, in February 2020, Joseph Redmon, the creator of YOLO announced that he has stopped his research in computer vision! He additionally stated that it was due to several concerns regarding the potential negative impact of his work.
YOLO以其卓越的速度和良好的准确性Swift在计算机视觉社区中扬名。 但是，在2020年2月，YOLO的创建者约瑟夫·雷德蒙宣布，他已经停止对计算机视觉的研究 ！ 他还说，这是由于对他的工作可能产生的负面影响感到担忧。
演示地址
This led to some hot community discussions and raised an important question: Will there be any YOLO updates in future?
这引起了社区的热烈讨论，并提出了一个重要的问题：将来会不会有YOLO的任何更新？
YOLO v4 (YOLO v4)
Redmon’s withdrawal was not the end of YOLO. Reliving many in the computer vision community, the 4th generation of YOLO has been released in April 2020. It has been introduced in a paper titled ‘YOLOv4: Optimal Speed and Accuracy of Object Detection’ by Alexey Bochkovskiy et al.
雷德蒙(Redmon)的退出并非YOLO的终结。 依赖于计算机视觉社区的许多人，第四代YOLO已于2020年4月发布。它已由Alexey Bochkovskiy等人发表在题为“ YOLOv4：目标检测 的 最佳速度和准确性 ”的论文中。
Furthermore, Redmon’s work was continued by Alexey in the fork of the main repository. The YOLO v4 has been considered the fastest and most accurate real-time model for object detection.
此外，Alexey在主存储库的分支中继续Redmon的工作。 YOLO v4被认为是用于物体检测的最快，最准确的实时模型。
YOLO v4的重大改进 (Major improvements in YOLO v4)
YOLO v4 takes the influence of state of art BoF (bag of freebies) and several BoS (bag of specials). The BoF improve the accuracy of the detector, without increasing the inference time. They only increase the training cost. On the other hand, the BoS increase the inference cost by a small amount however they significantly improve the accuracy of object detection.
YOLO v4受到了BoF(免费赠品袋)和几个BoS(特价袋)的影响。 BoF可提高检测器的精度，而无需增加推理时间。 它们只会增加培训成本。 另一方面，BoS会少量增加推理成本，但是它们会显着提高目标检测的准确性。
YOLO v4性能 (YOLO v4 Performance)
YOLO v4 also based on the Darknet and has obtained an AP value of 43.5 percent on the COCO dataset along with a real-time speed of 65 FPS on the Tesla V100, beating the fastest and most accurate detectors in terms of both speed and accuracy.
YOLO v4也基于Darknet，在COCO数据集上获得的AP值为43.5％，在Tesla V100上的实时速度为65 FPS，在速度和准确性方面均击败了最快，最准确的探测器。
When compared with YOLO v3, the AP and FPS have increased by 10 percent and 12 percent, respectively.
与YOLO v3相比，AP和FPS分别增加了10％和12％。
Redmon对YOLO作者身份的回应 (Response of Redmon on YOLO authorship)
On 24th April 2020, the Readme file of Redmon’s original github account updated with a links to Alexey’s forked repository and to the YOLO v4 paper. Redmon also tweeted:
2020年4月24日，Redmon原始github帐户的自述文件更新，并带有指向Alexey分叉存储库和YOLO v4论文的链接。 Redmon还发了一条推文：
演示地址
YOLO v5 (YOLO v5)
After the release of YOLO v4, within just two months of period, an another version of YOLO has been released called YOLO v5 ! It is by the Glenn Jocher, who already known among the community for creating the popular PyTorch implementation of YOLO v3.
在发布YOLO v4之后的短短两个月内，又发布了另一个版本的YOLO，称为YOLO v5！ 由Glenn Jocher撰写，他在社区中以创建流行的YOLO v3的PyTorch实现而闻名。
On June 9, 2020, Jocher stated that his YOLO v5 implementation is publicly released and is recommended to use in new projects. However he did not publish a paper to accompany his release, when initially releasing this new version.
