keras
Multi-backend deep learning library for building, training, running inference, and saving neural network models in Python.
npx skills add majiayu000/claude-skill-registry --skill skills-skilldoai-skilldo-10 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
## Imports ```python import keras from keras import Model, layers ``` ## Core Patterns ### Run inference with `Model.predict()` ✅ Current ```python import os # Use a backend that is installed; here, "tensorflow" is most widely available. os.environ["KERAS_BACKEND"] = "tensorflow" # Keras 3 requires TensorFlow backend as an extra dependency for most environments. import tensorflow as tf import keras from keras import layers import numpy as np model = keras.Sequential( [ layers.Input(shape=(4,)), layers.Dense(8, activation="relu"), layers.Dense(3, activation="softmax"), ] ) x = np.random.RandomState(0).randn(5, 4).astype("float32") preds = model.predict(x, verbose=0) print(preds.shape) ``` * Use `keras.Model.predict(x)` for forward-pass inference on NumPy arrays (and other backend-compatible inputs). * Works with any supported backend; for OpenVINO, inference is the intended workflow. ### Save a model with `Model.save()` to the native `.keras` format ✅ Current ```python import os import tempfile # Use a backend that supports saving; here, "tensorflow" is most widely available. os.environ["KERAS_BACKEND"] = "tensorflow" import tensorflow as tf import keras from keras import layers imp
- Imports
- Core Patterns
- Run inference with Model.predict() ✅ Current
- Save a model with Model.save() to the native .keras format ✅ Current
- Configure backend via environment before import ✅ Current
- OpenVINO backend for inference-only Model.predict() ✅ Current
- Configuration
- Pitfalls
- Wrong: Setting KERASBACKEND after importing keras
- Right: Set KERASBACKEND before importing keras
- Wrong: Trying to train on the OpenVINO backend (inference-only)
- Right: Use OpenVINO backend for Model.predict() only
- Wrong: Saving without an explicit .keras extension (ambiguous/legacy)
- Right: Save using the native .keras format
What does the keras skill do?
Multi-backend deep learning library for building, training, running inference, and saving neural network models in Python.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill skills-skilldoai-skilldo-10 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.