Jacob Solawetz

Machine Learning @ Roboflow - building tools and knowledge artifacts help practitioners solve computer vision. Previously quant trading, NLP research.

[Jacob Solawetz @JacobSolawetz]

@josephofiowa @MadeWithStone Haha so awesome - was that at max speed?

[Learn With A Robot @learnwitharobot]

An example of using @roboflow Inference API. https://t.co/vHy7wGNbo9 Here is a demo of our Vector being able to recognize another Vector by employing the inference API. https://t.co/I9gY91eFZU Very useful resource for robots and other edge devices which lack compute.

[Marisa Smith @MarisaDataNerd]

Come to see a cool @streamlit and @roboflow webinar!

[Brad Dwyer @braddwyer]

👀

[Jacob Solawetz @JacobSolawetz]

🚨Webinar Inbound: Come check out some really cool technology with @MarisaDataNerd I this Wednesday at 10AM CT.

We will be showcasing how you can use Roboflow + Streamlit to deploy computer vision applications in the web browser.

Register for free here: https://t.co/C5WaCFJBzJ

[Jacob Solawetz @JacobSolawetz]

Following up our recent work on zero-shot object tracking - we (@MadeWithStone @braddwyer) posted a guide here on how to do object tracking, eliminates labeling your tracks and training another model https://t.co/m2luAqfGNC

[Roboflow @roboflow]

Excited to see our partner Rex at LEDA teaching a class about Roboflow in Taiwan 🇹🇼!

➡ Anyone, anywhere can create a free public Roboflow account and start exploring computer vision. Visit https://t.co/r2iuJnztYo to get started today.

[Jacob Solawetz @JacobSolawetz]

https://t.co/1ixQck7nc3

[Jacob Solawetz @JacobSolawetz]

I've been waiting for someone to try this! Image patch level token identities is an interesting way to capture it. Would be interesting to see something on the granularity of image patches, down to pixels - maybe on micro model

https://t.co/gAAkgADhHu

[Brad Dwyer @braddwyer]

Zero-Shot Object Tracking: we added @OpenAI's CLIP as the feature extractor for Deep SORT to create a general-purpose object tracker that can work in conjunction with any object detection model.

https://t.co/cM4htM6ul4