SciPy 2020 brought together over 1,200 attendees from across the scientific and analytic computing community. Our inaugural Maintainers Track proved very popular and we’re looking for another great cohort of open-source projects and maintainers to facilitate this year’s discussion.
Our goal is to give open-source project maintainers the opportunity to share experiences working in open source and update the SciPy community on a project’s latest challenges and achievements.
This could also be a great opportunity to engage the broader community on ways they can get involved in your project.
All Things Open is a polyglot technology conference focusing on the tools, processes, and people making open source possible.
For 2020 ATO went virtual, transmitting world-class open source TED-style talks and workshops to 10,000+ devices worldwide.
Check out the Clearview AI talk and Q&A recording on the All Things Open YouTube channel!
With Conda and Git installed, you can easily download and run the ResNet and DenseNet deep learning models used in CCTView directly from your computer on real-life CCTV footage.
You can also quickly use a Jupyter notebook to experiment with different models, vehicle matching algorithms, or perform your own image processing.
The repository github.com/samdbrice/cctview contains fully functional demos of the models, code, and other data referenced in the series.
Facial recognition dates back to more than half a century and has seen recent breakthroughs with the advent of web platforms such as Google and Facebook. The deep learning models that underpin modern facial recognition technology continue to improve as their underlying dataset continues to grow, encouraging companies such as Clearview to amass continuously larger repositories of personal information from the public web.
Cloud platforms such as AWS make it incredibly easy to scale data collection from online sources. Open-source tools such as TensorFlow and PyTorch make it very simple to apply state-of-the-art deep learning object detection and recognition techniques.
“The flames kept building until both cabinets were empty
Woody insisted on sitting in the garage until all that remained was ash.
Lance could only guess at what he’d helped to destroy.”
- The Secret History of Facial Recognition, Shaun Ravin
Throughout this series, we've learned how facial recognition technology is flawed by design; ominously, those flaws are masked behind statements such as “independently tested…99% accuracy.”
While the technology itself is neither good, nor bad, nor neutral, law enforcement’s application deserves conscious scrutiny because it implicates important Constitutional values. We may very well decide that values such as privacy and…
In 2016 researchers at Carnegie Mellon University demonstrated the use of “adversarial glasses” to successfully dodge facial recognition and, in some cases, entirely impersonate a target individual.
CCTView’s demo app is based on the LEAN Stack template deployed on free-dyno Heroku. It has been implemented to work offline with preprocessed NYCDOT CCTV footage from Tuesday, May 5th, 2020, between the hours of 1 PM and 2 PM.
The gist of LEAN Stack is using the same language and pattern (i.e., TypeScript and Dependency Injection) on both the client and the server. Using TypeScript (i.e., NodeJS) on the server-side was made possible thanks to the features being pre-extracted into a language-agnostic format.
Demystifying Clearview AI Blog Series (Part 6)
We started our deep learning development lifecycle by streaming data from the NYC DOT public API and deploying a cloud-based pipeline to scale the process. With our raw data in hand, we performed some simple cleaning and restructuring then evaluated the performance of various object detection models for identifying vehicles from our captured CCTV feeds. With the scope of this demonstration in mind, we’ll be skipping the remaining steps of the deep learning development lifecycle and instead transition to a standard application development lifecycle.
Comparing the deep learning development lifecycle above to the…
When a Deep Learning model processes an image, it first converts the image into a numerical format colloquially known as a vector embedding.
Mathematically speaking, a vector embedding can be described as a multidimensional number that can be sorted, compared, and manipulated. Using vector embedding, a Deep Learning model can calculate how similar two different face images are. Based on a given criterion, a model can determine that two very different face images are in-fact of the same person. …
This page intentionally left blank.