Comments (1)
I realize this question is over a year old but it may help others who are learning.
Please have a look at the original U-Net architecture below.
If depth = 5
, then the original U-Net is reproduced. The code loops over depth
and makes 5 down-blocks. Then it loops over depth-1
to make 4 up-blocks, for a total of 9 blocks.
If you use depth = 3
, I believe you are correct thinking that the result will be 3 down-blocks + 2 up-blocks, for a total of 5.
Cheers.
from pytorch-unet.
Related Issues (13)
- Upsample layer vs. convTranspose2d HOT 2
- Data preparation for valid convolutions
- Doesn't Seem to learn or overfit even one image HOT 2
- No pooling layers? HOT 2
- So Can u train it in ISBI and predict in it?
- output size does not match input size when padding=True HOT 1
- Pooling: avg vs max HOT 2
- Hi, I find a problem? HOT 1
- Pre trained unet HOT 1
- Output Channel Size HOT 1
- Same vs Valid padding HOT 1
- question about Input Size HOT 4
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 pytorch-unet.