Comments (7)
raising to an exponent < 1 will still 'squash' the numbers closer together, compressing their ratios.
from minigo.
The confusion is over the comment: "exponentiate the probabilities by a temperature slightly larger than unity". But the code is hiding the true value of T. T = 1/0.95, not 0.95.
from minigo.
@killerducky Can you point me to the code where the true value of T is calculated? I just see this
Line 244 in e7e686d
from minigo.
They just wrote it in a different form. It's the same as this:
temp = 1.0/0.95
probs = probs ** (1/temp)
from minigo.
@amj yes, if the number is > 1 otherwise it does the opposite.
from minigo.
@marcocalignano not sure what you're saying. If the concern is that we are raising the raw visit counts to an exponent < 1, that has the effect of 'squashing' the numbers.
i.e., [1, 10, 100] ** 0.9 = [1, 7.9, 63]
This is also true for numbers < 1
[0.01, 0.1, 1] ** .9 = [.02, .13, 1]
the arithmetic ratios are smaller.
from minigo.
@amj Ok sorry if the arithmetic ratios is what count you are right I was just a bit disturbed by the fact that ifthe count is less that 1 you increase the number, if it it bigger than 1 you decrease it.
from minigo.
Related Issues (20)
- run concurrent selfplay without bazel HOT 1
- Running minigo with Sabaki GUI HOT 2
- Problem while building tpu-image HOT 3
- Problem in features.stone_features HOT 1
- Onscreen buttons in lw_demo don't toggle (work)
- Minigo not working on Coral accelerator HOT 4
- Add Edge TPU support to C++ engine HOT 1
- Decouple the conv data format from the input feature layout HOT 8
- How strong is the model in kyu/dan? HOT 7
- 000990-cormorant: stderr thread died HOT 1
- Wrong argument passed in minigui/fetch-and-run.sh HOT 1
- How to communicate with engine easily outside stdin HOT 2
- Support for sending board state to the engine via GTP HOT 6
- Looking for 9x9 model files in .minigo file format HOT 7
- Error on Minigo v15(990)
- tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found. (0) Invalid argument: Assign requires shapes of both tensors to match HOT 3
- The setting of num_readouts to get strongest of minigo
- train.sh in cloud tpu
- Minigo training using Coral Dev Board HOT 1
- ./cc/configure_tensorflow.sh 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 minigo.