sicara/tf-explain
Interpretability Methods for tf.keras models with Tensorflow 2.x
This tool helps machine learning engineers and researchers understand why their image recognition or other computer vision models make specific predictions. By providing your trained TensorFlow 2.x Keras model and an input image, it generates visual explanations, highlighting the most influential parts of the image that led to the model's decision. This allows practitioners to debug model behavior and build trust in their AI systems.
1,036 stars. Used by 1 other package. No commits in the last 6 months. Available on PyPI.
Use this if you need to visualize and interpret the decisions of your TensorFlow 2.x deep learning models, particularly for image data, to understand which input features are most important for a given prediction.
Not ideal if you are working with non-image data (like text or tabular data) or if your models are not built using TensorFlow 2.x Keras.
Stars
1,036
Forks
110
Language
Python
License
MIT
Last pushed
Jun 03, 2024
Commits (30d)
0
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sicara/tf-explain"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...