Comments (5)
In dlinknet, each conv-layer is followed by a batchnorm(conv-bn-relu), and, in fact, there's no difference between [-1.6,1.6] and [-1,1](or even [0,255]) in this case.
However, Unet(weight initialized by pytorch default initializer) without batchnorm do have better result using [-1.6,1.6] normalization. In this case, [-1.6,1.6](compare with [-1,1]) is equal to enlarge the initial learning rate and std of the initializer.
In dlinknet, channel-wise normalization equals adding two parameters weighting the RGB. It may have better result(I'm not sure), but I don't think this is so crucial~ 2333
from deepglobe-road-extraction-challenge.
This operation is to norm the image from [0,255] to [-1.6,1.6], you can norm the image to other range(better zero centered), [-1,1] or [-1.2,1.2] are fine :)
from deepglobe-road-extraction-challenge.
Thanks for your reply~ Is 1.6 a particular number that works the best in your case? And why don't you apply a std to each channel? Cause people always set mean and std at the same time. Haha~
from deepglobe-road-extraction-challenge.
Alright, thanks again. Happy New Year btw~ Lol
from deepglobe-road-extraction-challenge.
Happy New Year~ www
from deepglobe-road-extraction-challenge.
Related Issues (20)
- Licensing Terms HOT 1
- Multi class segmentation HOT 2
- 看到个道路提取的专利也叫dlinknet HOT 1
- Error when I run train.py HOT 1
- TypeError: new(): argument 'size' must be tuple of ints, but found element of type float at pos 2 HOT 1
- i got a problem :ValueError: num_samples should be a positive integer value, but got num_samples=0
- 代码不能跑 HOT 1
- 数据归一化时的处理(//255 * 3.2 - 1.6) HOT 2
- 关于数据集
- 希望借用codalab账号
- 希望借用codalab账号 HOT 2
- unet预测全黑 HOT 2
- test.py HOT 1
- 多GPU训练模型 HOT 1
- Error: axis 2 is out of bounds for array of dimension 1
- 您好在吗打扰一下您这个程序是哪里需要改动就能使用的,还是能直接使用
- init
- 使用其他数据集进行训练如何修改代码?
- Error: The size of tensor a (376) must match the size of tensor b (375) at non-singleton dimension 3
- mask[mask > XX] = 255, mask[mask <=XX] = 0, is the value of XX an experience value? Does the XX threshold need to be set differently for different graphs? HOT 3
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 deepglobe-road-extraction-challenge.