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
- Reject shape-bomb Orbax checkpoints in load_model and load_weights
- Remove TF dependencies in non-TF backends
- `keras.ops.image.resize` no longer rejects a non-positive `size` given as NumPy integers
- ops.image.gaussian_blur returns wrong values for non-square kernel_size on the TensorFlow backend
- ops.unfold, ops.unstack, ops.stop_gradient and ops.vectorized_map fail on non-tensor inputs with the torch backend
- ops.vstack of 1-D inputs returns a flat array on the TensorFlow backend
- ops.diagonal, ops.diag, ops.trace and ops.eye raise for out-of-range offsets on the TensorFlow backend
- ops.split fails with negative or out-of-range indices_or_sections on TensorFlow and torch
- ops.arange raises on an empty range on TensorFlow and torch
- fix(metrics): PearsonCorrelation returns 0.0 instead of NaN for zero-variance rows
- Docs
- Python not yet supported