-
Notifications
You must be signed in to change notification settings - Fork 270
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
merging dev to daily-dev #77
Conversation
Substitute `model.predict_classes` (only available for Sequential Model) using `numpy.argmax` with `axis=-1` to match predict_classes shape.
fixing the notebook URI
Syncing with original repo
Using a predict_classes function similar to Sequential Model for Functional Model To use this experimental function add experimental_functional_support=True to the Scan() parameters Adding a Jupyter Notebook example
Adding Experimental Support for Functional Model
fixes #62 and adds several missing docstrings
Issue with fn and fp values
Hello @mikkokotila! Thanks for updating the PR.
Comment last updated on August 25, 2018 at 16:22 Hours UTC |
Pull Request Test Coverage Report for Build 177
💛 - Coveralls |
- there was a bug in the metric_names - and another bug in reductions - this also revealed the issue with the test script related with reduction tests (the threshold should be 0.01 or similar low to make sure that the reduction runs)
No description provided.