2020年6月9日，Jocher宣布其YOLO v5实施已公开发布，建议在新项目中使用。 但是，在最初发布此新版本时，他并未随发布发布任何论文。
YOLO v5的重大改进 (Major improvements in YOLO v5)
YOLO v5 is different from all other prior releases, as this is a PyTorch implementation rather than a fork from original Darknet. Same as YOLO v4, the YOLO v5 has a CSP backbone and PA-NET neck. The major improvements includes mosaic data augmentation and auto learning bounding box anchors.
YOLO v5与所有其他以前的版本不同，因为这是PyTorch的实现，而不是原始Darknet的fork。 与YOLO v4相同，YOLO v5具有CSP主干和PA-NET颈。 主要改进包括镶嵌数据增强和自动学习边界框锚。
机器学习社区中的争议 (Controversy in machine learning community)
The release of YOLO v5 has attracted much attention and has caused heated discussions in machine learning community platforms. This was majorly due to several facts on an article published by the Roboflow team regarding the YOLO v5.
YOLO v5的发布引起了广泛关注，并引起了机器学习社区平台中的激烈讨论。 这主要是由于Roboflow团队发表的有关YOLO v5的文章中的一些事实。
That article, titled ‘YOLOv5 is Here’ has been published on June 10, 2020 on Roboflow blog, stating several important facts. Followings are some quotes from that blog post by Joseph Nelson and Jacob Solawetz.
题为“ YOLOv5在这里”的文章已于2020年6月10日发布在Roboflow博客上，陈述了一些重要事实。 以下是约瑟夫·纳尔逊(Joseph Nelson)和雅各布·索拉维兹(Jacob Solawetz)在该博客文章中的一些引用。
“Running a Tesla P100, we saw inference times up to 0.007 seconds per image, meaning 140 frames per second (FPS)! By contrast, YOLO v4 achieved 50 FPS after having been converted to the same Ultralytics PyTorch library.”
“运行Tesla P100，我们看到每个图像的推理时间高达0.007秒，意味着每秒140帧(FPS)！ 相比之下，YOLO v4在转换为相同的Ultralytics PyTorch库后达到了50 FPS。”
“YOLO v5 is small. Specifically, a weights file for YOLO v5 is 27 megabytes. Our weights file for YOLO v4 (with Darknet architecture) is 244 megabytes. YOLO v5 is nearly 90 percent smaller than YOLO v4.”
“ YOLO v5很小。 具体来说，YOLO v5的权重文件为27 MB。 YOLO v4(具有Darknet架构)的权重文件为244 MB。 YOLO v5比YOLO v4小近90％。”
So, it said to be that YOLO v5 is extremely fast and lightweight than YOLO v4, while the accuracy is on par with the YOLO v4 benchmark. But the major question raised by the community was: Are these benchmarks accurate and reproducible?
因此，据说YOLO v5比YOLO v4极其快速，轻巧，而准确性与YOLO v4基准相当。 但是社区提出的主要问题是：这些基准是否准确且可重复？
回应 (Responses)
The author of YOLO v4, Alexey was not happy about how all those comparisons have been made. He has responded to several questions raised in the github, mentioning the issues with those comparisons, specially the batch size.
YOLO v4的作者Alexey对于如何进行所有比较并不满意。 他回答了github中提出的几个问题 ，并提到了那些比较的问题，特别是批处理大小。
The Roboflow and YOLO v5 developers also responded positively to the Hacker News community’s questions and on June 14, by publishing an article on Roboflow blog, describing how they compared the two versions.
Roboflow和YOLO v5开发人员还对Hacker News社区的问题做出了积极回应，并于6月14日在Roboflow博客上发表了一篇文章 ，描述了他们如何比较这两个版本。
PP-YOLO (PP-YOLO)
PP-YOLO has been introduced in July 2020, via a paper titled PP-YOLO: An Effective and Efficient Implementation of Object Detector, by Xiang Long et al. It is based on PaddlePaddle (Parallel Distributed Deep Learning), an open source deep learning platform originally developed by Baidu scientists.
