This repository has been archived by the owner on Jan 24, 2024. It is now read-only.
基于飞桨2.0的应用案例教程（通过DCGAN实现人脸图像生成）代码提交 #923
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
通过DCGAN实现人脸图像生成
|
|
TCChenlong
reviewed
Nov 14, 2020
| "\n", | ||
| "生成对抗网络（Generative Adversarial Network [1]，简称GAN）是非监督式学习的一种方法，通过让两个神经网络相互博弈的方式进行学习。该方法最初由 lan·Goodfellow 等人于2014年提出，原论文见 [Generative Adversarial Network](https://arxiv.org/abs/1406.2661)。\n", | ||
| "\n", | ||
| " 生成对抗网络由一个生成网络与一个判别网络组成。生成网络从潜在空间（latent space）中随机采样作为输入，其输出结果需要尽量模仿训练集中的真实样本。判别网络的输入为真实样本或生成网络的输出，其目的是将生成网络的输出从真实样本中尽可能分辨出来。而生成网络则要尽可能地欺骗判别网络。两个网络相互对抗、不断调整参数，其目的是将生成网络生成的样本和真实样本尽可能的区分开[2] ）。 \n", |
There was a problem hiding this comment.
两个网络相互对抗、不断调整参数，其目的是将生成网络的输出从真实样本中尽可能分辨出来。
| "\n", | ||
| "对于生成器网络，$z$为从标准正态分布采样的潜在空间向量。$G(z)$表示生成器函数，该函数将矢量$z$映射到数据空间。生成器的目标是拟合训练数据($p_{data}$)的分布，以便可以从该估计分布中生成假样本($p_g$)。\n", | ||
| "\n", | ||
| "所以，$D(G(z))$是生成器$G$输出是真实的图像的概率。如Goodfellow的论文所述，$D$和$G$玩一个minimax游戏，其中$D$尝试最大化其正确分类真假的可能性$logD(x)$，以及$G$试图最小化以下可能性$D$会预测其输出是假的$log(1-D(G(x)))$。\n", |
| "\n", | ||
| "> $\\underset{G}{\\text{min}} \\underset{D}{\\text{max}}V(D,G) = \\mathbb{E}_{x\\sim p_{data}(x)}\\big[logD(x)\\big] + \\mathbb{E}_{z\\sim p_{z}(z)}\\big[log(1-D(G(z)))\\big]$\n", | ||
| "\n", | ||
| "从理论上讲，此minimax游戏的解决方案是$p_g = p_{data}$，鉴别者会盲目猜测输入是真实的还是假的。但是，GAN的收敛理论仍在积极研究中，实际上GAN常常会遇到梯度消失/爆炸问题。 \n", |
| "\n", | ||
| "生成对抗网络（Generative Adversarial Network [1]，简称GAN）是非监督式学习的一种方法，通过让两个神经网络相互博弈的方式进行学习。该方法最初由 lan·Goodfellow 等人于2014年提出，原论文见 [Generative Adversarial Network](https://arxiv.org/abs/1406.2661)。\n", | ||
| "\n", | ||
| " 生成对抗网络由一个生成网络与一个判别网络组成。生成网络从潜在空间（latent space）中随机采样作为输入，其输出结果需要尽量模仿训练集中的真实样本。判别网络的输入为真实样本或生成网络的输出，其目的是将生成网络的输出从真实样本中尽可能分辨出来。而生成网络则要尽可能地欺骗判别网络。两个网络相互对抗、不断调整参数，其目的是将生成网络生成的样本和真实样本尽可能的区分开[2] ）。 \n", |
There was a problem hiding this comment.
判别网络的输入为真实样本或生成网络的输出，其目的是将生成网络的输出从真实样本中尽可能分辨出来。
这么说似乎不是很准确，建议改为：
判别网络的输入为真实样本或生成网络的输出，其目的是将尽可能的分辨输入为真实样本或生成网络的输出。
| "\n", | ||
| " 生成对抗网络由一个生成网络与一个判别网络组成。生成网络从潜在空间（latent space）中随机采样作为输入，其输出结果需要尽量模仿训练集中的真实样本。判别网络的输入为真实样本或生成网络的输出，其目的是将生成网络的输出从真实样本中尽可能分辨出来。而生成网络则要尽可能地欺骗判别网络。两个网络相互对抗、不断调整参数，其目的是将生成网络生成的样本和真实样本尽可能的区分开[2] ）。 \n", | ||
| " \n", | ||
| "让$x$是代表图像的数据。$D(x)$是判别器网络，输出的概率为$x$来自训练数据还是生成器。在这里输入$D(x)$的$x$是CHW大小为3x128x128的图像。使得$x$来自训练数据时$D(x)$尽量接近1，$x$来自生成器时$D(x)$尽量接近0。$D(x)$也可以被认为是传统的二进制分类器。\n", |
There was a problem hiding this comment.
这一段也可以改一下：
假设 x 为CHW格式，大小为3x128x128的图像数据，D为判别器网络，D(x) 为 𝑥 来自训练数据还是生成器。当 𝑥 来自训练数据时 𝐷(𝑥) 尽量接近1， 𝑥 来自生成器时 𝐷(𝑥) 尽量接近0。 因此，𝐷(𝑥) 也可以被认为是传统的二分类器。
| "source": [ | ||
| "\n", | ||
| "train_dataset = DataGenerater()\n", | ||
| "img = fluid.layers.data(name='img', shape=[None,3,img_dim,img_dim], dtype='float32')\n", |
There was a problem hiding this comment.
可以改用 paddle.static.data
| "source": [ | ||
| "### 3.3 权重初始化\n", | ||
| "在 DCGAN 论文中，作者指定所有模型权重应从均值为0、标准差为0.02的正态分布中随机初始化。 \n", | ||
| "在Fluid中，调用fluid.initializer.NormalInitializer实现initialize设置" |
| }, | ||
| "outputs": [], | ||
| "source": [ | ||
| "import paddle.fluid as fluid\n", |
| "class Discriminator(paddle.nn.Layer):\n", | ||
| " def __init__(self):\n", | ||
| " super(Discriminator, self).__init__()\n", | ||
| " self.conv_1 = paddle.nn.Conv2D(3,64,4,2,1,bias_attr=False,weight_attr=fluid.ParamAttr(name=\"d_conv_weight_1_\",initializer=conv_initializer,trainable=True))\n", |
There was a problem hiding this comment.
fluid.ParamAttr -> paddle.ParamAttr
下同
| "class Generator(paddle.nn.Layer):\n", | ||
| " def __init__(self):\n", | ||
| " super(Generator, self).__init__()\n", | ||
| " self.conv_1 = paddle.nn.Conv2DTranspose(100,512,4,1,0,bias_attr=False,weight_attr=fluid.ParamAttr(name=\"g_dconv_weight_1_\",initializer=conv_initializer,trainable=True))\n", |
There was a problem hiding this comment.
fluid.ParamAttr -> paddle.ParamAttr
下同
根据修改意见，进行文档改进
TCChenlong
reviewed
Nov 27, 2020
| "collapsed": false | ||
| }, | ||
| "source": [ | ||
| "### 2.3 数据集预处理\n", |
| "collapsed": false | ||
| }, | ||
| "source": [ | ||
| "## 8 项目总结\n", |
| "collapsed": false | ||
| }, | ||
| "source": [ | ||
| "## 9 参考文献\n", |
| " * 取消 pooling 层：在网络中，所有的pooling层使用步幅卷积（strided convolutions）(判别器)和微步幅度卷积（fractional-strided convolutions）(生成器)进行替换。\n", | ||
| " * 加入 batch normalization：在生成器和判别器中均加入batchnorm。\n", | ||
| " * 使用全卷积网络：去掉了FC层，以实现更深的网络结构。\n", | ||
| " * 激活函数：在生成器（G）中，最后一层使用Tanh函数，其余层采用 ReLu 函数 ; 判别器（D）中都采用LeakyReLu。 \n", |
| "DCGAN是深层卷积网络与 GAN 的结合，其基本原理与 GAN 相同，只是将生成网络和判别网络用两个卷积网络（CNN）替代。为了提高生成样本的质量和网络的收敛速度，论文中的 DCGAN 在网络结构上进行了一些改进：\n", | ||
| "\n", | ||
| " * 取消 pooling 层：在网络中，所有的pooling层使用步幅卷积（strided convolutions）(判别器)和微步幅度卷积（fractional-strided convolutions）(生成器)进行替换。\n", | ||
| " * 加入 batch normalization：在生成器和判别器中均加入batchnorm。\n", |
| "source": [ | ||
| "conv_initializer=paddle.nn.initializer.Normal(mean=0.0, std=0.02)\n", | ||
| "bn_initializer=paddle.nn.initializer.Normal(mean=1.0, std=0.02)\n", | ||
| ")" |
LielinJiang
reviewed
Dec 1, 2020
| "import paddle\n", | ||
| "import paddle.nn.functional as F\n", | ||
| "\n", | ||
| "class Discriminator(paddle.nn.Layer):\n", |
LielinJiang
reviewed
Dec 1, 2020
| "class Discriminator(paddle.nn.Layer):\n", | ||
| " def __init__(self):\n", | ||
| " super(Discriminator, self).__init__()\n", | ||
| " self.conv_1 = paddle.nn.Conv2D(3,64,4,2,1,bias_attr=False,weight_attr=paddle.ParamAttr(name=\"d_conv_weight_1_\",initializer=conv_initializer,trainable=True))\n", |
There was a problem hiding this comment.
分两行把，先定义ParamAttr，再定义Conv2D。bias_attr默认值为None。trainable默认值为True，不修改默认值的情况下可以不写。
LielinJiang
reviewed
Dec 1, 2020
| "class Generator(paddle.nn.Layer):\n", | ||
| " def __init__(self):\n", | ||
| " super(Generator, self).__init__()\n", | ||
| " self.conv_1 = paddle.nn.Conv2DTranspose(100,512,4,1,0,bias_attr=False,weight_attr=paddle.ParamAttr(name=\"g_dconv_weight_1_\",initializer=conv_initializer,trainable=True))\n", |
ceci3
reviewed
Dec 1, 2020
| "\n", | ||
| " 生成对抗网络由一个生成网络与一个判别网络组成。生成网络从潜在空间（latent space）中随机采样作为输入，其输出结果需要尽量模仿训练集中的真实样本。判别网络的输入为真实样本或生成网络的输出，其目的是将尽可能的分辨输入为真实样本或生成网络的输出。而生成网络则要尽可能地欺骗判别网络。两个网络相互对抗、不断调整参数。 \n", | ||
| " \n", | ||
| "让$x$是代表图像的数据。$D(x)$是判别器网络，输出的概率为$x$来自训练数据还是生成器。假设$x$为CHW格式，大小为3x128x128的图像数据，D为判别器网络，$D(x)$为$𝑥$来自训练数据还是生成器。当$𝑥$来自训练数据时$𝐷(𝑥)$尽量接近1，$𝑥$来自生成器时$𝐷(𝑥)$尽量接近0。 因此，$𝐷(𝑥)$也可以被认为是传统的二分类器。\n", |
LielinJiang
approved these changes
Dec 17, 2020
wadefelix
pushed a commit
to wadefelix/FluidDoc
that referenced
this pull request
Jul 30, 2021
* Create dcgan_face.ipynb 通过DCGAN实现人脸图像生成 * 进一步改进格式 * 改为paddle.nn * bug修复 * 更新生成器G和判别器D迭代图 * Update dcgan_face.ipynb 根据修改意见，进行文档改进 * 二次修改 根据修改意见进行第二次修改 * 进一步修改 根据修改意见第三次修改 * 12-11修改 根据修改意见再一次修改
TCChenlong
added a commit
to PaddlePaddle/docs
that referenced
this pull request
Jul 30, 2021
….0_docs to docs/practices (#3694) * image segmentation with u-net notebook (PaddlePaddle/book#870) * image segmentation with u-net notebook * update segmentation notebook * imdb_bow_classification added (PaddlePaddle/book#871) * dynamic graph example added (PaddlePaddle/book#876) * cnn based image classification added, minor changes to dygraph example (PaddlePaddle/book#877) * upgrade code that in image_segmentation from 2.0-alpha to 2.0-beta (PaddlePaddle/book#879) * image segmentation with u-net notebook * update segmentation notebook * upgrade code from 2.0-alpha to 2.0-beta * add getting started doc (PaddlePaddle/book#880) * image segmentation with u-net notebook * update segmentation notebook * upgrade code from 2.0-alpha to 2.0-beta * add getting started doc * delete invalid files * add tow models with develop-paddle (PaddlePaddle/book#881) * seq2seq with attention added (PaddlePaddle/book#882) * seq2seq with attention added * image_search use latest API * update seq2seq with attention * seq2seq with attention updated (PaddlePaddle/book#884) * add linear_regression.ipynb (PaddlePaddle/book#885) * fix_lenet_docs test=develop (PaddlePaddle/book#886) * add high level api doc (PaddlePaddle/book#887) * upgrade code to 2.0-beta * add high level api doc * fix_warning_info (PaddlePaddle/book#888) * fix_test_loader (PaddlePaddle/book#889) * fix_test_loader * fix_mnist_wrongs * update several notebooks (PaddlePaddle/book#890) * change from Pool2D to AdaptiveAvgPool2d in image_search * hello paddle updated * convnet_image_classification updated * dynamic_graph updated * convnet_image_classification updated * imdb bow classification updated * Fix style (PaddlePaddle/book#891) * fix_some_wrongs * fix_logs * minor wording changes (PaddlePaddle/book#892) * Course (PaddlePaddle/book#883) * add save_model * update api * change api name * change api name * add define callback/metric/loss chapter (PaddlePaddle/book#893) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * update several notebooks (PaddlePaddle/book#894) * rerun code with 2.0-beta whl (PaddlePaddle/book#895) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * rerun code with 2.0-beta whl * fix lr (PaddlePaddle/book#896) * fix docs for beta and change docs style (PaddlePaddle/book#900) * change version from dev to 2.0Beta (PaddlePaddle/book#899) * change version from dev to 2.0Beta * change version * fix linear_regression (PaddlePaddle/book#898) * fix lr 9.12 * fix linear_regression * Fix Bug: modify PetModel to PetNet (PaddlePaddle/book#901) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * rerun code with 2.0-beta whl * fix bug: modify PetModel to PetNet * [Bug Fix]change paddle.disable_static() position (PaddlePaddle/book#902) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * rerun code with 2.0-beta whl * fix bug: modify PetModel to PetNet * Fix BUG: change paddle.disable_static() position * add addition_rnn doc (PaddlePaddle/book#916) * Create addition_rnn.ipynb Sequence to sequence learning for performing number addition * fix some typo fix some typo * Update addition_rnn.ipynb * 基于飞桨2.0的应用案例教程（通过AutoEncoder实现时序数据异常检测）代码提交 (PaddlePaddle/book#914) * '提交数据文件' * upload ipynb * 对ipynbn修改 * 改用2.0 load 标题下署名，数据集文件删除 * 通过OCR实现验证码识别 代码提交 (PaddlePaddle/book#917) * init OCR.ipynb * 修改作者格式和一处描述 * 1. 更改pp为paddle。 2. 统一“预测”、“推理”术语为“预测”。 3. 简化文字部分描述。 * 添加super_resolution_sub_pixel (PaddlePaddle/book#910) * 添加super_resolution_sub_pixel * 添加super_resolution_sub_pixel * 修改错别字等 * 添加作者信息 * update codes to use 2.0RC (PaddlePaddle/book#921) * upgrade some code from 2.0-beta to 2.0-rc (PaddlePaddle/book#922) * 基于飞桨2.0的关键点检测方法及应用之（人脸关键点检测）代码提交 (PaddlePaddle/book#919) * upload facial_landmark.ipynb to landmark_detection * upgrade code in facial_landmark.ipynb * reviewed modify in facial_landmark.ipynb * fix guides (PaddlePaddle/book#925) * update save_model to 2.0rc (PaddlePaddle/book#924) * update save_model to 2.0rc * update save_model to 2.0rc * udpate to reflect 2.0RC version numbers (PaddlePaddle/book#926) * update to rc (PaddlePaddle/book#928) * update to rc (PaddlePaddle/book#929) * fix bugs (PaddlePaddle/book#930) * update hapi and image_segmentation (PaddlePaddle/book#931) * OCR案例更新 (PaddlePaddle/book#927) * 根据最新反馈建议新增了以下修改： 1.添加数据集压缩包下载链接和使用方法 2.测试pillow在paddlepaddle安装后是否需要单独安装 3.在目录下添加测试数据 4.更换第三方解码器并实现青春版，待2.0更新ctc-decode后再更新该处代码。 * 适配2.0RC0 * Update the paddle version to 2.0.0-rc0 (PaddlePaddle/book#932) Update the paddle version to 2.0.0-rc0 * update to rc (PaddlePaddle/book#933) * update to rc1 (PaddlePaddle/book#940) * update to rc1 * remote doc * update lr to 2.0rc1 (PaddlePaddle/book#941) * correct convnet iamge classify example (PaddlePaddle/book#942) * 基于飞桨2.0的应用案例教程（通过DCGAN实现人脸图像生成）代码提交 (PaddlePaddle/book#923) * Create dcgan_face.ipynb 通过DCGAN实现人脸图像生成 * 进一步改进格式 * 改为paddle.nn * bug修复 * 更新生成器G和判别器D迭代图 * Update dcgan_face.ipynb 根据修改意见，进行文档改进 * 二次修改 根据修改意见进行第二次修改 * 进一步修改 根据修改意见第三次修改 * 12-11修改 根据修改意见再一次修改 * update to rc1 (PaddlePaddle/book#944) * update to rc1 * update to rc1 * fix some bugs (PaddlePaddle/book#945) * fix some bugs * fix some bugs * fix some bugs * update images (PaddlePaddle/book#946) * 基于飞桨2.0的应用案例教程（通过CycleGAN实现图像风格迁移）代码提交 (PaddlePaddle/book#938) * add CycleGAN folder * delete CycleGAN folder * add CycleGAN floder * add CycleGAN.ipynb * delete other files * move the CycleGAN folder * add cyclegan.ipynb * replace cyclegan.ipynb * replace cyclegan.ipynb * replace cyclegan.ipynb * replace cyclegan.ipynb * update cyclegan.ipynb * Signed-off-by: ctkindle <[email protected]> * Signed-off-by: ctkindle <[email protected]> * Signed-off-by: ctkindle <[email protected]> * use min() instead of expression * use min() instead of expression * update to 2.0 (PaddlePaddle/book#948) * update to 2.0 * fix typo bugs * update to 2.0 (PaddlePaddle/book#949) * update to 2.0 * update OCR * update ocr * 点云分类PointNet文档 (PaddlePaddle/book#958) * 点云分类PointNet * Update pointnet.ipynb * Update pointnet.ipynb * 使用协同过滤实现电影推荐 (PaddlePaddle/book#960) * Add files via upload * Delete Collaborative filtering.ipynb * Create ttes.py * Delete ttes.py * Create test.py * Add files via upload * Delete test.py * Add files via upload * Delete Collaborative filtering.ipynb * 飞桨2.0实例教程——使用预训练词向量 (PaddlePaddle/book#934) * 飞桨2.0实例教程——使用预训练词向量 * 飞桨2.0实例教程——使用预训练词向量 删除了1312-1315行多余代码，训练和评测verbose改为1并重新生成了输出。 * Delete pretrained_word_embeddings.ipynb * 飞桨2.0应用案例——使用预训练的词向量 删除了原先的位置，增加了预训练词向量文件夹 * Update pretrained_word_embeddings.ipynb 修改了两处说明（Line9,190），修改了最近修改时间（Line15） * modified based on the latest comments * 强化学习——Actor Critic Method (PaddlePaddle/book#961) * Create Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * update to 2.0.1 (PaddlePaddle/book#962) * update to 2.0.1 * fix index * fix bugs (PaddlePaddle/book#969) * update_to_2.1 (PaddlePaddle/book#977) * update_to_2.1 * update practice * update practice * Advantage Actor-Critic(A2C) (PaddlePaddle/book#973) * Create Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Deep_Deterministic_Policy_Gradient_(DDPG) (PaddlePaddle/book#967) * Create Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * rename it as docs/practices Co-authored-by: Chunyu Zhang <[email protected]> Co-authored-by: jzhang533 <[email protected]> Co-authored-by: Chen Long <[email protected]> Co-authored-by: swtkiwi <[email protected]> Co-authored-by: Chen Long <[email protected]> Co-authored-by: dingjiaweiww <[email protected]> Co-authored-by: jm12138 <[email protected]> Co-authored-by: Reatris <[email protected]> Co-authored-by: GT-Zhang <[email protected]> Co-authored-by: Ralph LU <[email protected]> Co-authored-by: zzs95 <[email protected]> Co-authored-by: ZMpursue <[email protected]> Co-authored-by: FutureSI <[email protected]> Co-authored-by: Zhihao Cao <[email protected]> Co-authored-by: HUANGCHENGAI <[email protected]> Co-authored-by: WinSun <[email protected]> Co-authored-by: EastSmith <[email protected]>
wadefelix
added a commit
to wadefelix/FluidDoc
that referenced
this pull request
Jul 30, 2021
….0_docs to docs/practices (PaddlePaddle#3694) * image segmentation with u-net notebook (PaddlePaddle/book#870) * image segmentation with u-net notebook * update segmentation notebook * imdb_bow_classification added (PaddlePaddle/book#871) * dynamic graph example added (PaddlePaddle/book#876) * cnn based image classification added, minor changes to dygraph example (PaddlePaddle/book#877) * upgrade code that in image_segmentation from 2.0-alpha to 2.0-beta (PaddlePaddle/book#879) * image segmentation with u-net notebook * update segmentation notebook * upgrade code from 2.0-alpha to 2.0-beta * add getting started doc (PaddlePaddle/book#880) * image segmentation with u-net notebook * update segmentation notebook * upgrade code from 2.0-alpha to 2.0-beta * add getting started doc * delete invalid files * add tow models with develop-paddle (PaddlePaddle/book#881) * seq2seq with attention added (PaddlePaddle/book#882) * seq2seq with attention added * image_search use latest API * update seq2seq with attention * seq2seq with attention updated (PaddlePaddle/book#884) * add linear_regression.ipynb (PaddlePaddle/book#885) * fix_lenet_docs test=develop (PaddlePaddle/book#886) * add high level api doc (PaddlePaddle/book#887) * upgrade code to 2.0-beta * add high level api doc * fix_warning_info (PaddlePaddle/book#888) * fix_test_loader (PaddlePaddle/book#889) * fix_test_loader * fix_mnist_wrongs * update several notebooks (PaddlePaddle/book#890) * change from Pool2D to AdaptiveAvgPool2d in image_search * hello paddle updated * convnet_image_classification updated * dynamic_graph updated * convnet_image_classification updated * imdb bow classification updated * Fix style (PaddlePaddle/book#891) * fix_some_wrongs * fix_logs * minor wording changes (PaddlePaddle/book#892) * Course (PaddlePaddle/book#883) * add save_model * update api * change api name * change api name * add define callback/metric/loss chapter (PaddlePaddle/book#893) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * update several notebooks (PaddlePaddle/book#894) * rerun code with 2.0-beta whl (PaddlePaddle/book#895) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * rerun code with 2.0-beta whl * fix lr (PaddlePaddle/book#896) * fix docs for beta and change docs style (PaddlePaddle/book#900) * change version from dev to 2.0Beta (PaddlePaddle/book#899) * change version from dev to 2.0Beta * change version * fix linear_regression (PaddlePaddle/book#898) * fix lr 9.12 * fix linear_regression * Fix Bug: modify PetModel to PetNet (PaddlePaddle/book#901) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * rerun code with 2.0-beta whl * fix bug: modify PetModel to PetNet * [Bug Fix]change paddle.disable_static() position (PaddlePaddle/book#902) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * rerun code with 2.0-beta whl * fix bug: modify PetModel to PetNet * Fix BUG: change paddle.disable_static() position * add addition_rnn doc (PaddlePaddle/book#916) * Create addition_rnn.ipynb Sequence to sequence learning for performing number addition * fix some typo fix some typo * Update addition_rnn.ipynb * 基于飞桨2.0的应用案例教程（通过AutoEncoder实现时序数据异常检测）代码提交 (PaddlePaddle/book#914) * '提交数据文件' * upload ipynb * 对ipynbn修改 * 改用2.0 load 标题下署名，数据集文件删除 * 通过OCR实现验证码识别 代码提交 (PaddlePaddle/book#917) * init OCR.ipynb * 修改作者格式和一处描述 * 1. 更改pp为paddle。 2. 统一“预测”、“推理”术语为“预测”。 3. 简化文字部分描述。 * 添加super_resolution_sub_pixel (PaddlePaddle/book#910) * 添加super_resolution_sub_pixel * 添加super_resolution_sub_pixel * 修改错别字等 * 添加作者信息 * update codes to use 2.0RC (PaddlePaddle/book#921) * upgrade some code from 2.0-beta to 2.0-rc (PaddlePaddle/book#922) * 基于飞桨2.0的关键点检测方法及应用之（人脸关键点检测）代码提交 (PaddlePaddle/book#919) * upload facial_landmark.ipynb to landmark_detection * upgrade code in facial_landmark.ipynb * reviewed modify in facial_landmark.ipynb * fix guides (PaddlePaddle/book#925) * update save_model to 2.0rc (PaddlePaddle/book#924) * update save_model to 2.0rc * update save_model to 2.0rc * udpate to reflect 2.0RC version numbers (PaddlePaddle/book#926) * update to rc (PaddlePaddle/book#928) * update to rc (PaddlePaddle/book#929) * fix bugs (PaddlePaddle/book#930) * update hapi and image_segmentation (PaddlePaddle/book#931) * OCR案例更新 (PaddlePaddle/book#927) * 根据最新反馈建议新增了以下修改： 1.添加数据集压缩包下载链接和使用方法 2.测试pillow在paddlepaddle安装后是否需要单独安装 3.在目录下添加测试数据 4.更换第三方解码器并实现青春版，待2.0更新ctc-decode后再更新该处代码。 * 适配2.0RC0 * Update the paddle version to 2.0.0-rc0 (PaddlePaddle/book#932) Update the paddle version to 2.0.0-rc0 * update to rc (PaddlePaddle/book#933) * update to rc1 (PaddlePaddle/book#940) * update to rc1 * remote doc * update lr to 2.0rc1 (PaddlePaddle/book#941) * correct convnet iamge classify example (PaddlePaddle/book#942) * 基于飞桨2.0的应用案例教程（通过DCGAN实现人脸图像生成）代码提交 (PaddlePaddle/book#923) * Create dcgan_face.ipynb 通过DCGAN实现人脸图像生成 * 进一步改进格式 * 改为paddle.nn * bug修复 * 更新生成器G和判别器D迭代图 * Update dcgan_face.ipynb 根据修改意见，进行文档改进 * 二次修改 根据修改意见进行第二次修改 * 进一步修改 根据修改意见第三次修改 * 12-11修改 根据修改意见再一次修改 * update to rc1 (PaddlePaddle/book#944) * update to rc1 * update to rc1 * fix some bugs (PaddlePaddle/book#945) * fix some bugs * fix some bugs * fix some bugs * update images (PaddlePaddle/book#946) * 基于飞桨2.0的应用案例教程（通过CycleGAN实现图像风格迁移）代码提交 (PaddlePaddle/book#938) * add CycleGAN folder * delete CycleGAN folder * add CycleGAN floder * add CycleGAN.ipynb * delete other files * move the CycleGAN folder * add cyclegan.ipynb * replace cyclegan.ipynb * replace cyclegan.ipynb * replace cyclegan.ipynb * replace cyclegan.ipynb * update cyclegan.ipynb * Signed-off-by: ctkindle <[email protected]> * Signed-off-by: ctkindle <[email protected]> * Signed-off-by: ctkindle <[email protected]> * use min() instead of expression * use min() instead of expression * update to 2.0 (PaddlePaddle/book#948) * update to 2.0 * fix typo bugs * update to 2.0 (PaddlePaddle/book#949) * update to 2.0 * update OCR * update ocr * 点云分类PointNet文档 (PaddlePaddle/book#958) * 点云分类PointNet * Update pointnet.ipynb * Update pointnet.ipynb * 使用协同过滤实现电影推荐 (PaddlePaddle/book#960) * Add files via upload * Delete Collaborative filtering.ipynb * Create ttes.py * Delete ttes.py * Create test.py * Add files via upload * Delete test.py * Add files via upload * Delete Collaborative filtering.ipynb * 飞桨2.0实例教程——使用预训练词向量 (PaddlePaddle/book#934) * 飞桨2.0实例教程——使用预训练词向量 * 飞桨2.0实例教程——使用预训练词向量 删除了1312-1315行多余代码，训练和评测verbose改为1并重新生成了输出。 * Delete pretrained_word_embeddings.ipynb * 飞桨2.0应用案例——使用预训练的词向量 删除了原先的位置，增加了预训练词向量文件夹 * Update pretrained_word_embeddings.ipynb 修改了两处说明（Line9,190），修改了最近修改时间（Line15） * modified based on the latest comments * 强化学习——Actor Critic Method (PaddlePaddle/book#961) * Create Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * update to 2.0.1 (PaddlePaddle/book#962) * update to 2.0.1 * fix index * fix bugs (PaddlePaddle/book#969) * update_to_2.1 (PaddlePaddle/book#977) * update_to_2.1 * update practice * update practice * Advantage Actor-Critic(A2C) (PaddlePaddle/book#973) * Create Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Deep_Deterministic_Policy_Gradient_(DDPG) (PaddlePaddle/book#967) * Create Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * rename it as docs/practices Co-authored-by: Chunyu Zhang <[email protected]> Co-authored-by: jzhang533 <[email protected]> Co-authored-by: Chen Long <[email protected]> Co-authored-by: swtkiwi <[email protected]> Co-authored-by: Chen Long <[email protected]> Co-authored-by: dingjiaweiww <[email protected]> Co-authored-by: jm12138 <[email protected]> Co-authored-by: Reatris <[email protected]> Co-authored-by: GT-Zhang <[email protected]> Co-authored-by: Ralph LU <[email protected]> Co-authored-by: zzs95 <[email protected]> Co-authored-by: ZMpursue <[email protected]> Co-authored-by: FutureSI <[email protected]> Co-authored-by: Zhihao Cao <[email protected]> Co-authored-by: HUANGCHENGAI <[email protected]> Co-authored-by: WinSun <[email protected]> Co-authored-by: EastSmith <[email protected]>
wadefelix
added a commit
to wadefelix/FluidDoc
that referenced
this pull request
Aug 4, 2021
….0_docs to docs/practices (PaddlePaddle#3694) * image segmentation with u-net notebook (PaddlePaddle/book#870) * image segmentation with u-net notebook * update segmentation notebook * imdb_bow_classification added (PaddlePaddle/book#871) * dynamic graph example added (PaddlePaddle/book#876) * cnn based image classification added, minor changes to dygraph example (PaddlePaddle/book#877) * upgrade code that in image_segmentation from 2.0-alpha to 2.0-beta (PaddlePaddle/book#879) * image segmentation with u-net notebook * update segmentation notebook * upgrade code from 2.0-alpha to 2.0-beta * add getting started doc (PaddlePaddle/book#880) * image segmentation with u-net notebook * update segmentation notebook * upgrade code from 2.0-alpha to 2.0-beta * add getting started doc * delete invalid files * add tow models with develop-paddle (PaddlePaddle/book#881) * seq2seq with attention added (PaddlePaddle/book#882) * seq2seq with attention added * image_search use latest API * update seq2seq with attention * seq2seq with attention updated (PaddlePaddle/book#884) * add linear_regression.ipynb (PaddlePaddle/book#885) * fix_lenet_docs test=develop (PaddlePaddle/book#886) * add high level api doc (PaddlePaddle/book#887) * upgrade code to 2.0-beta * add high level api doc * fix_warning_info (PaddlePaddle/book#888) * fix_test_loader (PaddlePaddle/book#889) * fix_test_loader * fix_mnist_wrongs * update several notebooks (PaddlePaddle/book#890) * change from Pool2D to AdaptiveAvgPool2d in image_search * hello paddle updated * convnet_image_classification updated * dynamic_graph updated * convnet_image_classification updated * imdb bow classification updated * Fix style (PaddlePaddle/book#891) * fix_some_wrongs * fix_logs * minor wording changes (PaddlePaddle/book#892) * Course (PaddlePaddle/book#883) * add save_model * update api * change api name * change api name * add define callback/metric/loss chapter (PaddlePaddle/book#893) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * update several notebooks (PaddlePaddle/book#894) * rerun code with 2.0-beta whl (PaddlePaddle/book#895) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * rerun code with 2.0-beta whl * fix lr (PaddlePaddle/book#896) * fix docs for beta and change docs style (PaddlePaddle/book#900) * change version from dev to 2.0Beta (PaddlePaddle/book#899) * change version from dev to 2.0Beta * change version * fix linear_regression (PaddlePaddle/book#898) * fix lr 9.12 * fix linear_regression * Fix Bug: modify PetModel to PetNet (PaddlePaddle/book#901) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * rerun code with 2.0-beta whl * fix bug: modify PetModel to PetNet * [Bug Fix]change paddle.disable_static() position (PaddlePaddle/book#902) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * rerun code with 2.0-beta whl * fix bug: modify PetModel to PetNet * Fix BUG: change paddle.disable_static() position * add addition_rnn doc (PaddlePaddle/book#916) * Create addition_rnn.ipynb Sequence to sequence learning for performing number addition * fix some typo fix some typo * Update addition_rnn.ipynb * 基于飞桨2.0的应用案例教程（通过AutoEncoder实现时序数据异常检测）代码提交 (PaddlePaddle/book#914) * '提交数据文件' * upload ipynb * 对ipynbn修改 * 改用2.0 load 标题下署名，数据集文件删除 * 通过OCR实现验证码识别 代码提交 (PaddlePaddle/book#917) * init OCR.ipynb * 修改作者格式和一处描述 * 1. 更改pp为paddle。 2. 统一“预测”、“推理”术语为“预测”。 3. 简化文字部分描述。 * 添加super_resolution_sub_pixel (PaddlePaddle/book#910) * 添加super_resolution_sub_pixel * 添加super_resolution_sub_pixel * 修改错别字等 * 添加作者信息 * update codes to use 2.0RC (PaddlePaddle/book#921) * upgrade some code from 2.0-beta to 2.0-rc (PaddlePaddle/book#922) * 基于飞桨2.0的关键点检测方法及应用之（人脸关键点检测）代码提交 (PaddlePaddle/book#919) * upload facial_landmark.ipynb to landmark_detection * upgrade code in facial_landmark.ipynb * reviewed modify in facial_landmark.ipynb * fix guides (PaddlePaddle/book#925) * update save_model to 2.0rc (PaddlePaddle/book#924) * update save_model to 2.0rc * update save_model to 2.0rc * udpate to reflect 2.0RC version numbers (PaddlePaddle/book#926) * update to rc (PaddlePaddle/book#928) * update to rc (PaddlePaddle/book#929) * fix bugs (PaddlePaddle/book#930) * update hapi and image_segmentation (PaddlePaddle/book#931) * OCR案例更新 (PaddlePaddle/book#927) * 根据最新反馈建议新增了以下修改： 1.添加数据集压缩包下载链接和使用方法 2.测试pillow在paddlepaddle安装后是否需要单独安装 3.在目录下添加测试数据 4.更换第三方解码器并实现青春版，待2.0更新ctc-decode后再更新该处代码。 * 适配2.0RC0 * Update the paddle version to 2.0.0-rc0 (PaddlePaddle/book#932) Update the paddle version to 2.0.0-rc0 * update to rc (PaddlePaddle/book#933) * update to rc1 (PaddlePaddle/book#940) * update to rc1 * remote doc * update lr to 2.0rc1 (PaddlePaddle/book#941) * correct convnet iamge classify example (PaddlePaddle/book#942) * 基于飞桨2.0的应用案例教程（通过DCGAN实现人脸图像生成）代码提交 (PaddlePaddle/book#923) * Create dcgan_face.ipynb 通过DCGAN实现人脸图像生成 * 进一步改进格式 * 改为paddle.nn * bug修复 * 更新生成器G和判别器D迭代图 * Update dcgan_face.ipynb 根据修改意见，进行文档改进 * 二次修改 根据修改意见进行第二次修改 * 进一步修改 根据修改意见第三次修改 * 12-11修改 根据修改意见再一次修改 * update to rc1 (PaddlePaddle/book#944) * update to rc1 * update to rc1 * fix some bugs (PaddlePaddle/book#945) * fix some bugs * fix some bugs * fix some bugs * update images (PaddlePaddle/book#946) * 基于飞桨2.0的应用案例教程（通过CycleGAN实现图像风格迁移）代码提交 (PaddlePaddle/book#938) * add CycleGAN folder * delete CycleGAN folder * add CycleGAN floder * add CycleGAN.ipynb * delete other files * move the CycleGAN folder * add cyclegan.ipynb * replace cyclegan.ipynb * replace cyclegan.ipynb * replace cyclegan.ipynb * replace cyclegan.ipynb * update cyclegan.ipynb * Signed-off-by: ctkindle <[email protected]> * Signed-off-by: ctkindle <[email protected]> * Signed-off-by: ctkindle <[email protected]> * use min() instead of expression * use min() instead of expression * update to 2.0 (PaddlePaddle/book#948) * update to 2.0 * fix typo bugs * update to 2.0 (PaddlePaddle/book#949) * update to 2.0 * update OCR * update ocr * 点云分类PointNet文档 (PaddlePaddle/book#958) * 点云分类PointNet * Update pointnet.ipynb * Update pointnet.ipynb * 使用协同过滤实现电影推荐 (PaddlePaddle/book#960) * Add files via upload * Delete Collaborative filtering.ipynb * Create ttes.py * Delete ttes.py * Create test.py * Add files via upload * Delete test.py * Add files via upload * Delete Collaborative filtering.ipynb * 飞桨2.0实例教程——使用预训练词向量 (PaddlePaddle/book#934) * 飞桨2.0实例教程——使用预训练词向量 * 飞桨2.0实例教程——使用预训练词向量 删除了1312-1315行多余代码，训练和评测verbose改为1并重新生成了输出。 * Delete pretrained_word_embeddings.ipynb * 飞桨2.0应用案例——使用预训练的词向量 删除了原先的位置，增加了预训练词向量文件夹 * Update pretrained_word_embeddings.ipynb 修改了两处说明（Line9,190），修改了最近修改时间（Line15） * modified based on the latest comments * 强化学习——Actor Critic Method (PaddlePaddle/book#961) * Create Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * update to 2.0.1 (PaddlePaddle/book#962) * update to 2.0.1 * fix index * fix bugs (PaddlePaddle/book#969) * update_to_2.1 (PaddlePaddle/book#977) * update_to_2.1 * update practice * update practice * Advantage Actor-Critic(A2C) (PaddlePaddle/book#973) * Create Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Deep_Deterministic_Policy_Gradient_(DDPG) (PaddlePaddle/book#967) * Create Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * rename it as docs/practices Co-authored-by: Chunyu Zhang <[email protected]> Co-authored-by: jzhang533 <[email protected]> Co-authored-by: Chen Long <[email protected]> Co-authored-by: swtkiwi <[email protected]> Co-authored-by: Chen Long <[email protected]> Co-authored-by: dingjiaweiww <[email protected]> Co-authored-by: jm12138 <[email protected]> Co-authored-by: Reatris <[email protected]> Co-authored-by: GT-Zhang <[email protected]> Co-authored-by: Ralph LU <[email protected]> Co-authored-by: zzs95 <[email protected]> Co-authored-by: ZMpursue <[email protected]> Co-authored-by: FutureSI <[email protected]> Co-authored-by: Zhihao Cao <[email protected]> Co-authored-by: HUANGCHENGAI <[email protected]> Co-authored-by: WinSun <[email protected]> Co-authored-by: EastSmith <[email protected]>
wadefelix
added a commit
to wadefelix/FluidDoc
that referenced
this pull request
Aug 4, 2021
….0_docs to docs/practices (PaddlePaddle#3694) * image segmentation with u-net notebook (PaddlePaddle/book#870) * image segmentation with u-net notebook * update segmentation notebook * imdb_bow_classification added (PaddlePaddle/book#871) * dynamic graph example added (PaddlePaddle/book#876) * cnn based image classification added, minor changes to dygraph example (PaddlePaddle/book#877) * upgrade code that in image_segmentation from 2.0-alpha to 2.0-beta (PaddlePaddle/book#879) * image segmentation with u-net notebook * update segmentation notebook * upgrade code from 2.0-alpha to 2.0-beta * add getting started doc (PaddlePaddle/book#880) * image segmentation with u-net notebook * update segmentation notebook * upgrade code from 2.0-alpha to 2.0-beta * add getting started doc * delete invalid files * add tow models with develop-paddle (PaddlePaddle/book#881) * seq2seq with attention added (PaddlePaddle/book#882) * seq2seq with attention added * image_search use latest API * update seq2seq with attention * seq2seq with attention updated (PaddlePaddle/book#884) * add linear_regression.ipynb (PaddlePaddle/book#885) * fix_lenet_docs test=develop (PaddlePaddle/book#886) * add high level api doc (PaddlePaddle/book#887) * upgrade code to 2.0-beta * add high level api doc * fix_warning_info (PaddlePaddle/book#888) * fix_test_loader (PaddlePaddle/book#889) * fix_test_loader * fix_mnist_wrongs * update several notebooks (PaddlePaddle/book#890) * change from Pool2D to AdaptiveAvgPool2d in image_search * hello paddle updated * convnet_image_classification updated * dynamic_graph updated * convnet_image_classification updated * imdb bow classification updated * Fix style (PaddlePaddle/book#891) * fix_some_wrongs * fix_logs * minor wording changes (PaddlePaddle/book#892) * Course (PaddlePaddle/book#883) * add save_model * update api * change api name * change api name * add define callback/metric/loss chapter (PaddlePaddle/book#893) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * update several notebooks (PaddlePaddle/book#894) * rerun code with 2.0-beta whl (PaddlePaddle/book#895) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * rerun code with 2.0-beta whl * fix lr (PaddlePaddle/book#896) * fix docs for beta and change docs style (PaddlePaddle/book#900) * change version from dev to 2.0Beta (PaddlePaddle/book#899) * change version from dev to 2.0Beta * change version * fix linear_regression (PaddlePaddle/book#898) * fix lr 9.12 * fix linear_regression * Fix Bug: modify PetModel to PetNet (PaddlePaddle/book#901) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * rerun code with 2.0-beta whl * fix bug: modify PetModel to PetNet * [Bug Fix]change paddle.disable_static() position (PaddlePaddle/book#902) * upgrade code to 2.0-beta * add high level api doc * add define callback/metric/loss chapter * add define callback/metric/loss chapter * rerun code with 2.0-beta whl * fix bug: modify PetModel to PetNet * Fix BUG: change paddle.disable_static() position * add addition_rnn doc (PaddlePaddle/book#916) * Create addition_rnn.ipynb Sequence to sequence learning for performing number addition * fix some typo fix some typo * Update addition_rnn.ipynb * 基于飞桨2.0的应用案例教程（通过AutoEncoder实现时序数据异常检测）代码提交 (PaddlePaddle/book#914) * '提交数据文件' * upload ipynb * 对ipynbn修改 * 改用2.0 load 标题下署名，数据集文件删除 * 通过OCR实现验证码识别 代码提交 (PaddlePaddle/book#917) * init OCR.ipynb * 修改作者格式和一处描述 * 1. 更改pp为paddle。 2. 统一“预测”、“推理”术语为“预测”。 3. 简化文字部分描述。 * 添加super_resolution_sub_pixel (PaddlePaddle/book#910) * 添加super_resolution_sub_pixel * 添加super_resolution_sub_pixel * 修改错别字等 * 添加作者信息 * update codes to use 2.0RC (PaddlePaddle/book#921) * upgrade some code from 2.0-beta to 2.0-rc (PaddlePaddle/book#922) * 基于飞桨2.0的关键点检测方法及应用之（人脸关键点检测）代码提交 (PaddlePaddle/book#919) * upload facial_landmark.ipynb to landmark_detection * upgrade code in facial_landmark.ipynb * reviewed modify in facial_landmark.ipynb * fix guides (PaddlePaddle/book#925) * update save_model to 2.0rc (PaddlePaddle/book#924) * update save_model to 2.0rc * update save_model to 2.0rc * udpate to reflect 2.0RC version numbers (PaddlePaddle/book#926) * update to rc (PaddlePaddle/book#928) * update to rc (PaddlePaddle/book#929) * fix bugs (PaddlePaddle/book#930) * update hapi and image_segmentation (PaddlePaddle/book#931) * OCR案例更新 (PaddlePaddle/book#927) * 根据最新反馈建议新增了以下修改： 1.添加数据集压缩包下载链接和使用方法 2.测试pillow在paddlepaddle安装后是否需要单独安装 3.在目录下添加测试数据 4.更换第三方解码器并实现青春版，待2.0更新ctc-decode后再更新该处代码。 * 适配2.0RC0 * Update the paddle version to 2.0.0-rc0 (PaddlePaddle/book#932) Update the paddle version to 2.0.0-rc0 * update to rc (PaddlePaddle/book#933) * update to rc1 (PaddlePaddle/book#940) * update to rc1 * remote doc * update lr to 2.0rc1 (PaddlePaddle/book#941) * correct convnet iamge classify example (PaddlePaddle/book#942) * 基于飞桨2.0的应用案例教程（通过DCGAN实现人脸图像生成）代码提交 (PaddlePaddle/book#923) * Create dcgan_face.ipynb 通过DCGAN实现人脸图像生成 * 进一步改进格式 * 改为paddle.nn * bug修复 * 更新生成器G和判别器D迭代图 * Update dcgan_face.ipynb 根据修改意见，进行文档改进 * 二次修改 根据修改意见进行第二次修改 * 进一步修改 根据修改意见第三次修改 * 12-11修改 根据修改意见再一次修改 * update to rc1 (PaddlePaddle/book#944) * update to rc1 * update to rc1 * fix some bugs (PaddlePaddle/book#945) * fix some bugs * fix some bugs * fix some bugs * update images (PaddlePaddle/book#946) * 基于飞桨2.0的应用案例教程（通过CycleGAN实现图像风格迁移）代码提交 (PaddlePaddle/book#938) * add CycleGAN folder * delete CycleGAN folder * add CycleGAN floder * add CycleGAN.ipynb * delete other files * move the CycleGAN folder * add cyclegan.ipynb * replace cyclegan.ipynb * replace cyclegan.ipynb * replace cyclegan.ipynb * replace cyclegan.ipynb * update cyclegan.ipynb * Signed-off-by: ctkindle <[email protected]> * Signed-off-by: ctkindle <[email protected]> * Signed-off-by: ctkindle <[email protected]> * use min() instead of expression * use min() instead of expression * update to 2.0 (PaddlePaddle/book#948) * update to 2.0 * fix typo bugs * update to 2.0 (PaddlePaddle/book#949) * update to 2.0 * update OCR * update ocr * 点云分类PointNet文档 (PaddlePaddle/book#958) * 点云分类PointNet * Update pointnet.ipynb * Update pointnet.ipynb * 使用协同过滤实现电影推荐 (PaddlePaddle/book#960) * Add files via upload * Delete Collaborative filtering.ipynb * Create ttes.py * Delete ttes.py * Create test.py * Add files via upload * Delete test.py * Add files via upload * Delete Collaborative filtering.ipynb * 飞桨2.0实例教程——使用预训练词向量 (PaddlePaddle/book#934) * 飞桨2.0实例教程——使用预训练词向量 * 飞桨2.0实例教程——使用预训练词向量 删除了1312-1315行多余代码，训练和评测verbose改为1并重新生成了输出。 * Delete pretrained_word_embeddings.ipynb * 飞桨2.0应用案例——使用预训练的词向量 删除了原先的位置，增加了预训练词向量文件夹 * Update pretrained_word_embeddings.ipynb 修改了两处说明（Line9,190），修改了最近修改时间（Line15） * modified based on the latest comments * 强化学习——Actor Critic Method (PaddlePaddle/book#961) * Create Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * Update Actor_Critic_Method.ipynb * update to 2.0.1 (PaddlePaddle/book#962) * update to 2.0.1 * fix index * fix bugs (PaddlePaddle/book#969) * update_to_2.1 (PaddlePaddle/book#977) * update_to_2.1 * update practice * update practice * Advantage Actor-Critic(A2C) (PaddlePaddle/book#973) * Create Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Update Advantage Actor-Critic(A2C).ipynb * Deep_Deterministic_Policy_Gradient_(DDPG) (PaddlePaddle/book#967) * Create Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * Update Deep_Deterministic_Policy_Gradient_(DDPG).ipynb * rename it as docs/practices Co-authored-by: Chunyu Zhang <[email protected]> Co-authored-by: jzhang533 <[email protected]> Co-authored-by: Chen Long <[email protected]> Co-authored-by: swtkiwi <[email protected]> Co-authored-by: Chen Long <[email protected]> Co-authored-by: dingjiaweiww <[email protected]> Co-authored-by: jm12138 <[email protected]> Co-authored-by: Reatris <[email protected]> Co-authored-by: GT-Zhang <[email protected]> Co-authored-by: Ralph LU <[email protected]> Co-authored-by: zzs95 <[email protected]> Co-authored-by: ZMpursue <[email protected]> Co-authored-by: FutureSI <[email protected]> Co-authored-by: Zhihao Cao <[email protected]> Co-authored-by: HUANGCHENGAI <[email protected]> Co-authored-by: WinSun <[email protected]> Co-authored-by: EastSmith <[email protected]>
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.