-
Notifications
You must be signed in to change notification settings - Fork 481
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Error when running run.py self #75
Comments
Try run.py self again, but this time do not have any best model files. |
I deleted everything in data/model but I get the same error. |
If there is no model_best_config.json file, the error should not be the same. It should say something like no best model found, creating... Also, there is a lot of output about numerous loaded modules. This makes it hard to see anything. |
Attached error logs with nothing in data/model.
|
Something isn't right. Please let me know how it goes. Caution: Self play takes a very long time. |
Still does not work.
With data/model empty.
|
I haven't run this is many months. |
Did not work as reported in #73 . |
OK, something is hinky. So, next I renamed the data directory and ran with "self". Then, I tried "uci" mode, and it worked fine with the new un-trained weights. Then, I tried "self" mode and it started playing some games. Did not go further than that. |
Could you refer me to a commit where everything worked? Maybe roll back the master branch to that and move the current master to a different branch. |
Good idea. I'm still a github noob, but I'll try to figure it out. BTW I haven't looked at this repo in many months. Most have moved on to https://github.com/LeelaChessZero/ |
It would be awesome if you could do that!
Ah, my interest in this is because it is written in python :) |
There already is a forked repo that works for me. See: PS Be careful with the Keras and tensorflow-gpu versions. I have to use either 1.4 or 1.5 on my older cpu which only has popcnt. Also nets built with one version are not always compatible with another. I typically train with Ubuntu and run test matches with Win7 |
For a python Leela option see: |
I am getting the same error on that as well. Did you try that recently? |
Just tried it this morning and it worked fine. Did uci, self, and opt commands and all worked for me on Win7 with Keras 2.1.4 and TF gpu 1.4 |
I met the same problems |
usr python3.6.5 and tensorflow-gup1.8.0 |
The text was updated successfully, but these errors were encountered: