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 supported274 Subscribers
Add a CodeTriage badge to keras
Help out
- Issues
- [TF Backend] keras.ops.adaptive_max_pool and adaptive_average_pool raise AttributeError: tuple object has no attribute as_list on NumPy inputs with channels_last
- keras.ops.slogdet returns incorrect symbolic shape () instead of x.shape[:-2] for sign on batched matrices
- Fix symbolic output shape of sign in Slogdet.compute_output_spec for batched matrices
- pearson_correlation has no zero-variance guard, unlike concordance_correlation in the same file
- keras.ops.one_hot handles negative axis (< -1) inconsistently across backends
- NumPy and JAX backends: `binary_crossentropy` does not return the dtype of `output`
- `categorical_crossentropy` and `sparse_categorical_crossentropy` do not return the dtype of `output`
- keras.ops.categorical_crossentropy ignores axis argument in symbolic compute_output_spec
- keras.ops.batch_normalization raises AttributeError on symbolic tensors when offset is provided and scale=None
- keras.ops.multi_hot returns wrong dtype (inputs.dtype instead of floatx/dtype) for symbolic KerasTensors
- Docs
- Python not yet supported