持续创作，加速成长！这是我参与「掘金日新计划 · 6 月更文挑战」的第28天，点击查看活动详情
ShowMeAI日报系列全新升级！覆盖AI人工智能 工具&框架 | 项目&代码 | 博文&分享 | 数据&资源 | 研究&论文 等方向。点击查看 历史文章列表，在公众号内订阅话题 #ShowMeAI资讯日报，可接收每日最新推送。点击 专题合辑&电子月刊 快速浏览各专题全集。
1.工具&框架
工具：Try to hijack AI!- 机器学习模型漏洞检测工具箱
tags: [机器学习，模型漏洞，检测工具]
'Try to hijack AI! - reveal the vulnerabilities of machine learning models, algorithms for AI security such as Model Inversion, Poisoning Attack, Evasion Attack, Differential Privacy, and Homomorphic Encryption' by Syumei
GitHub: github.com/Koukyosyume…
工具：Zotero PDF Translate- Zotero 6的PDF翻译插件
tags: [PDF插件，翻译]
'Zotero PDF Translate - PDF translation add-on for Zotero 6' by windingwind
GitHub: github.com/windingwind…
工具库：HyperTS- 易用，高效，统一的全管道自动时间序列分析工具，支持时间序列预测，分类及回归
tags: [时间序列，时序分类，时序回归]
'HyperTS - A Full-Pipeline Automated Time Series (AutoTS) Analysis Toolkit.' by DataCanvasIO
GitHub: github.com/DataCanvasI…
工具库：KLineChart- 可高度自定义的轻量级k线图
tags: [k线图，可视化]
Lightweight k-line chart that can be highly customized. Zero dependencies. Support mobile.（可高度自定义的轻量级k线图，无第三方依赖，支持移动端）' by liihuu
GitHub: github.com/liihuu/KLin…
工具库：Auto-Causality- 自动化因果推理库
tags: [因果推理，归因]
'Auto-Causality: A library for automated Causal Inference model estimation and selection - AutoML for causal inference.' by TransferWise Ltd.
GitHub: github.com/transferwis…
工具库：Feast- 机器学习特征存储工具库
tags: [特征存储，机器学习]
'Feast - Feature Store for Machine Learning'
Feast是一个用于机器学习的开源特征存储工具库。Feast是模型训练和在线推理生产分析数据的最快途径之一。
GitHub: github.com/feast-dev/f…
2.博文&分享
分享：精益副业- 程序员如何优雅地做副业
tags: [副业，程序员]
GitHub: github.com/easychen/le…
Link: r.ftqq.com/lean-side-b…
3.数据&资源
数据集：HaGRID：手势识别数据集
tags: [手势识别，手势，数据集]
'HaGRID - HAnd Gesture Recognition Image Dataset - HAnd Gesture Recognition Image Dataset' by Alexander Kapitanov
GitHub: github.com/hukenovs/ha…
资源分享：PyData London 2022 PyMC贝叶斯建模教程资料
tags: [PyData，贝叶斯建模]
'Probabilistic Python: An Introduction to Bayesian Modeling with PyMC - PyData London 2022 Tutorial' by Chris Fonnesbeck
GitHub: github.com/fonnesbeck/…
4.研究&论文
公众号回复关键字 日报，免费获取整理好的6月论文合辑。
论文：ARF: Artistic Radiance Fields
论文标题：ARF: Artistic Radiance Fields
论文时间：13 Jun 2022
所属领域：计算机视觉
对应任务：图像生成，艺术创作
论文作者：Kai Zhang, Nick Kolkin, Sai Bi, Fujun Luan, Zexiang Xu, Eli Shechtman, Noah Snavely
论文简介：We present a method for transferring the artistic features of an arbitrary style image to a 3D scene./我们提出了一种将任意风格图像的艺术特征转移到三维场景中的方法。
论文摘要：We present a method for transferring the artistic features of an arbitrary style image to a 3D scene. Previous methods that perform 3D stylization on point clouds or meshes are sensitive to geometric reconstruction errors for complex real-world scenes. Instead, we propose to stylize the more robust radiance field representation. We find that the commonly used Gram matrix-based loss tends to produce blurry results without faithful brushstrokes, and introduce a nearest neighbor-based loss that is highly effective at capturing style details while maintaining multi-view consistency. We also propose a novel deferred back-propagation method to enable optimization of memory-intensive radiance fields using style losses defined on full-resolution rendered images. Our extensive evaluation demonstrates that our method outperforms baselines by generating artistic appearance that more closely resembles the style image. Please check our project page for video results and open-source implementations: www.cs.cornell.edu/projects/ar…
我们提出了一种将任意风格图像的艺术特征转移到三维场景中的方法。以前在点云或网格上进行三维风格化的方法对复杂的真实世界场景的几何重建错误很敏感。相反，我们建议对更强大的辐射场表示进行风格化。我们发现，常用的基于Gram矩阵的损失往往会产生模糊的结果，而没有真实的笔触，因此我们引入了基于近邻的损失，它在捕捉风格细节方面非常有效，同时保持了多视图的一致性。我们还提出了一种新的延迟反向传播方法，以便利用在全分辨率渲染图像上定义的风格损失来优化内存密集型的光影场。我们的广泛评估表明，我们的方法通过生成更接近于风格图像的艺术外观而优于基线。请查看我们的项目页面，了解视频结果和开源实现：www.cs.cornell.edu/projects/ar… 。
