All Projects → darkonhub → Darkon

darkonhub / Darkon

Licence: apache-2.0
Toolkit to Hack Your Deep Learning Models

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Darkon

Skater
Python Library for Model Interpretation/Explanations
Stars: ✭ 973 (+321.21%)
Mutual labels:  deep-neural-networks, ml
Niftynet
[unmaintained] An open-source convolutional neural networks platform for research in medical image analysis and image-guided therapy
Stars: ✭ 1,276 (+452.38%)
Mutual labels:  deep-neural-networks, ml
Ludwig
Data-centric declarative deep learning framework
Stars: ✭ 8,018 (+3371%)
Mutual labels:  deep-neural-networks, ml
Serving
A flexible, high-performance serving system for machine learning models
Stars: ✭ 5,306 (+2196.97%)
Mutual labels:  deep-neural-networks, ml
Andrew Ng Notes
This is Andrew NG Coursera Handwritten Notes.
Stars: ✭ 180 (-22.08%)
Mutual labels:  deep-neural-networks, ml
Ffdl
Fabric for Deep Learning (FfDL, pronounced fiddle) is a Deep Learning Platform offering TensorFlow, Caffe, PyTorch etc. as a Service on Kubernetes
Stars: ✭ 640 (+177.06%)
Mutual labels:  deep-neural-networks, ml
Dltk
Deep Learning Toolkit for Medical Image Analysis
Stars: ✭ 1,249 (+440.69%)
Mutual labels:  deep-neural-networks, ml
Caffe2
Caffe2 is a lightweight, modular, and scalable deep learning framework.
Stars: ✭ 8,409 (+3540.26%)
Mutual labels:  deep-neural-networks, ml
Djl
An Engine-Agnostic Deep Learning Framework in Java
Stars: ✭ 2,262 (+879.22%)
Mutual labels:  deep-neural-networks, ml
Deephyper
DeepHyper: Scalable Asynchronous Neural Architecture and Hyperparameter Search for Deep Neural Networks
Stars: ✭ 117 (-49.35%)
Mutual labels:  deep-neural-networks, ml
Compression
Data compression in TensorFlow
Stars: ✭ 458 (+98.27%)
Mutual labels:  deep-neural-networks, ml
Oneflow
OneFlow is a performance-centered and open-source deep learning framework.
Stars: ✭ 2,868 (+1141.56%)
Mutual labels:  deep-neural-networks, ml
Openrec
OpenRec is an open-source and modular library for neural network-inspired recommendation algorithms
Stars: ✭ 360 (+55.84%)
Mutual labels:  deep-neural-networks, ml
Mnn
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba
Stars: ✭ 6,284 (+2620.35%)
Mutual labels:  deep-neural-networks, ml
Tensorflow
An Open Source Machine Learning Framework for Everyone
Stars: ✭ 161,335 (+69741.99%)
Mutual labels:  deep-neural-networks, ml
Onnx
Open standard for machine learning interoperability
Stars: ✭ 11,829 (+5020.78%)
Mutual labels:  deep-neural-networks, ml
Tfmesos
Tensorflow in Docker on Mesos #tfmesos #tensorflow #mesos
Stars: ✭ 194 (-16.02%)
Mutual labels:  deep-neural-networks, ml
Ml Examples
Arm Machine Learning tutorials and examples
Stars: ✭ 207 (-10.39%)
Mutual labels:  deep-neural-networks, ml
Torchfold
Tools for PyTorch
Stars: ✭ 220 (-4.76%)
Mutual labels:  deep-neural-networks
Books
整理一些书籍 ,包含 C&C++ 、git 、Java、Keras 、Linux 、NLP 、Python 、Scala 、TensorFlow 、大数据 、推荐系统、数据库、数据挖掘 、机器学习 、深度学习 、算法等。
Stars: ✭ 222 (-3.9%)
Mutual labels:  ml


Build Status codecov License PyPI Gitter Codacy Badge


Darkon: Toolkit to Hack Your Deep Learning Models

Darkon is an open source toolkit to understand deep learning models better. Deep learning is often referred as a black-box that is difficult to understand. But, accountability and controllability could be critical to commercialize deep learning models. People often think that high accuracy on prepared dataset is enough to use the model for commercial products. However, well-performing models on prepared dataset often fail in real world usages and cause corner cases to be fixed. Moreover, it is necessary to explain the result to trust the system in some applications such as medical diagnosis, financial decisions, etc. We hope
Darkon can help you to understand the trained models, which could be used to debug failures, interpret decisions, and so on.

Here, we provide functions to analyze deep learning model decisions easily applicable to any Tensorflow models (other models to be supported later). Influence score can be useful to understand the model through training samples. The score can be used for filtering bad training samples that affects test performance negatively. It is useful to prioritize potential mislabeled examples to be fixed, and debug distribution mismatch between train and test samples. In this version, we have added Grad-CAM and Guided Grad-CAM, which are useful to understand decisions of CNN models.

We will gradually enable technologies to analyze deep learning models easily applicable to your existing projects. More features will be released soon. Feedback and feature request are always welcome, which help us to manage priorities. Please keep your eyes on Darkon.

Demo

Demo Page

Dependencies

Installation

Install Darkon alone

pip install darkon

Install with TensorFlow CPU

pip install darkon[tensorflow]

Install with TensorFlow GPU

pip install darkon[tensorflow-gpu]

Examples

API Documentation

Communication

Authors

Neosapience, Inc.

License

Apache License 2.0

References

[1] Cook, R. D. and Weisberg, S. "Residuals and influence in regression", New York: Chapman and Hall, 1982

[2] Koh, P. W. and Liang, P. "Understanding Black-box Predictions via Influence Functions" ICML2017

[3] Pearlmutter, B. A. "Fast exact multiplication by the hessian" Neural Computation, 1994

[4] Agarwal, N., Bullins, B., and Hazan, E. "Second order stochastic optimization in linear time" arXiv preprint arXiv:1602.03943

[5] Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra "Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization" ICCV2017

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].