Comments (5)
You can try using GridSearchCV
from sklearn (http://scikit-learn.org/stable/modules/generated/sklearn.grid_search.GridSearchCV.html).
A (almost) example usage here: https://github.com/google/skflow/blob/master/skflow/tests/test_grid_search.py
Otherwise - it's really just an experiments and trying to understand how it changes the quality of the model. There just basic rules of thumb (like start with the same number as original features and then go less and less: e.g. for 500 features you can use [500, 250, 100]). You also want to balance the number of examples you have versus a number of parameters. Usually, you want to have ~10 examples per parameter.
from skflow.
Haha, thank you for giving this rule of thumb.
I have to confess that there a lot "rule of thumb" presented in discussion in quora or stackoverflow or researchgate to construct hidden layers in DNN, but let me check with your rule.
from skflow.
I think GridSearch in sklearn is similar with h2o.grid in h2o deep learning.
However, the idea is you need to present all the possible hidden_units
. We can list 1 000 000 000 different hidden_units and let the computer run, but I am not sure if it is a smart way. (For me it is just a brute force approach - maybe I am wrong)
from skflow.
There are other hyperparameter optimizers that actually take into account the values and accuracy of the model to pick next values (we use something like this in Google).
For example of Open Source library you can try - http://hyperopt.github.io/hyperopt/
from skflow.
Hope this helped! I'm closing this bug for now.
from skflow.
Related Issues (20)
- Verbose is not considered during the training. HOT 1
- need more models in skflow.models HOT 2
- seq2seq example doesn't work HOT 1
- IndexError: index 20860 is out of bounds for axis 0 with size 18805 HOT 3
- TypeError inside skflow HOT 1
- text_classification.py giving error HOT 2
- skflow and tensorboard HOT 1
- Conditional RBM and distributed computing HOT 1
- can not run two tensorflow program one by one HOT 1
- Exception in the Custom model example HOT 2
- Scikitflow documentation update requested HOT 1
- getting none values not supported error HOT 3
- neural_translation.py showing error HOT 4
- Exception when restore DNN model HOT 1
- Tensor name "hiddenlayer_2/biases" not found in checkpoint files HOT 1
- checkpoint can't be restored... HOT 1
- DNNClassifier init failed HOT 1
- Why hasn't this repo been archived yet?
- Is this project still working? HOT 1
- .travis.yml: The 'sudo' tag is now deprecated in Travis CI HOT 1
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 skflow.