-
Notifications
You must be signed in to change notification settings - Fork 4
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
Rewrite cnn module to use tf2.0 #207
Labels
enhancement
New feature or request
Comments
arrrobase
added a commit
that referenced
this issue
Mar 13, 2020
arrrobase
added a commit
that referenced
this issue
Mar 16, 2020
arrrobase
added a commit
that referenced
this issue
Mar 16, 2020
arrrobase
added a commit
that referenced
this issue
Mar 17, 2020
arrrobase
added a commit
that referenced
this issue
Mar 17, 2020
arrrobase
added a commit
that referenced
this issue
Mar 17, 2020
arrrobase
added a commit
that referenced
this issue
Apr 2, 2020
arrrobase
added a commit
that referenced
this issue
Apr 2, 2020
arrrobase
added a commit
that referenced
this issue
Apr 10, 2020
arrrobase
added a commit
that referenced
this issue
Apr 21, 2020
arrrobase
added a commit
that referenced
this issue
Apr 21, 2020
arrrobase
added a commit
that referenced
this issue
Apr 22, 2020
arrrobase
added a commit
that referenced
this issue
Apr 23, 2020
arrrobase
added a commit
that referenced
this issue
Apr 23, 2020
arrrobase
added a commit
that referenced
this issue
Apr 23, 2020
arrrobase
added a commit
that referenced
this issue
Apr 30, 2020
arrrobase
added a commit
that referenced
this issue
Apr 30, 2020
svdavid
added a commit
that referenced
this issue
May 26, 2020
* #207 migrate cnn module to tf2 * fix rebase merge issues, failing tests * sparse, prettier logging; beginnings of banks * fir bank with tests; change layer.name to layer.ms_name * nems/tf-rewrite compatibility * add tensorflow-probability to travis * add inits to newtf; fix bug in tf/nems comp for multiple output chans; init static nls in newtfinit * rewrite of tfinit * add decimal handling to et in newtf * mask during comparison * add gradient with weight logging to callbacks; add tensorboard * scaling u parameter *100 in STP, set default IC for relu to -0.1 * start of damped oscillator in newtf * nan weight callback * fix weight restore after nan termination * commented STP a bit better, _cumtrapz in stp.py to exactly match TF implementation--in theory. Still some mistmatch * bugfix oldtf stp.q; xfail stp.q in test_tf/new * Fixed: xforms_kwargs get added to regristry kwargs as before * Added option to specify initial context contents when using fit_model_xforms * add gpu only option to tests Co-authored-by: Stephen David <[email protected]> Co-authored-by: Jacob <[email protected]>
jacobpennington
pushed a commit
that referenced
this issue
May 26, 2020
Pending changes for TF rewrite:
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
No description provided.
The text was updated successfully, but these errors were encountered: