• <div><p>We added fast wavenet generation. Addresses issue #26. <p><strong>Verification - We compared the output of our fast generation with slow generation, and ensured it exactly matches. - We also ...
• <div><p>World generation is fairly bleh right now and does not feature biomes. It also does not use the updated generation API. The optimal solution to rectify this would be: - Adapting world ...
• <div><p>make the generation for transaction <h2>Checklist <ul><li>add generation for transaction generation </li><li>i work in user story number ...
• <div><p>Update validation generation to allow for flattening array properties and outside types. <p>Regenerate Neg CRD code generation for open api definitions for missing types and change ...
• <div><p>In the code generation as you have mentioned to use Namatus for the nmt in that the input is a declaration,docstring and output is body . then how the code will be generated ? <p>in ...
• <div><p>Things I want to try if I ...<ul><li>[ ] Music generation (unconditional)</li><li>[ ] MIDI-conditioned piano sound generation</li></ul>该提问来源于开源项目：r9y9/wavenet_vocoder</p></div>
• <div><p>I wanted to know if you are happy with the power generation you are offering at the moment, ( By happy I mean you don't want to add anything new.) If you do take ideas for new unique power...
• - On gem generation, if not set to false/rspec/minitest, ask if the user would like to generate tests along with their gems. Save the answer as bundle config gem.tests. - Ensure that --coc, --mit, --...
• <div><p>If in SAI editor phase set to 1-9, then comment generation isnt work</p><p>该提问来源于开源项目：Helias/Keira2</p></div>
• <div><p>Hi ,I am confused about the label generation , if you could help, I would appreciate it. When I open the get_labels.py script, I don't know the parameter 'source-file-mean' . How ...
• column generation is an insightful overview of the state-of-the-art in integer programming column generation and its many applications. The volume begins with "A Primer in Column Generation" which ...
• <div><p>Hello, have improved email generation function, added possible ways to generate male/female email addresses. Added the Gender generation function, and a wrapper as Person for the First Name, ...
• <div><p>There is an issue in the map implementation where the generation is put into the top 24 bits of the index stored in the hash->index map <p>...
• Generation TasksImproved GANrelated tasksImproved GAN-Image GenerationGANProblems of GANImproved GANNew paper from DeepMindSemi-parametric StrategyImage GenerationMessage-Passing StrategyMessage Passi...
Generation TasksImproved GANrelated tasksImproved GAN-Image GenerationGANProblems of GANImproved GANNew paper from DeepMindSemi-parametric StrategyImage GenerationMessage-Passing StrategyMessage Passing Strategy for Feature Sharing.Domain Adaptation StrategyVideo generationText Effects TransferScene graph GenerationRobot ControlCross-Modal Zero-Shot Hashing retrievalReferenceAcknowledgment

Reference[原文]: Joselynzhao.top & 夏木青 | Generation Tasks

Improved GAN
如何从语言描述的场景来生成图像

image synthesis

可以通过 RNN+GAN 生成实现
Improved GAN-Image Generation
GAN
Improved GAN-Image Generation

Image Generation from Scene Graphs (CVPR2018)
Stackgan: Text to photo-realistic image synthesis with
stacked generative adversarial networks. (ICCV 2017)
使用堆积的生成对抗网络实现从文本到真实图像的合成

Problems of GAN
carefully balance the capabilities between the generator and the discriminator
仔细平衡发生器和鉴别器之间的能力
unsuitable parameter settings can degrade the performance
不合适的参数设置会降低性能
Improved GAN
Evolutionary Generative Adversarial Networks (TEVC 2019)
New paper from DeepMind
Vector Quantized Variational AutoEncoder model（VQ-VAE2 wins bigGAN）
矢量量化变分自动编码器模型

Semi-parametric Strategy
半参数策略
Image Generation
Parametric models
end-to-end training of highly expressive models. （高度表达模型）
Nonparametric models （非参数模型）
extract materials from large real image datasets during testing
在测试的时候提取信息
Semi-parametric Strategy
Semi-parametric Image Synthesis (CVPR2018)
The problem of existing image generation methods （现有方法的问题）
give stunning results on limited domains such as
descriptions of birds, flowers or people.
Low-quality image of other domains.
作用领域有限
Using semi-parametric strategy to improve  Image generation method
Message-Passing Strategy
Message Passing Strategy for Feature Sharing.
用于特征共享的消息传递策略
Scene Graph Generation from Objects, Phrases and Region Captions(ICCV2017)

区域适应策略
give stunning results on limited domains such as descriptions of birds, flowers or people.
Using Domain Adaptation to improve Image generation method  in more domains.
Video generation

输入 深度图像
输出 对手关节、姿势的估计

3D Hand Shape and Pose Estimation from a Single RGB Image（CVPR19 Oral）
Text Effects Transfer

创新的分布感知数据增强策略
TET-GAN: Text Effects Transfer via Stylization and Destylization
（AAAI2019）
Scene graph Generation

modeling these statistical correlations between object pairs and relationships can effectively regularize the semantic prediction space （structured knowledge graph ）
对这些对象和关系之间的统计相关性建模可以有效地规范语义预测空间（结构化知识图）
Knowledge-Embedded Routing Network for   Scene Graph Generation （CVPR2019）

Robot Control

Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection(2017)