向龙(PP-YOLO)于2020年7月通过香龙(Xiang Long)等人的题为《 PP-YOLO：一种有效且高效的目标检测器实现 》的论文被引入。 它基于PaddlePaddle(并行分布式深度学习)，PaddlePaddle是最初由百度科学家开发的开源深度学习平台。
PP-YOLO是新颖的型号吗？ (Is PP-YOLO a novel model?)
PP-YOLO is based on YOLO v3 model. The paper clearly states that the goal of PP-YOLO is to implement an object detector with relatively balanced effectiveness and efficiency that can be directly applied in actual application scenarios, rather than propose a novel detection model.
PP-YOLO基于YOLO v3模型。 该文件明确指出，PP-YOLO的目标是实现一种具有相对平衡的有效性和效率的对象检测器，该对象检测器可以直接应用于实际应用场景中，而不是提出一种新颖的检测模型。
The notable changes include the replacement of Darknet53 backbone of YOLO v3 with a ResNet backbone and increase of training batch size from 64 to 192 (as mini-batch size of 24 on 8 GPUs).
显着的变化包括用ResNet骨干替换了YOLO v3的Darknet53骨干，并将训练批次大小从64增加到192(在8个GPU上的最小批次大小为24)。
PP-YOLO性能 (PP-YOLO Performance)
According to the paper, the PP-YOLO can achieve a mAP of 45.2% COCO dataset which exceeds the 43.5% of YOLO v4. When tested on a V100 with batch size = 1, the PP-YOLO can achieve a inference speed of 72.9 FPS, which is also higher than 65 FPS of YOLO v4.
根据该论文，PP-YOLO可以实现45.2％COCO数据集的mAP，超过YOLO v4的43.5％。 在批量大小为1的V100上进行测试时，PP-YOLO可以达到72.9 FPS的推理速度，这也比YOLO v4的65 FPS更高。
The PP-YOLO authors speculate that the better optimization of tensorRT on ResNet model than Darknet is the main reason behind this performance improvement.
PP-YOLO的作者推测，ResNet模型上的tensorRT比Darknet更好的优化是导致此性能提高的主要原因。
最后的话 (Final words)
In this article, we have discussed the important milestones of YOLO’s evolvement and the story behind many new YOLO releases in 2020, while emphasizing on major improvements and performance of these latest YOLO versions. In a summary, the YOLO v4 is the latest Darknet based implementation of this state of art object detector. It also has a paper published with benchmarks by Alexey Bochkovskiy. On the other hand, the YOLO v5 is a new PyTorch implementation by Ultralytics and when tested with larger batch size, it said to have a higher interference speed than most of the detectors. However, at the time of writing this article, there is no peer reviewed paper published for YOLO v5. The PP-YOLO is an another new YOLO upgrade based on a deep learning framework called PaddlePaddle, and it improves the YOLO v3 model to obtain a better balance between effectiveness and efficiency. The facts we discussed like the architecture, improvements and performance on each release will be helpful when selecting the most appropriate YOLO version for a particular project. Keep Learning !
在本文中，我们讨论了YOLO演变的重要里程碑，以及2020年许多YOLO新版本发布背后的故事，同时重点介绍了这些最新YOLO版本的重大改进和性能。 总而言之，YOLO v4是这种最先进的目标检测器的最新基于Darknet的实现。 它还有一篇由Alexey Bochkovskiy基准发布的论文。 另一方面，YOLO v5是Ultralytics的一种新的PyTorch实施，在以较大的批量进行测试时，据说它比大多数检测器具有更高的干扰速度。 但是，在撰写本文时，还没有针对YOLO v5发表同行评审的论文。 PP-YOLO是另一种新的YOLO升级，它基于称为PaddlePaddle的深度学习框架，它改进了YOLO v3模型，从而在效果和效率之间取得了更好的平衡。 当为特定项目选择最合适的YOLO版本时，我们讨论的事实(例如，每个发行版的体系结构，改进和性能)将很有帮助。 保持学习 ！
翻译自: https://towardsdatascience.com/yolo-v4-or-yolo-v5-or-pp-yolo-dad8e40f7109
简述yolo1-yolo3