keras
https://github.com/keras-team/keras
Python
Deep Learning for humans
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported271 Subscribers
View all SubscribersAdd a CodeTriage badge to keras
Help out
- Issues
- OpenVINO backend: ops return wrong values or fail (scalar operands in the wrong element type, three CPU-plugin bugs, shape bugs)
- Backend kernels do not follow the op spec: ignored `dtype` arguments, rejected index dtypes, wrong output structure
- Layer.__delattr__ does not untrack sub-layers
- Ensure categorical and sparse categorical crossentropy return output dtype
- pearson_correlation has no zero-variance guard, unlike concordance_correlation in the same file
- `categorical_crossentropy` and `sparse_categorical_crossentropy` do not return the dtype of `output`
- Resolve weak float to bfloat16 under bfloat16 floatx
- Integer and bool inputs give wrong values in several activations, with no error
- torch: float64 `Dense` returns float32 since #23225, and float64 handling on torch is inconsistent
- rms_normalization and layer_normalization truncate integer and bool inputs to the input dtype
- Docs
- Python not yet supported