论文：Zero-Shot AutoML with Pretrained Models
论文标题：Zero-Shot AutoML with Pretrained Models
论文时间：16 Jun 2022
所属领域：机器学习
对应任务：AutoML，Meta-Learning，自动化机器学习，元学习
论文作者：Ekrem Öztürk, Fabio Ferreira, Hadi S. Jomaa, Lars Schmidt-Thieme, Josif Grabocka, Frank Hutter
论文简介：Given a new dataset D and a low compute budget, how should we choose a pre-trained model to fine-tune to D, and set the fine-tuning hyperparameters without risking overfitting, particularly if D is small?/给定一个新的数据集D和低计算力限制，我们应该如何选择一个预训练的模型来微调到D，并设置微调超参数而不冒过拟合的风险，特别是在D很小的时候？
论文摘要：Given a new dataset D and a low compute budget, how should we choose a pre-trained model to fine-tune to D, and set the fine-tuning hyperparameters without risking overfitting, particularly if D is small? Here, we extend automated machine learning (AutoML) to best make these choices. Our domain-independent meta-learning approach learns a zero-shot surrogate model which, at test time, allows to select the right deep learning (DL) pipeline (including the pre-trained model and fine-tuning hyperparameters) for a new dataset D given only trivial meta-features describing D such as image resolution or the number of classes. To train this zero-shot model, we collect performance data for many DL pipelines on a large collection of datasets and meta-train on this data to minimize a pairwise ranking objective. We evaluate our approach under the strict time limit of the vision track of the ChaLearn AutoDL challenge benchmark, clearly outperforming all challenge contenders.
给定一个新的数据集D和低计算量预算，我们应该如何选择一个预训练的模型来微调到D，并设置微调超参数而不冒过度拟合的风险，特别是当D很小的时候？在这里，我们扩展了自动机器学习（AutoML），以最好地做出这些选择。我们的独立于领域的元学习方法学习了一个零样本的代理模型，在测试时，可以为一个新的数据集D选择正确的深度学习（DL）管道（包括预训练的模型和微调超参数），只给定描述D的琐碎元特征，如图像分辨率或类的数量。为了训练这个零样本模型，我们在大量的数据集上收集了许多DL管道的性能数据，并对这些数据进行元训练，以最小化成对的排名目标。我们在ChaLearn AutoDL挑战基准的视觉轨道的严格时间限制下评估了我们的方法，明显优于所有挑战的竞争者。
论文：Learning Implicit Feature Alignment Function for Semantic Segmentation
论文标题：Learning Implicit Feature Alignment Function for Semantic Segmentation
论文时间：17 Jun 2022
所属领域：计算机视觉
对应任务：Semantic Segmentation，语义分割
论文作者：Hanzhe Hu, Yinbo Chen, Jiarui Xu, Shubhankar Borse, Hong Cai, Fatih Porikli, Xiaolong Wang
论文简介：As such, IFA implicitly aligns the feature maps at different levels and is capable of producing segmentation maps in arbitrary resolutions./因此，IFA隐含着对不同层次的特征图的对齐，并且能够产生任意分辨率的分割图。
论文摘要：Integrating high-level context information with low-level details is of central importance in semantic segmentation. Towards this end, most existing segmentation models apply bilinear up-sampling and convolutions to feature maps of different scales, and then align them at the same resolution. However, bilinear up-sampling blurs the precise information learned in these feature maps and convolutions incur extra computation costs. To address these issues, we propose the Implicit Feature Alignment function (IFA). Our method is inspired by the rapidly expanding topic of implicit neural representations, where coordinate-based neural networks are used to designate fields of signals. In IFA, feature vectors are viewed as representing a 2D field of information. Given a query coordinate, nearby feature vectors with their relative coordinates are taken from the multi-level feature maps and then fed into an MLP to generate the corresponding output. As such, IFA implicitly aligns the feature maps at different levels and is capable of producing segmentation maps in arbitrary resolutions. We demonstrate the efficacy of IFA on multiple datasets, including Cityscapes, PASCAL Context, and ADE20K. Our method can be combined with improvement on various architectures, and it achieves state-of-the-art computation-accuracy trade-off on common benchmarks. Code will be made available at github.com/hzhupku/ifa
