计算机视觉作业-2018Spring 内容 混合图像。 拐角检测。 标度空间斑点检测。 :场景分类器 视觉词袋模型和最近邻分类器(kNN)。 视觉单词袋模型和判别式分类器(SVM)。 在ImageNet上使用ResNet50预训练的权重进行转移学习。 在ImageNet上使用VGG16预训练的权重进行转移学习。 在ImageNet上使用GoogleNet预训练的权重进行转移学习。 消失点检测。 单视图计量。 使用参考对象的高度查找图像中对象的高度。 图像拼接。 贡献者 和(
2021-10-02 11:50:07 18.87MB python computer-vision deep-learning svm
1
实时语音克隆 该存储库是使用实时工作的声码器实现的(SV2TTS)的实现。 如果您好奇或正在寻找我未记录的信息,请随时检查。 通常,我建议您快速浏览一下引言之外的数字。 SV2TTS是一个三阶段的深度学习框架,它允许从几秒钟的音频中创建语音的数字表示,并使用它来调节经过训练的文本到语音模型,以推广到新的语音。 视频演示(单击图片): 已实施文件 网址 指定 标题 实施源 SV2TTS 将学习从演讲者验证转移到多演讲者语音合成 这个回购 WaveRNN(声码器) 高效的神经音频合成 Tacotron 2(合成器) 基于梅尔谱图预测的条件波网自然合成TTS GE2E(编码器)
2021-10-01 07:30:19 955KB python deep-learning tensorflow pytorch
1
Generative modeling is one of the hottest topics in AI. It’s now possible to teach a machine to excel at human endeavors such as painting, writing, and composing music. With this practical book, machine-learning engineers and data scientists will discover how to re-create some of the most impressive examples of generative deep learning models, such as variational autoencoders,generative adversarial networks (GANs), encoder-decoder models, and world models. Author David Foster demonstrates the inner workings of each technique, starting with the basics of deep learning before advancing to some of the most cutting-edge algorithms in the field. Through tips and tricks, you’ll understand how to make your models learn more efficiently and become more creative. Discover how variational autoencoders can change facial expressions in photos Build practical GAN examples from scratch, including CycleGAN for style transfer and MuseGAN for music generation Create recurrent generative models for text generation and learn how to improve the models using attention Understand how generative models can help agents to accomplish tasks within a reinforcement learning setting Explore the architecture of the Transformer (BERT, GPT-2) and image generation models such as ProGAN and StyleGAN
2021-09-30 21:08:02 39.18MB deep learning
1
Chapter 1, Introduction to Deep Learning, speaks all about refreshing general concepts and terminology associated with deep learning in a simple way without too much math and equations. Also, it will show how deep learning network has evolved throughout the years and how they are making an inroad in the unsupervised domain with the emergence of generative models. Chapter 2, Unsupervised Learning with GAN, shows how Generative Adversarial Networks work and speaks about the building blocks of GANs. It will show how deep learning networks can be used on semi-supervised domains, and how you can apply them to image generation and creativity. GANs are hard to train. This chapter looks at some techniques to improve the training/learning process. Chapter 3, Transfer Image Style Across Various Domains, speaks about being very creative with simple but powerful CGAN and CycleGAN models. It explains the use of Conditional GAN to create images based on certain characteristics or conditions. This chapter also discusses how to overcome model collapse problems by stabilizing your network training using BEGAN. And finally, it covers transferring styles across different domains (apple to orange; horse to zebra) using CycleGAN. Chapter 4, Building Realistic Images from Your Text, presents the latest approach of stacking Generative Adversarial Networks into multiple stages to decompose the problem of text to image synthesis into two more manageable subproblems with StackGAN. The chapter also shows how DiscoGAN successfully transfers styles across multiple domains to generate output images of handbags from the given input of shoe images or to perform gender transformations of celebrity images. Chapter 5, Using Various Generative Models to Generate Images, introduces the concept of a pretrained model and discusses techniques for running deep learning and generative models over large distributed systems using Apache Spark. We will then enhance the resolution of low quality images using pr
2021-09-30 20:59:57 10.73MB 对抗神经网络
1
对计算机视觉(cv)以及自然语言处理(NLP)两个热门的方向的技术进行总结概述.
2021-09-29 21:00:48 5.28MB 深度学习
1
牙齿检测仪 数据集目前是私有的,但是是由一位外科医生使用VoTT进行标记制作的。 导出是使用Tensorflow Pascal VOC格式进行的 该项目分为两个任务: 检测牙齿修复,牙髓治疗和植入物(模型/治疗) 检测牙齿并确定其ISO牙科标记(型号/索引) 安装 从Google云端硬盘下载数据集(目前数据集是私有的) 安装tensorflow对象检测: : 安装Cloud SDK以在Google Cloud 上运行 pip install -r requirements.txt # Tensorflow Object Detection API git clone git@github.com:tensorflow/models.git git clone https://github.com/cocodataset/cocoapi.git cd cocoapi/Python
2021-09-29 19:48:54 11.49MB deep-learning tensorflow health neural-networks
1
随着深度神经网络(DNN)在现实世界的应用中变得越来越普遍,有可能故意用不会欺骗人类的数据“愚弄”它们,这提供了一种新的攻击向量。这本实用的书籍探讨了现实世界的场景,其中DNN(大部分AI固有的算法)每天用于处理图像,音频和视频数据。 作者Katy Warr考虑了攻击动机,这种对抗性输入带来的风险,以及增强AI对这些攻击的稳健性的方法。如果您是开发DNN算法的数据科学家,一位对如何使AI系统更具弹性的攻击感兴趣的安全架构师,或者对人工和生物感知之间的差异着迷的人,本书适合您。 •深入研究DNN并发现它们如何被对抗性输入欺骗 •调查用于生成能够欺骗DNN的对抗性输入的方法 •探索真实场景并模拟对抗性威胁 •评估神经网络的稳健性;学习提高AI系统对抗对抗性数据的弹性的方法 •检查AI在未来几年内如何更好地模仿人类感知
2021-09-29 17:12:01 19.43MB 深度学习 Deep Learning 神经网络
1
时间序列异常检测:深度学习方法评估。 该存储库的目标是为多种最新深度学习方法的时间序列数据异常检测提供基准测试管道。 实施算法 名称 纸 LSTM-AD ,ESANN 2015 LSTM-ED ,ICML 2016 自动编码器 ,DaWaK 2002 甜甜圈 ,WWW 2018 REBM ,ICML 2016 达格 ,ICLR 2018 LSTM-DAGMM 使用 -Autoencoder而不是神经网络自动编码器扩展 用法 git clone git://github.com/KDD-OpenSource/DeepADoTS.git virtualenv venv -
2021-09-29 16:13:32 54KB timeseries deep-learning time-series tensorflow
1
使用google BERT进行CoNLL-2003 NER! 为了获得更好的性能,您可以尝试使用fennlp,有关更多详细信息,请参见fennlp。 BERT-NER版本2使用Google的BERT进行命名实体识别(CoNLL-2003作为数据集)。 原始版本(请参阅old_version以获得更多详细信息)包含一些硬代码,并且缺少相应的注释,因此不方便理解。 因此,在此更新版本中,有一些新的思想和技巧(关于数据预处理和图层设计)可以帮助您快速实现微调模型(您只需要
2021-09-29 15:08:15 2.09MB Python Deep Learning
1
Deep LearningUFLDL 教程(中文版)Deep LearningUFLDL 教程(中文版)
2021-09-29 10:42:34 4MB Deep Learning
1