Comments (4)
There is no script for computing IoU or mIoU in this repository. Computing IoU using numpy just like this.
def iou(a, b): a //= 255 b //= 255 o = a+b i = (o==2).sum() u = (o>=1).sum() if u == 0: return 1.0 return 1.0*i/u
from deepglobe-road-extraction-challenge.
Thanks for the reply.
Another question: how did you do the validation if the validation masks are not available in the dataset?
(I had also seen the same question of yours on the DeepGlobe forum, but there was no reply there)
from deepglobe-road-extraction-challenge.
For your question, I did not validate my models in the final phase.
I tried several methods in the development phase, and found that D-LinkNet34 is better than the ensemble of LinkNet34 and Unet on the validation set.
Therefore, I trained D-LinkNet50, D-LinkNet101 and D-Unet in the final phase, and submitted the predictions on the test set only.
It would be more standard to use some kind of validation such as cross-validation. However, due to the time limitation and no many training images, I did not partition some of the data as validation set.
from deepglobe-road-extraction-challenge.
@zlkanata
Thanks for the help!
from deepglobe-road-extraction-challenge.
Related Issues (20)
- 作者您好,请问下img = np.array(img, np.float32).transpose(2,0,1)/255.0 * 3.2 - 1.6 后面的*3.2-1.6的操作有什么目的,加或不加会对训练结果有影响吗
- 推理结果全白或全黑 HOT 1
- 请问膨胀率从1,2,4,8提升到1,2,4,8,16能带来效果提升吗?
- 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
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.