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 supported283 Subscribers
Add a CodeTriage badge to keras
Help out
- Issues
- keras3 doesn't respect explicit `.to` calls on inputs and model params with torch backend.
- Inconsistent manner of the metric `SpecificityAtSensitivity` among different backends
- Request for Assistance with JAX Backend: Custom Model Training with Multiple Submodels
- Conv2D.compute_output_shape() returns a shape while the layer failed to generate an output
- [BUG] Google collab example not working: Multi-GPU distributed training with PyTorch
- Difference in training with `model.fit` and with `tf.GradientTape`
- Unless specified otherwise, keras.Input defaults to 'float32', regardless of the current 'floatx' setting
- Backward compatibility issues: arbitrary inputs and overreliance on custom layers
- Backend-agnostic JIT compilation support for non supervised learning workflows
- Gradients Sum in Keras 3 Optimizer with Tensorflow backend
- Docs
- Python not yet supported