Comments (5)
brilee
commented on July 19, 2024
Reopening; we can mark fixed when we've actually got another process automatically processing tfrecord file, implemented a get_eval_input function in preprocessing.py, and hook up eval/train to alternate running in dual_net.train().
from minigo.
amj
commented on July 19, 2024
Sounds good. Should we do this at the end of a training run, basically? as a separate process?
from minigo.
brilee
commented on July 19, 2024
Yeah, it could be as simple as train() then eval(). We don't need that much
granularity; one data point per generation is good enough.
…On Wed, Feb 7, 2018 at 3:42 AM Andrew Jackson ***@***.***> wrote:
Sounds good. Should we do this at the end of a training run, basically? as
a separate process?
—
You are receiving this because you modified the open/close state.
Reply to this email directly, view it on GitHub
<#43 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/ABQlFvHxgIFrUCJE-eXjVGrmz-97nIKXks5tSWIGgaJpZM4R3xlE>
.
from minigo.
amj
commented on July 19, 2024
It'd be great to also get a datapoint on how the rotation/reflection bias is trending. Could be as simple as take a position, do all 8 rotations, compute the stddev of the 8 value estimates, and do that as part as eval()
from minigo.
amj
commented on July 19, 2024
(The 'rotation bias' issue is in #84 )
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.