Roboflow Universe Reviews and details

Social recommendations and mentions

• Show HN: I am using AI to drop hats outside my window onto New Yorkers

  FWIW you can use roboflow models on-device as well. detect.roboflow.com is just a hosted version of our inference server (if you run the docker somewhere you can swap out that URL for localhost or wherever your self-hosted one is running). Behind the scenes it’s an http interface for our inference[1] Python package which you can run natively if your app is in Python as well. Pi inference is pretty slow (probably... - Source: Hacker News / 6 months ago

• Show HN: Pip install inference, open source computer vision deployment

  It’s an easy to use inference server for computer vision models. The end result is a Docker container that serves a standardized API as a microservice that your application uses to get predictions from computer vision models (though there is also a native Python interface). It’s backed by a bunch of component pieces: * a server (so you don’t have to reimplement things like image processing & prediction... - Source: Hacker News / over 1 year ago

• Open discussion and useful links people trying to do Object Detection

  * Most of the time I find Roboflow extremely handy, I used it to merge datasets, augmentate, read tutorials and that kind of thing. Basically you just create your dataset with roboflow and focus on other aspects. Source: almost 2 years ago

• TensorFlow Datasets (TFDS): a collection of ready-to-use datasets

  For computer vision, there are 100k+ open source classification, object detection, and segmentation datasets available on Roboflow Universe: https://universe.roboflow.com. - Source: Hacker News / almost 2 years ago

• Ask HN: Who is hiring? (December 2022)

  Roboflow | Multiple Roles | Full-time (Remote) | https://roboflow.com/careers?ref=whoishiring1222 Roboflow is the fastest way to use computer vision in production. We help developers give their software the sense of sight. Our end-to-end platform[1] provides tooling for image collection, annotation, dataset exploration and curation, training, and deployment. Over 100k engineers (including engineers from 2/3... - Source: Hacker News / about 2 years ago

• Please suggest resources to learn how to work with pre-trained CV models

  Solid website and app overall for learning more about computer vision, discovering datasets, and keeping up with advancements in the field: * https://roboflow.com/learn * https://universe.roboflow.com (datasets) | https://blog.roboflow.com/computer-vision-datasets-and-apis/ * https://blog.roboflow.com. Source: about 2 years ago

• Suggestion for identification problem with shipping labels?

  If you're lacking training images, you can also use [Roboflow Universe](https://universe.roboflow.com) to obtain them (over 100 million labeled images available). Source: about 2 years ago

• Ask HN: Who is hiring? (November 2022)

  Roboflow | Multiple Roles | Full-time (Remote) | https://roboflow.com/careers Roboflow is the fastest way to use computer vision in production. We help developers give their software the sense of sight. Our end-to-end platform[1] provides tooling for image collection, annotation, dataset exploration and curation, training, and deployment. Over 100k engineers (including engineers from 2/3 Fortune 100 companies)... - Source: Hacker News / about 2 years ago

• When annotating an image, if a collection of an entity changes the nature of the entity, do you label them collectively or separately?

  Based on what I do/use when I prepare models: A good framework for creating and improving this dataset faster is to use Roboflow Universe and search “flowers” and “bouquets of flowers” in the search bar (it’s like Google Images for CV Datasets). You can search images by subject, or metadata, and clone them directly into a free public workspace (they house up to 10k images without charge). *... Source: about 2 years ago

• Need help on finding an area where machine learning is applicable on day-to-day life but not implemented already

  Lots of ideas will come to mind if you look and search through open source datasets: https://universe.roboflow.com/. Source: about 2 years ago

• Ask HN: Any good self-hosted image recognition software?

  Npx @roboflow/inference-server Then you can POST an image at any of the models to localhost:9001 eg base64 yourImage.jpg | curl -d @- "http://localhost:9001/some-model/1?api_key=xxxx" And you get back JSON predictions. There are also client libs[2] and sample code[3] for pretty much any language you might want to use it in. You can also run any of the models directly in a browser with WebGL[4], in a native mobile... - Source: Hacker News / about 2 years ago

• Ask HN: Who is hiring? (September 2022)

  Roboflow | Multiple Roles | Full-time (Remote) | https://roboflow.com/careers Roboflow is the fastest way to use computer vision in production. We help developers give their software the sense of sight. Our end-to-end platform[1] provides tooling for image collection, annotation, dataset exploration and curation, training, and deployment. Over 100k engineers (including engineers from 2/3 Fortune 100 companies)... - Source: Hacker News / over 2 years ago

• How do i use a pre trained model on a dataset?

  If you can find or put it on Roboflow Universe there’s example inference code you can use. Source: over 2 years ago

• Help With Datasets

  Yes, try searching on Roboflow Universe. People have shared over 100k image datasets there. Source: over 2 years ago

• ML-powered, human-in-the-loop system to manage wildlife camera trap images & annotations

  Also, they have well over 66 million images on there, and the search bar on https://universe.roboflow.com is akin to Google Images for CV datasets - https://blog.roboflow.com/computer-vision-datasets-and-apis/. Source: over 2 years ago

• I made a web app to count domino pips and keep track of your score across games

  Roboflow Universe is the biggest (and imo best) place to share computer vision datasets. It'll let people easily browse the images, convert & download in any common format, and even let them try out a pre-trained model before they train their own. Source: over 2 years ago

• How to make Vector recognize humans?

  How to use a pre-trained model at Roboflow Universe to let the Vector robot recognize humans! Learn from my new blog post. Here is a snapshot of what Vector sees on his cam. Source: over 2 years ago

• Hey everyone, I am new to AI and computer vision and collecting face recognition/analysis information. Anyone who can help?

  If you’re looking for datasets as well, you can find them by searching “faces” or “face” by subject or metadata on Roboflow Universe. Source: over 2 years ago

• How to build a working AI only using synthetic data in just 5 minutes

  Have you seen Roboflow Universe? They have thousands of projects from their community already labeled for download and use. I always start there when I want t to start a new model. Recently for my trash picking up robot I found a good litter dataset to start from. https://universe.roboflow.com/. - Source: Hacker News / over 2 years ago