在语义分割中，将高水平的上下文信息与低水平的细节结合起来是非常重要的。为此，大多数现有的分割模型对不同尺度的特征图进行双线性上采样和卷积，然后在同一分辨率下对它们进行排列。然而，双线性上采样模糊了在这些特征图中学习到的精确信息，而卷积则会产生额外的计算成本。为了解决这些问题，我们提出了隐式特征对齐功能（IFA）。我们的方法受到了迅速扩大的隐性神经表征主题的启发，其中基于坐标的神经网络被用来指定信号的领域。在IFA中，特征向量被看作是代表一个二维信息场。给定一个查询坐标，附近的特征向量及其相对坐标从多级特征图中获取，然后输入MLP以产生相应的输出。因此，IFA隐含地对齐了不同层次的特征图，并能够产生任意分辨率的分割图。我们在多个数据集上证明了IFA的功效，包括Cityscapes、PASCAL Context和ADE20K。我们的方法可以与各种架构上的改进相结合，并且在常见的基准上实现了最先进的计算-准确度权衡。代码将在[github.com/hzhupku/IFA…
论文：Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation
论文标题：Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation
论文时间：CVPR 2022
所属领域：计算机视觉
对应任务：2D Human Pose Estimation，Multi-Person Pose Estimation，Pose Estimation，二维人体姿态估计，多人姿态估计，姿态估计
论文作者：Yihan Wang, Muyang Li, Han Cai, Wei-Ming Chen, Song Han
论文简介：Inspired by this finding, we design LitePose, an efficient single-branch architecture for pose estimation, and introduce two simple approaches to enhance the capacity of LitePose, including Fusion Deconv Head and Large Kernel Convs./在这一发现的启发下，我们设计了LitePose，一个用于姿态估计的高效单分支架构，并介绍了两种简单的方法来提高LitePose的能力，包括融合Deconv Head和Large Kernel Convs。
论文摘要：Pose estimation plays a critical role in human-centered vision applications. However, it is difficult to deploy state-of-the-art HRNet-based pose estimation models on resource-constrained edge devices due to the high computational cost (more than 150 GMACs per frame). In this paper, we study efficient architecture design for real-time multi-person pose estimation on edge. We reveal that HRNet's high-resolution branches are redundant for models at the low-computation region via our gradual shrinking experiments. Removing them improves both efficiency and performance. Inspired by this finding, we design LitePose, an efficient single-branch architecture for pose estimation, and introduce two simple approaches to enhance the capacity of LitePose, including Fusion Deconv Head and Large Kernel Convs. Fusion Deconv Head removes the redundancy in high-resolution branches, allowing scale-aware feature fusion with low overhead. Large Kernel Convs significantly improve the model's capacity and receptive field while maintaining a low computational cost. With only 25% computation increment, 7x7 kernels achieve +14.0 mAP better than 3x3 kernels on the CrowdPose dataset. On mobile platforms, LitePose reduces the latency by up to 5.0x without sacrificing performance, compared with prior state-of-the-art efficient pose estimation models, pushing the frontier of real-time multi-person pose estimation on edge. Our code and pre-trained models are released at github.com/mit-han-lab…
姿态估计在以人为本的视觉应用中起着关键作用。然而，由于计算成本高（每帧超过150个GMACs），很难在资源有限的边缘设备上部署最先进的基于HRNet的姿势估计模型。在本文中，我们研究了在边缘上进行实时多人姿势估计的有效架构设计。我们通过逐步缩小的实验发现，HRNet的高分辨率分支对于低计算区域的模型是多余的。去除这些分支后，效率和性能都有所提高。受这一发现的启发，我们设计了LitePose，一个用于姿态估计的高效单分支架构，并介绍了两种简单的方法来提高LitePose的能力，包括Fusion Deconv Head和Large Kernel Convs。Fusion Deconv Head消除了高分辨率分支中的冗余，允许以低开销实现规模感知的特征融合。Large Kernel Convs大大改善了模型的容量和感受野，同时保持了低计算成本。在CrowdPose数据集上，仅用25%的计算增量，7x7内核就比3x3内核实现了+14.0 mAP。在移动平台上，LitePose在不牺牲性能的情况下将延迟降低了5.0倍，与之前最先进的高效姿势估计模型相比，将实时多人姿势估计的前沿推向了边缘。我们的代码和预训练模型发布在github.com/mit-han-lab…。
论文：Flowformer: Linearizing Transformers with Conservation Flows
论文标题：Flowformer: Linearizing Transformers with Conservation Flows
论文时间：13 Feb 2022
所属领域：时间序列
对应任务：时间序列
