Comments (5)
我确认了下应该为 5 x 5,你可以参考pytorch的文档 ConvTranspose2d,
一个简单的测试代码:
import torch
import torch.nn as nn
conv_transpose = nn.ConvTranspose2d(1, 1, 3, stride=2, dilation=1)
x = torch.rand(1, 1, 2, 2)
y = conv_transpose(x)
print(y.size()) # [1, 1, 5, 5]
from graphneuralnetwork.
是不是通过填充元素后,步长变为1了?
from graphneuralnetwork.
首先转置卷积中的stride的概念与卷积中有所不同,另一方面转置卷积就是要增加输出的大小,因此卷积的步长应该都是1,否则没法保证输出的大小
from graphneuralnetwork.
好像padding的概念也不一样,真正的padding大小为k-1-p?h'=k+2(k-1-p)?
from graphneuralnetwork.
是的,真正padding的大小为k-1-p,具体的计算公式参考上面的pytorch文档。
from graphneuralnetwork.
Related Issues (20)
- 关于chapter7 graphsage 每轮epoch最后一轮batch src_node变成1000 但是设置的根节点数目为16 HOT 1
- 关于书的92、93、94页的疑问和错误。 HOT 1
- 能不能把电子版本里面的错误都改掉? HOT 15
- 5.5卷积神经网络的疑问? HOT 1
- P88 5.3节 特征矩阵计算错误? HOT 1
- something seems wrong in the file of main.py in chapter07 HOT 1
- 35页公式2.23上面一句话有错 HOT 1
- 第九章的代码 HOT 2
- 关于第7章GAT部分的一些错误 HOT 1
- 第五页K阶子图定义 HOT 4
- Unpicklingerror: invalid loadkey,' \ x0a' HOT 2
- 第5章勘误 HOT 2
- 第五章勘误:Laplacian Matrix的正交分解 HOT 3
- 公式5.18如何理解 HOT 1
- 第五章代码有错误 HOT 6
- Issue in generating .test.index file
- 关于chapter7中GraphSAGE的代码中好像并没有体现采样顺序k->1,聚合顺序1->k的问题
- Node classification task
- 77页的公式不太对
- 关于《深入浅出图神经网络:GNN原理解析》一书中chapter9代码的问题
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from graphneuralnetwork.