使用深度哈希的图像检索中最惊人的成功主要涉及判别模型，该模型需要标签。在本文中，我们使用二进制生成的adver sarial网络（BGAN）将图像以无监督的方式嵌入到二进制代码中。通过将生成对抗网络（GAN）的输入噪声变量限制为二进制且以每个输入图像的特征为条件，BGAN可以同时学习每个图像的二进制表示形式，并生成与原始图像相似的图像。在提出的框架中，我们解决了两个主要问题： 1）如何不松懈地直接生成二进制代码？ 2）如何为二进制表示配备准确率图像检索功能？ 我们通过提出新的符号激活策略和指导学习过程的损失函数来解决这些问题，损失函数包括对抗性损失，内容损失和邻域结构损失的新模型

我们提出了一个简单的正则化方案来处理生成对抗网络（GAN）中的模式缺失和训练不稳定的问题。 关键思想是利用鉴别器学习到的视觉特征。 我们通过向生成器提供由鉴别器提取的真实数据特征来重建真实数据。 将重建损失添加到GAN的目标函数中，以强制生成器可以根据鉴别器的特征进行重建，这有助于明确指导生成器朝着接近实际数据的可能配置进行。 所提出的重建损失提高了GAN的性能，在不同的数据集上产生了更高质量的图像，并且可以轻松地与其他正则化损失函数（例如梯度罚分）组合以提高各种GAN的性能。 我们对不同数据集上广泛采用的DCGAN体系结构和复杂的ResNet体系结构进行了实验，结果表明了该方法的有效性和鲁棒性。

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

半监督学习以改善肺癌的检测 使用生成模型和半监督学习促进肺癌检测 用于训练的数据集 LUNA16数据集（ ） Kaggle数据科学碗2017（ ） 建筑学 结果 结节检测器结果 发电机结果 分类器结果 方法 准确性 监督学习 64％ 半监督学习 87.3％ 资源 Kaggle数据科学碗2017内核 Luna2016-肺结节检测 Tensorflow中的半监督学习GAN [链接] DSB2017 [链接] Keras-GAN [链接] 使用很少的数据构建强大的图像分类模型[link] 贡献者： Dhamodhran（ @ svella9 ） 悉达思R科蒂（ siddharthkoti ） 维杰·蒙达拉吉（ Vijay-Mundaragi ）

Generative Adversarial Networks with Python Deep Learning Generative Models for Image Synthesis and Image Translation by Jason Brownlee 29 step-by-step lessons, 652 pages. intuitions behind models, much more. generate faces, translate photos, more 生成对抗网络是一种深度学习生成模型，可以在一系列图像合成和图像对图像转换问题上实现惊人的照片现实效果。 在这部新的电子书写在友好的机器学习掌握风格，你习惯了，跳过数学，直接跳到获得结果。 通过清晰的解释、标准的 Python 库（Keras和TensorFlow 2）和分步教程课程，您将发现如何为自己的计算机视觉项目开发生成对抗网络。

ELECTRA 中文 预训练 ELECTREA 模型: 基于对抗学习 pretrain Chinese Model code Repost from google official code: 具体使用说明：参考 官方链接 Electra Chinese tiny模型路径 google drive electra-tiny baidu drive electra-tiny code:rs99 模型说明 与 tinyBERT 的 配置相同 generator 为 discriminator的 1/4 How to use official code Steps 修改 configure_pretraining.py 里面的 数据路径、tpu、gpu 配置 修改 model_size：可在 code/util/training_utils.py 里面 自行定义模型大小 数据输入格式：原始的

On the steerability of generative adversarial networks.pptx

两年一度的计算机视觉国际顶级会议 International Conference on Computer Vision（ICCV 2017）在意大利威尼斯开幕。Google Brain 研究科学家Ian Goodfellow在会上作为主题为《生成对抗网络(Generative Adversarial Networks)》的Tutorial 最新演讲, 介绍了GAN的原理和最新的应用。

Learning Generative Adversarial Networks_Next generation deep learning simplified First published: October 2017 | 203页 | pdf格式

This book is for data scientists, machine learning (ML) developers, and deep learning practitioners looking for a quick reference to tackle challenges and tasks in the GAN domain. Familiarity with machine learning concepts and a working knowledge of the Python programming language will help you get the most out of the book.