alibi-detect
Element
alibi-detect | Element | |
---|---|---|
9 | 615 | |
2,085 | 10,656 | |
1.6% | 0.9% | |
7.6 | 9.9 | |
12 days ago | 4 days ago | |
Python | TypeScript | |
GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
alibi-detect
-
Exploring Open-Source Alternatives to Landing AI for Robust MLOps
Numerous tools exist for detecting anomalies in time series data, but Alibi Detect stood out to me, particularly for its capabilities and its compatibility with both TensorFlow and PyTorch backends.
- Looking for recommendations to monitor / detect data drifts over time
-
[D] Distributions to represent an Image Dataset
That is, to see whether a test image belongs in the distribution of the training images and to provide a routine for special cases. After a bit of reading Ive found that this is related to the field of drift detection in which I tried out alibi-detect . Whereby the training images are trained by an autoencoder and any subsequent drift will be flagged by the AE.
-
[D] Which statistical test would you use to detect drift in a dataset of images?
Wasserstein distance is not very suitable for drift detection on most problems given that the sample complexity (and estimation error) scales with O(n^(-1/d)) with n the number of instances (100k-10m in your case) and d the feature dimension (192 in your case). More interesting will be to use for instance a detector based on the maximum mean discrepancy (MMD) with estimation error of O(n^(-1/2)). Notice the absence of the feature dimension here. You can find scalable implementations in Alibi Detect (disclosure: I am a contributor): MMD docs, image example. We just added the KeOps backend for the MMD detector to scale and speed up the drift detector further, so if you install from master, you can leverage this backend and easily scale the detector to 1mn instances on e.g. 1 RTX2080Ti GPU. Check this example for more info.
-
Ask HN: Who is hiring? (January 2022)
Seldon | Multiple positions | London/Cambridge UK | Onsite/Remote | Full time | seldon.io
At Seldon we are building industry leading solutions for deploying, monitoring, and explaining machine learning models. We are an open-core company with several successful open source projects like:
* https://github.com/SeldonIO/seldon-core
* https://github.com/SeldonIO/mlserver
* https://github.com/SeldonIO/alibi
* https://github.com/SeldonIO/alibi-detect
* https://github.com/SeldonIO/tempo
We are hiring for a range of positions, including software engineers(go, k8s), ml engineers (python, go), frontend engineers (js), UX designer, and product managers. All open positions can be found at https://www.seldon.io/careers/
- What Machine Learning model monitoring tools can you recommend?
- Ask HN: Who is hiring? (December 2021)
-
[D] How do you deal with covariate shift and concept drift in production?
I work in this area and also contribute to outlier/drift detection library https://github.com/SeldonIO/alibi-detect. To tackle this type of problem, I would strongly encourage following a more principled, fundamentally (statistically) sound approach. So for instance measuring metrics such as the KL-divergence (or many other f-divergences) will not be that informative since it has a lot of undesirable properties for the problem at hand (in order to be informative requires already overlapping distributions P and Q, it is asymmetric, not a real distance metric, will not scale well with data dimensionality etc). So you should probably look at Integral Probability Metrics (IPMs) such as the Maximum Mean Discrepancy (MMD) instead which have much nicer behaviour to monitor drift. I highly recommend the Interpretable Comparison of Distributions and Models NeurIPS workshop talks for more in-depth background.
-
[D] Is this a reasonable assumption in machine learning?
All of the above functionality and more can be easily used under a simple API in https://github.com/SeldonIO/alibi-detect.
Element
- Element: A sovereign and secure communications platform
-
Reset password in Cinny
I made an account in Cinny using my Github account. I am trying to migrate my account into element.io. How do I do this? Forgot password is not even an option in Cinny.
-
IT Pro Tuesday #280 - Identity/Access Mgmt, Training, Collaboration Tool & More
Element is an open-source instant messaging client built on the Matrix protocol, offering users features such as end-to-end encryption, file sharing, and voice/video calls. The self-hosted version accommodates up to 200 users at no charge, providing a budget-saving secure and collaborative communication platform. perthguppy describes it as a "slack style team chat."
- Um pouco da realidade de Copacabana - principalmente aos finais de semana
- O Fazueli está destruindo o Sul do Brasil
-
[For Hire] Computer Programming Tutor or Teacher (C, C++, and others, details inside)
Hello! I am offering my services as a C and C++ tutor/teacher for $25 an hour. You pay at the end of each hour and you can walk away without paying for the first hour if you are unsatisfied. I can work with beginners through the upper intermediate level. I can either tutor you while you take an existing course or teach you from scratch. As for my experience, I've been working with C++ for over three years, driven by my love of learning, programming, and technology. I’ve worked with over 50 clients during the past year with all positive feedback. Below is my policy when dealing with less familiar subjects. While C and C++ are the languages I am most experienced with, I regularly take on jobs in other languages. When working with subjects I am not overly or at all familiar with, I only charge $20 an hour, sometimes with additional discounts. This is to compensate for the extra time I may need to spend on the project. I am a quick learner who can learn what I need to help you through your course as you go. I have done this with many people before with great results. Please note this works best the closer you are to the start of your course. The following are subjects I have tutored for at least one semester: C, C++, Python, OpenGL, operating systems, drivers, R, and Web Assembly. I addition, I have some limited experience in the following subjects: HTML, CSS, JavaScript, Lua, Bash, Vulkan, CMake, NASM, Pandas, and Asio. Again, please keep in mind that even if your subject is not listed, I may still be able to help you. Please DM me if you are interested in hiring me or have any questions at all. We will work via Element (https://element.io) voice/screen share calls, so please make sure you have a mic available. I look forward to hearing from you.
- Correios, Petrobras, Banco do Brasil e outras empresas estatais devem ser privatizadas?
-
Matrix 2.0: The Future of Matrix
- Various GUI instability bugs: chats that are suddenly empty, text suddenly randomly overlaid on other text
1: https://github.com/vector-im/element-web/issues/24392
- O mais engraçado desse dado é que na lista tem países que a esquerda considera "social democrata" e nenhum desses países tem 418 estatais 🤡
-
Possible scam
"You can set up an account and download the ELEMENT chat app on your phone or pc https://element.io/ so I can get you in contact with the hiring officer as soon as possible."
What are some alternatives?
pytorch-widedeep - A flexible package for multimodal-deep-learning to combine tabular data with text and images using Wide and Deep models in Pytorch
cinny - Yet another matrix client
cleanlab - The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.
Screenshare-with-audio-on-Discord-with-Linux - A repo trying to gather all info regarding proper screensharing on Discord with Desktop Audio for linux users
pyod - A Comprehensive and Scalable Python Library for Outlier Detection (Anomaly Detection)
simplex-chat - SimpleX - the first messaging network operating without user identifiers of any kind - 100% private by design! iOS, Android and desktop apps 📱!
seldon-core - An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models
schildichat-desktop - Matrix client / Element Web/Desktop fork
river - 🌊 Online machine learning in Python
Tox - The future of online communications.
Anomaly_Detection_Tuto - Anomaly detection tutorial on univariate time series with an auto-encoder
Mattermost - Mattermost is an open source platform for secure collaboration across the entire software development lifecycle..