Towards Accurate Task Accomplishment with Low-Cost Robotic Arms（CVPR2019）

Cross-Modal Zero-Shot Hashing retrieval
跨模态 zero-shot 哈希检索

Attribute-Guided Network for Cross-Modal Zero-Shot Hashing(T-NNLS19)
Reference

Image Generation from Scene Graphs (CVPR2018)
Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. (ICCV 2017)
Evolutionary Generative Adversarial Networks  (TEVC 2019)
Semi-parametric Image Synthesis (CVPR2018)
Scene Graph Generation from Objects, Phrases and Region Captions(ICCV2017)
3D Hand Shape and Pose Estimation from a Single RGB Image（CVPR19 Oral）
TET-GAN: Text Effects Transfer via Stylization and Destylization
（AAAI2019）
Knowledge-Embedded Routing Network for   Scene Graph Generation （CVPR2019）
Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection(2017)
Towards Accurate Task Accomplishment with Low-Cost Robotic Arms（CVPR2019）
Attribute-Guided Network for Cross-Modal Zero-Shot Hashing(T-NNLS19)

Acknowledgment
感谢本篇博文的内容提供者：崔亚文（Cui Yawen）· HPCL


展开全文
• <div><p>Adding the possible generation of mipmaps since this option is available on the web version (and tilting the view can generally requests a lot of mipmaping usage). This options probably needs ...
• <div><p>This pull request does significant restructuring of the methods related to reaction generation, motivated by #1192. These changes are intended to reduce code duplication, improve organization,...
• <div><p>From the <a href="http://www.minecraftforum.net/forums/mapping-and-modding/minecraft-mods/2524489-realistic-terrain-generation-rtg-realistic-biomes?comment=2255">thread, Realistic Terrain ...
• ve made a lot of progress on code generation and standalone mode, but the code generation code has now become quite brittle and difficult to work with. I don't think that what it's doing is ...
• <div><p>This PR fixes the data generation, which was completely broken for the messages generations other than the current one. It was broken mainly because of the message generation from the ...
• <p>Now, if the thumbnail version is -1 (during Pyramid generation) then we use a random version number to prevent caching of the clock thumbnail in the browser. Clock thumbnails will be retrieved each...
• <div><p>Support for Prometheus jwt token generation <p>Will have admin API's for jwt generation - <code>mc admin prometheus --generate myminio</code></p>该提问来源于开源项目：minio/mc</p></...
• <div><p>On the latest experimental overmap generation seems to fail almost every time for my on Cities: 8 with Spacing: 4, and fail every time when spacing is more than 4. Generation also seems to ...
• <p>I do not get any values for Power Generation. Have enabled DSMR2.2 and working fine for Power Consumption. For Generation it gives: No data. <p>Should i enable this somewhere?</p><p>该提问来源于...
• <div><p>It appears that <a href="https://bulbapedia.bulbagarden.net/wiki/List_of_Pok%C3%A9mon_by_National_Pok%C3%A9dex_number#Generation_VII">generation 7 pokemon</a> are missing from the API....
• <h1>API generation <p>The core of the generation is ready, though there is still a few work to do, we can already use it. <p>The api generation is not hard coded. Instead there is core generator, in ...
• <div><p>Refactor octree generation. This will helps in: * Making it extensible for building octree from file or iterator * Flexibility to use octree builder in other packages <p>Future plans: * ...
• <div><p>The purpose of this PR is to simplify of Mapper class generation as we drop interface generation support. We don't need to generate <code>Creators, <code>Factories</code>. <p>Plus we don&#...
• A family hierarchy is usually presented by a pedigree tree where all the nodes on the same level belong to the same generation. Your task is to find the generation with the largest population. Input ...
A family hierarchy is usually presented by a pedigree tree where all the nodes on the same level belong to the same generation. Your task is to find the generation with the largest population.

Input Specification:

Each input file contains one test case. Each case starts with two positive integers N (<100) which is the total number of family members in the tree (and hence assume that all the members are numbered from 01 to N), and M (<N) which is the number of family members who have children. Then M lines follow, each contains the information of a family member in the following format:

ID K ID[1] ID[2] ... ID[K]


where ID is a two-digit number representing a family member, K (>0) is the number of his/her children, followed by a sequence of two-digit ID's of his/her children. For the sake of simplicity, let us fix the root ID to be 01. All the numbers in a line are separated by a space.

Output Specification:

For each test case, print in one line the largest population number and the level of the corresponding generation. It is assumed that such a generation is unique, and the root level is defined to be 1.

Sample Input:

23 13
21 1 23
01 4 03 02 04 05
03 3 06 07 08
06 2 12 13
13 1 21
08 2 15 16
02 2 09 10
11 2 19 20
17 1 22
05 1 11
07 1 14
09 1 17
10 1 18


Sample Output:

9 4

vector或者数组存储树

有点类似层序遍历，层序遍历是使用queue进行输出，但是我想了半天没有想出一个很好地办法计算每层的节点数量。

最后参考了别人的代码，使用vector来模拟，好处就在于可以使用erase直接删除上一代节点

#include <iostream>
#include <vector>
#include <queue>
using namespace std;
int main(){
vector<int> nodes[100];           //保存树
int n,m;
scanf("%d %d",&n,&m);
for(int i=0;i<m;i++){
int pId,nCh;
scanf("%d %d",&pId,&nCh);
for(int j=0;j<nCh;j++){
int temp;
scanf("%d",&temp);
nodes[pId].push_back(temp);      //谁的孩子谁装
}
}
int max=0,level=1,t;
vector<int> data;
data.push_back(1);                      //把根节点装进去
while(!data.empty()){
int size=data.size();               //当代节点数量
if(size>max){
t=level;
max=size;
}
for(int k=0;k<size;k++){
for(int l=0;l<nodes[data[k]].size();l++){  //添加下一代节点
data.push_back(nodes[data[k]][l]);
}
}
data.erase(data.begin(),data.begin()+size);
level++;

}
printf("%d %d",max,t);
return 0;
}

`
展开全文
• <div><p>This is a work in progress targeting TS type annotation generation. For now, only basic structures will be generated.</p><p>该提问来源于开源项目：apollographql/apollo-tooling</p></div>

...