论文作者：Haixu Wu, Jialong Wu, Jiehui Xu, Jianmin Wang, Mingsheng Long
论文简介：By respectively conserving the incoming flow of sinks for source competition and the outgoing flow of sources for sink allocation, Flow-Attention inherently generates informative attentions without using specific inductive biases./通过分别保存用于源竞争的汇的流入和用于汇分配的源的流出，Flow-Attention内在地产生了信息性的注意，而不使用特定的感应偏差。
论文摘要：Transformers based on the attention mechanism have achieved impressive success in various areas. However, the attention mechanism has a quadratic complexity, significantly impeding Transformers from dealing with numerous tokens and scaling up to bigger models. Previous methods mainly utilize the similarity decomposition and the associativity of matrix multiplication to devise linear-time attention mechanisms. They avoid degeneration of attention to a trivial distribution by reintroducing inductive biases such as the locality, thereby at the expense of model generality and expressiveness. In this paper, we linearize Transformers free from specific inductive biases based on the flow network theory. We cast attention as the information flow aggregated from the sources (values) to the sinks (results) through the learned flow capacities (attentions). Within this framework, we apply the property of flow conservation into attention and propose the Flow-Attention mechanism of linear complexity. By respectively conserving the incoming flow of sinks for source competition and the outgoing flow of sources for sink allocation, Flow-Attention inherently generates informative attentions without using specific inductive biases. Empowered by the Flow-Attention, Flowformer yields strong performance in linear time for wide areas, including long sequence, time series, vision, natural language, and reinforcement learning. The code and settings are available at this repository: github.com/thuml/Flowf…
基于注意力机制的Transformer已经在各个领域取得了令人瞩目的成功。然而，注意力机制具有二次复杂性，极大地阻碍了Transformers处理众多标记和扩展到更大的模型。以前的方法主要是利用相似性分解和矩阵乘法的关联性来设计线性时间注意机制。他们通过重新引入归纳性的偏置，如位置，来避免注意力退化为琐碎的分布，从而牺牲了模型的通用性和表现力。在本文中，我们在流网络理论的基础上对Transformer进行了线性化，不存在特定的归纳性偏置。我们把注意力看作是通过所学的流动能力（注意力）从源（值）到汇（结果）的信息流汇总。在这个框架内，我们将流量守恒的特性应用于注意力，并提出了线性复杂性的流量-注意力机制。通过分别保护源竞争的汇入流量和汇分配的源流出流量，Flow-Attention在不使用特定的归纳偏置的情况下，内在地产生了信息性注意。在Flow-Attention的支持下，Flowformer在线性时间内产生了强大的性能，包括长序列、时间序列、视觉、自然语言和强化学习等广泛领域。代码和设置可在这个资源库中找到：github.com/thuml/Flowf…
论文：HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction
论文标题：HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction
论文时间：CVPR 2022
所属领域：计算机视觉
对应任务：Autonomous Driving，Autonomous Vehicles，Motion Forecasting，motion prediction，Self-Driving Cars，Trajectory Prediction，无人驾驶，自动驾驶，运动预测，自动驾驶汽车，轨迹预测
论文地址：openaccess.thecvf.com/content/CVP…
论文作者：Zikang Zhou, Luyao Ye, JianPing Wang, Kui Wu, Kejie Lu
论文简介：To tackle this challenge, we propose Hierarchical Vector Transformer (HiVT) for fast and accurate multi-agent motion prediction./为了应对这一挑战，我们提出了层次向量Transformer（Hierarchical Vector Transformer，HiVT），用于快速而准确的多代理运动预测。
论文摘要：Accurately predicting the future motions of surrounding traffic agents is critical for the safety of autonomous vehicles. Recently, vectorized approaches have dominated the motion prediction community due to their capability of capturing complex interactions in traffic scenes. However, existing methods neglect the symmetries of the problem and suffer from the expensive computational cost, facing the challenge of making real-time multi-agent motion prediction without sacrificing the prediction performance. To tackle this challenge, we propose Hierarchical Vector Transformer (HiVT) for fast and accurate multi-agent motion prediction. By decomposing the problem into local context extraction and global interaction modeling, our method can effectively and efficiently model a large number of agents in the scene. Meanwhile, we propose a translation-invariant scene representation and rotation-invariant spatial learning modules, which extract features robust to the geometric transformations of the scene and enable the model to make accurate predictions for multiple agents in a single forward pass. Experiments show that HiVT achieves the state-of-the-art performance on the Argoverse motion forecasting benchmark with a small model size and can make fast multi-agent motion prediction.
准确地预测周围交通代理的未来运动对自主车辆的安全至关重要。最近，矢量方法在运动预测领域占主导地位，因为它们能够捕捉到交通场景中的复杂交互作用。然而，现有的方法忽略了问题的对称性，并存在昂贵的计算成本，面临着在不牺牲预测性能的情况下进行实时多代理运动预测的挑战。为了应对这一挑战，我们提出了层次向量Transformer（Hierarchical Vector Transformer，HiVT），用于快速、准确的多Agent运动预测。通过将问题分解为局部环境提取和全局交互建模，我们的方法可以有效地对场景中的大量代理进行建模。同时，我们提出了一个平移不变的场景表示和旋转不变的空间学习模块，这些模块提取了对场景的几何变换具有鲁棒性的特征，并使模型能够在一次向前传递中对多个代理进行准确的预测。实验表明，HiVT在Argoverse运动预测基准上以较小的模型规模达到了最先进的性能，并能进行快速的多Agent运动预测。
论文：A Comprehensive Survey on Graph Anomaly Detection with Deep Learning
论文标题：A Comprehensive Survey on Graph Anomaly Detection with Deep Learning
论文时间：14 Jun 2021
所属领域：机器学习
对应任务：Anomaly Detection，异常检测
代码实现：github.com/XiaoxiaoMa-… , github.com/xiaomingaaa…
论文作者：Xiaoxiao Ma, Jia Wu, Shan Xue, Jian Yang, Chuan Zhou, Quan Z. Sheng, Hui Xiong, Leman Akoglu
论文简介：In this survey, we aim to provide a systematic and comprehensive review of the contemporary deep learning techniques for graph anomaly detection./在这项调查中，我们旨在对当代用于图异常检测的深度学习技术进行系统而全面的回顾。
论文摘要：Anomalies represent rare observations (e.g., data records or events) that deviate significantly from others. Over several decades, research on anomaly mining has received increasing interests due to the implications of these occurrences in a wide range of disciplines. Anomaly detection, which aims to identify rare observations, is among the most vital tasks in the world, and has shown its power in preventing detrimental events, such as financial fraud, network intrusion, and social spam. The detection task is typically solved by identifying outlying data points in the feature space and inherently overlooks the relational information in real-world data. Graphs have been prevalently used to represent the structural information, which raises the graph anomaly detection problem - identifying anomalous graph objects (i.e., nodes, edges and sub-graphs) in a single graph, or anomalous graphs in a database/set of graphs. However, conventional anomaly detection techniques cannot tackle this problem well because of the complexity of graph data. For the advent of deep learning, graph anomaly detection with deep learning has received a growing attention recently. In this survey, we aim to provide a systematic and comprehensive review of the contemporary deep learning techniques for graph anomaly detection. We compile open-sourced implementations, public datasets, and commonly-used evaluation metrics to provide affluent resources for future studies. More importantly, we highlight twelve extensive future research directions according to our survey results covering unsolved and emerging research problems and real-world applications. With this survey, our goal is to create a "one-stop-shop" that provides a unified understanding of the problem categories and existing approaches, publicly available hands-on resources, and high-impact open challenges for graph anomaly detection using deep learning.
