Comments (3)
@lacker says to make a simpler neural net that works better with the given amount of IR training data, so the analysis overfits less.
Then expand the layers/data.
Don't just use some complicated neural net unsuited to the task.
from deeposm.
Yeah, I think you want to get to a state where "it works, just could be better" before scaling up. That way you can figure out how long you need to train, and keep params in a state where you don't overfit. I would try something real simple, like one convolution layer plus one softmax layer, and see if you can make it "work". By "work" I mean significantly better than random, like 80% accuracy, and not much of an overfitting problem.
from deeposm.
I think we're now in a state of "works with the simplest network." A single relu or single convolutional relu with a maxpool.
from deeposm.
Related Issues (20)
- automate/improve infrastructure HOT 7
- todos in progress
- INSTALL ISSUES HOT 5
- I think there is errata in "false positives" words HOT 1
- Deeposm.org UI: Add "Flag as fixed" control HOT 1
- Posssible to work with Google Earth Imagery HOT 2
- Fail to run train_neural_net.py HOT 3
- Paths issues HOT 1
- Getting Error while training the neural net !!! HOT 7
- gdal version mismatch? HOT 4
- Getting warning while Training neural net HOT 13
- Cannot download NAIP images on s3 using boto HOT 3
- Getting the import error HOT 2
- Pillow version is low, cause error when saving JPEG files HOT 2
- [Suggest] Can you develop new function that generates website content?
- Clock in docker is wrong, so aws doesn't allow download HOT 1
- Is web mercator transform correct? HOT 1
- Simple offline prediction
- Training stops with 'NoneType' object has no attribute 'name' HOT 1
- Pretrained models
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 deeposm.