oracle / Skater
Licence: upl-1.0
Python Library for Model Interpretation/Explanations
Stars: ✭ 973
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Skater
Ludwig
Data-centric declarative deep learning framework
Stars: ✭ 8,018 (+724.05%)
Mutual labels: deep-neural-networks, ml, datascience
Emotion Classification From Audio Files
Understanding emotions from audio files using neural networks and multiple datasets.
Stars: ✭ 189 (-80.58%)
Mutual labels: datascience, deep-neural-networks
Tensorflow
An Open Source Machine Learning Framework for Everyone
Stars: ✭ 161,335 (+16481.19%)
Mutual labels: deep-neural-networks, ml
Openchem
OpenChem: Deep Learning toolkit for Computational Chemistry and Drug Design Research
Stars: ✭ 356 (-63.41%)
Mutual labels: deep-neural-networks, predictive-modeling
Oneflow
OneFlow is a performance-centered and open-source deep learning framework.
Stars: ✭ 2,868 (+194.76%)
Mutual labels: deep-neural-networks, ml
Ml Examples
Arm Machine Learning tutorials and examples
Stars: ✭ 207 (-78.73%)
Mutual labels: deep-neural-networks, ml
Predictive Maintenance Using Lstm
Example of Multiple Multivariate Time Series Prediction with LSTM Recurrent Neural Networks in Python with Keras.
Stars: ✭ 352 (-63.82%)
Mutual labels: deep-neural-networks, lstm-neural-networks
Pytorch Kaldi
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
Stars: ✭ 2,097 (+115.52%)
Mutual labels: deep-neural-networks, lstm-neural-networks
Metaflow
🚀 Build and manage real-life data science projects with ease!
Stars: ✭ 5,108 (+424.97%)
Mutual labels: ml, datascience
Compression
Data compression in TensorFlow
Stars: ✭ 458 (-52.93%)
Mutual labels: deep-neural-networks, ml
Serving
A flexible, high-performance serving system for machine learning models
Stars: ✭ 5,306 (+445.32%)
Mutual labels: deep-neural-networks, ml
Chameleon recsys
Source code of CHAMELEON - A Deep Learning Meta-Architecture for News Recommender Systems
Stars: ✭ 202 (-79.24%)
Mutual labels: deep-neural-networks, lstm-neural-networks
Tfmesos
Tensorflow in Docker on Mesos #tfmesos #tensorflow #mesos
Stars: ✭ 194 (-80.06%)
Mutual labels: deep-neural-networks, ml
Darkon
Toolkit to Hack Your Deep Learning Models
Stars: ✭ 231 (-76.26%)
Mutual labels: deep-neural-networks, ml
Andrew Ng Notes
This is Andrew NG Coursera Handwritten Notes.
Stars: ✭ 180 (-81.5%)
Mutual labels: deep-neural-networks, ml
Statistical-Learning-using-R
This is a Statistical Learning application which will consist of various Machine Learning algorithms and their implementation in R done by me and their in depth interpretation.Documents and reports related to the below mentioned techniques can be found on my Rpubs profile.
Stars: ✭ 27 (-97.23%)
Mutual labels: datascience, predictive-modeling
Mnn
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba
Stars: ✭ 6,284 (+545.84%)
Mutual labels: deep-neural-networks, ml
Deephyper
DeepHyper: Scalable Asynchronous Neural Architecture and Hyperparameter Search for Deep Neural Networks
Stars: ✭ 117 (-87.98%)
Mutual labels: deep-neural-networks, ml
Djl
An Engine-Agnostic Deep Learning Framework in Java
Stars: ✭ 2,262 (+132.48%)
Mutual labels: deep-neural-networks, ml
Openrec
OpenRec is an open-source and modular library for neural network-inspired recommendation algorithms
Stars: ✭ 360 (-63%)
Mutual labels: deep-neural-networks, ml
Skater
Skater is a unified framework to enable Model Interpretation for all forms of model to help one build an Interpretable machine learning system often needed for real world use-cases(** we are actively working towards to enabling faithful interpretability for all forms models). It is an open source python library designed to demystify the learned structures of a black box model both globally(inference on the basis of a complete data set) and locally(inference about an individual prediction).
The project was started as a research idea to find ways to enable better interpretability(preferably human interpretability) to predictive "black boxes" both for researchers and practioners. The project is still in beta phase.
Install Skater
pip
Option 1: without rule lists and without deepinterpreter
pip install -U skater
Option 2: without rule lists and with deep-interpreter:
1. Ubuntu: pip3 install --upgrade tensorflow (follow instructions at https://www.tensorflow.org/install/ for details and best practices)
2. sudo pip install keras
3. pip install -U skater==1.1.2
Option 3: For everything included
1. conda install gxx_linux-64
2. Ubuntu: pip3 install --upgrade tensorflow (follow instructions https://www.tensorflow.org/install/ for
details and best practices)
3. sudo pip install keras
4. sudo pip install -U --no-deps --force-reinstall --install-option="--rl=True" skater==1.1.2
To get the latest changes try cloning the repo and use the below mentioned commands to get started,
1. conda install gxx_linux-64
2. Ubuntu: pip3 install --upgrade tensorflow (follow instructions https://www.tensorflow.org/install/ for
details and best practices)
3. sudo pip install keras
4. git clone the repo
5. sudo python setup.py install --ostype=linux-ubuntu --rl=True
Testing
- If repo is cloned:
python skater/tests/all_tests.py - If pip installed:
python -c "from skater.tests.all_tests import run_tests; run_tests()"
Usage and Examples
See examples folder for usage examples.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].