Jacob Solawetz Profile
Jacob Solawetz

@JacobSolawetz

Followers
60
Following
5
Media
0
Statuses
10

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

Joined April 2019
Don't wanna be here? Send us removal request.
@JacobSolawetz
Jacob Solawetz
4 years
RT @hiamitabha: An example of using @roboflow Inference API. Here is a demo of our Vector being able to recognize….
0
4
0
@JacobSolawetz
Jacob Solawetz
4 years
RT @MarisaDataNerd: Come to see a cool @streamlit and @roboflow webinar!.
0
2
0
@JacobSolawetz
Jacob Solawetz
4 years
RT @braddwyer: 👀.
0
2
0
@JacobSolawetz
Jacob Solawetz
4 years
🚨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:
lu.ma
Check out the perfect pair - Roboflow and Streamlit take your machine learning app to the next level. Join our webinar to find out how on September 15th at 10…
0
0
4
@JacobSolawetz
Jacob Solawetz
4 years
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
blog.roboflow.com
This post is a comprehensive guide on how to implement object tracking with your object detection model to track your custom objects
0
3
3
@JacobSolawetz
Jacob Solawetz
4 years
RT @roboflow: Excited to see our partner Rex at LEDA teaching a class about Roboflow in Taiwan 🇹🇼!. ➡ Anyone, anywhere can create a free pu….
0
3
0
@JacobSolawetz
Jacob Solawetz
4 years
Tweet card summary image
en.wikipedia.org
0
0
0
@JacobSolawetz
Jacob Solawetz
4 years
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.
Tweet card summary image
arxiv.org
We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. Following BERT developed in the natural language...
0
0
0
@JacobSolawetz
Jacob Solawetz
4 years
RT @braddwyer: Zero-Shot Object Tracking: we added @OpenAI's CLIP as the feature extractor for Deep SORT to create a general-purpose object….
0
102
0