异常值代表了明显偏离他人的罕见样本（如数据记录或事件）。几十年来，由于这些现象在广泛的学科中的影响，对异常挖掘的研究受到越来越多的关注。异常检测的目的是识别罕见的观察结果，是世界上最重要的任务之一，并在防止有害事件，如金融欺诈、网络入侵和社会垃圾邮件方面显示了其力量。检测任务通常是通过识别特征空间中的离群数据点来解决的，本质上忽略了现实世界数据中的关系信息。图已经被普遍用来表示结构信息，这就提出了图异常检测问题--识别单个图中的异常图对象（即节点、边和子图），或数据库/图集中的异常图。然而，由于图数据的复杂性，传统的异常检测技术不能很好地解决这个问题。对于深度学习的出现，用深度学习进行图的异常检测最近得到了越来越多的关注。在这项调查中，我们旨在对当代用于图异常检测的深度学习技术进行系统而全面的回顾。我们汇编了开源的实现、公共数据集和常用的评估指标，为未来的研究提供丰富的资源。更重要的是，根据我们的调查结果，我们强调了12个广泛的未来研究方向，包括未解决的和新兴的研究问题以及现实世界的应用。通过这项调查，我们的目标是创建一个 "一站式服务"，提供对问题类别和现有方法的统一理解，公开可用的实践资源，以及使用深度学习的图形异常检测的高影响力的公开挑战。
论文：Small-Text: Active Learning for Text Classification in Python
论文标题：Small-Text: Active Learning for Text Classification in Python
论文时间：21 Jul 2021
所属领域：自然语言处理
对应任务：Active Learning，Classification，Multi-class Classification，Multi Label Text Classification，Multi-Label Text Classification，Text Classification，主动学习，分类，多分类，多标签文本分类，文本分类
论文作者：Christopher Schröder, Lydia Müller, Andreas Niekler, Martin Potthast
论文简介：We present small-text, a simple and modular active learning library, which offers pool-based active learning for single- and multi-label text classification in Python./我们介绍了small-text，一个简单而模块化的主动学习库，它为Python中的单标签和多标签文本分类提供基于pool的主动学习。
论文摘要：We present small-text, a simple and modular active learning library, which offers pool-based active learning for single- and multi-label text classification in Python. It comes with various pre-implemented state-of-the-art query strategies, including some that can leverage the GPU. Clearly defined interfaces allow the combination of a multitude of classifiers, query strategies, and stopping criteria, thereby facilitating a quick mix and match, and enabling a rapid development of both active learning experiments and applications. To make various classifiers accessible in a consistent way, it integrates several well-known existing machine learning libraries, namely, scikit-learn, PyTorch, and huggingface transformers, where the latter integrations are available as optionally installable extensions, making the availability of a GPU competely optional. The library is available under the MIT License at github.com/webis-de/sm…
我们介绍了small-text，一个简单而模块化的主动学习库，它为Python中的单标签和多标签文本分类提供了基于pool的主动学习。它带有各种预先实现的最先进的查询策略，包括一些可以利用GPU的策略。明确定义的接口允许结合多种分类器、查询策略和停止标准，从而促进快速混合和匹配，并使主动学习实验和应用的快速发展。为了使各种分类器能够以一致的方式使用，它集成了几个著名的现有机器学习库，即scikit-learn、PyTorch和huggingface转化器，其中后者的集成可以作为可选择安装的扩展，使GPU的可用性成为可选项。该库在MIT许可下可在 github.com/webis-de/sm… 获取。
我们是 ShowMeAI，致力于传播AI优质内容，分享行业解决方案，用知识加速每一次技术成长！点击查看 历史文章列表，在公众号内订阅话题 #ShowMeAI资讯日报，可接收每日最新推送。点击 专题合辑&电子月刊 快速浏览各专题全集。