Comments (1)
The meta_minimize()
method in the MetaOptimizer
class returns a namedtuple
that contains a tensor with the state of the optimizee parameters at the end of an unroll. You can just add that to the call to sess.run()
and print the results to look at the state of the optimizee.
The train
function in convergence_test.py
is a good example of how to do this.
from learning-to-learn.
Related Issues (20)
- AttributeError: module 'tensorflow.contrib.rnn' has no attribute 'RNNCell' HOT 2
- Debugging the meta-optimizer
- Distributed version of this?
- AttributeError: 'module' object has no attribute 'AbstractModule' HOT 9
- Just a ConvNet HOT 1
- Dependency: dill HOT 2
- Resetting each epoch? HOT 4
- No restore logic in evaluate.py HOT 1
- Problems for CIFAR experiments HOT 2
- structures don't have the same sequence type HOT 12
- windows run error HOT 5
- Tensorflow and sonnet versions? HOT 1
- fatal error:iso:no such a file or directory. HOT 1
- TypeError: The two structures don't have the same nested structure. HOT 2
- How to add accuracy prediciton
- Is BPTT implemented here?
- mnist result is not good HOT 3
- cifar queues problem
- MNIST not reproducible HOT 1
- Followup to Issue 22
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 learning-to-learn.