海思3559a学习.md

海思3559a 海思Hi3559AV100/Hi3519AV100 NNIE深度学习模块开发与调试记录

Playing Mountain Car Using Actor-Critic Method.md

Playing Mountain Car Using Actor-Critic MethodPlaying Mountain Car Using Actor-Critic Method

基于动态规划的强化学习.md

Dynamic Programming Based Reinforcement Learning Methods Reinforcement Learning Policy Iteration Learning

Deep Convolutional Generative Adversarial Networks.md

we introduced the basic ideas behind how GANs work. We showed that they can draw samples from some simple, easy-to-sample distribution, like a uniform or normal distribution, and transform them into samples that appear to match the distribution of some dataset. And while our example of matching a 2D Gaussian distribution got the point across, it is not especially exciting.

生成对抗网络.md GAN

Generative Adversarial Networks Throughout most of this book, we have talked about how to make predictions. In some form or another, we used deep neural networks learned mappings from data points to labels. This kind of learning is called discriminative learning, as in, we'd like to be able to discriminate between photos cats and photos of dogs. Classifiers and regressors are both examples of discriminative learning. And neural networks trained by backpropagation have upended everything we thought we knew about discriminative learning on large complicated datasets. Classification accuracies on high-res images has gone from useless to human-level (with some caveats) in just 5-6 years. We will spare you another spiel about all the other discriminative tasks where deep neural networks do astoundingly well.

图像分类案例2.md

在本节中，我们将解决Kaggle竞赛中的犬种识别挑战，比赛的网址是https://www.kaggle.com/c/dog-breed-identification 在这项比赛中，我们尝试确定120种不同的狗。该比赛中使用的数据集实际上是著名的ImageNet数据集的子集。

图像分类案例1.md

现在，我们将运用在前面几节中学到的知识来参加Kaggle竞赛，该竞赛解决了CIFAR-10图像分类问题。比赛网址是https://www.kaggle.com/c/cifar-10

图像风格迁移.md pytorch

在本节中，我们将介绍如何使用卷积神经网络自动将某图像中的样式应用在另一图像之上，即样式迁移（style transfer）[1]。这里我们需要两张输入图像，一张是内容图像，另一张是样式图像，我们将使用神经网络修改内容图像使其在样式上接近样式图像。图9.12中的内容图像为本书作者在西雅图郊区的雷尼尔山国家公园（Mount Rainier National Park）拍摄的风景照，而样式图像则是一副主题为秋天橡树的油画。最终输出的合成图像在保留了内容图像中物体主体形状的情况下应用了样式图像的油画笔触，同时也让整体颜色更加鲜艳。

目标检测和边界框.md

锚框 目标检测算法通常会在输入图像中采样大量的区域，然后判断这些区域中是否包含我们感兴趣的目标，并调整区域边缘从而更准确地预测目标的真实边界框（ground-truth bounding box）。不同的模型使用的区域采样方法可能不同。这里我们介绍其中的一种方法：它以每个像素为中心生成多个大小和宽高比（aspect ratio）不同的边界框。这些边界框被称为锚框（anchor box）。我们将在后面基于锚框实践目标检测。

梯度下降.md pytorch

一维梯度下降 证明：沿梯度反方向移动自变量可以减小函数值 学习率 局部最小值 多维梯度下降 自适应方法