• 2 min read
Introducing the Object Count Histogram
We are excited to announce the introduction of object count histograms, now available in the Roboflow dataset health check.
• 2 min read
Roboflow Changelog: January 2021
Welcome to our monthly changelog where we catalog our recent feature additions and improvements. If you missed it, you can find last month's changelog here.
This month we launched Roboflow Annotate, an integrated image annotation tool included in all Roboflow plans. In the first few weeks, over 1500
• 6 min read
Football, Kaggle, Roboflow: Using Computer Vision to Tackle Helmet Safety
SUMMARY
This post walks through a Kaggle competition case study focused on detecting American football helmet impacts to help researchers understand conditions that contribute to traumatic brain injury. The authors use Scaled-YOLOv4, selected for its inference speed, and use Roboflow to preprocess and augment the provided training images. A
• 2 min read
Get a Hosted API for your Object Detection Model
SUMMARY
After training a custom object detection model, the hardest part is often deploying it without managing servers that sit idle or buckle under load. Roboflow Infer addresses this by training a model on your labeled dataset and immediately exposing it as a hosted API that scales with demand, so
• 4 min read
Tackling the Internet of Things with Roboflow: Object Detection Apps on Android
Joo chan Kim, PhD student, is developing an object detection application for Android devices that can identify specific IoT sensors by using a custom detection model.
• 6 min read
How to Train Scaled-YOLOv4 to Detect Custom Objects
Object detection technology advances with the release of Scaled-YOLOv4. This blog is written to help you apply Scaled-YOLOv4 to your custom object detection task, to detect any object in the world, given the right training data.
• 5 min read
Apple's M1 is up to 3.6x as fast at training machine learning models
We compared the Apple M1 chip to the Intel Core i5 chip on an object detection task using Create ML.
• 2 min read
Unveiling Our New Limited Edition T-Shirt
SUMMARY
Roboflow is offering a limited-edition t-shirt, designed by Los Angeles artist Von Deon, to community members whose computer vision projects get featured on the Roboflow blog. Von Deon's design features an abstract rendering of Lenny, Roboflow's raccoon mascot, with his signature floral style.
• 2 min read
Introducing Roboflow Annotate
SUMMARY
Roboflow Annotate is a self-serve image annotation tool built directly into the Roboflow platform, removing the friction of managing a separate labeling tool outside your pipeline. The integrated design supports team collaboration from a single source of truth and makes it straightforward to jump in and out of
• 2 min read
Share Your Datasets with the Computer Vision Community
SUMMARY
Roboflow offers to publicly host community-contributed computer vision datasets, making them discoverable to tens of thousands of developers and automatically indexed by Google Dataset Search. Hosted datasets are available for download in every major annotation format, including Pascal VOC XML, COCO JSON, and TFRecords, with no conversion work
• 1 min read
Roboflow Changelog: December 2020
Welcome to the first of our monthly changelogs, where we will be cataloging our recent feature additions and improvements.
Roboflow Organize
* Added ability to rebalance train/test split
* Clarified pro plan features in-app
* Sped up thumbnail generation
* Added image upload by URL to the upload API
* Paginated the image
• 8 min read
Scaled-YOLOv4 is Now the Best Model for Object Detection
SUMMARY
Scaled-YOLOv4 set a new state-of-the-art result for object detection on the Microsoft COCO benchmark at the time of its publication, surpassing Google's EfficientDet across both the speed and accuracy ends of the performance frontier. The model achieves this by scaling the depth, stages,
• 2 min read
Revamping Train, Validation, Test, Split Management
Splitting data into train, validation, and test splits is essential to building good computer vision models. Today, we are announcing in-app changes to Roboflow that make it even easier to manage your train test splits as you are working through the computer vision workflow.
• 6 min read
Google Researchers Say Underspecification is Ruining Your Model Performance. Here's Five Ways to Fix That.
We read that Google underspecification paper so you don't have to.
• 6 min read
YOLOv4 - Ten Tactics to Build a Better Model
The YOLO v4 repository is currently one of the best places to train a custom object detector, and the capabilities of the Darknet repository are vast. In this post, we discuss and implement ten advanced tactics in YOLO v4 so you can build the best object detection model from your custom dataset.
• 3 min read
Hands on with the Roboflow Infer Web Application Interface Builder
SUMMARY
After training a model with Roboflow Train, the Example Web App gives an immediate browser-based interface to test predictions: upload an image or provide a URL, adjust confidence thresholds and bounding box overlap, filter classes, and view results as an annotated image or raw JSON. Because the app
• 3 min read
Evaluating Object Detection Models with mAP by Class
SUMMARY
Overall mAP scores can mask weak spots in a multi-class object detection model: a 98% aggregate hides the fact that one class is dragging performance down. Roboflow Train addresses this by surfacing per-class mAP on both the validation and training sets after every training run, so you
• 5 min read
How This Fulbright Scholar is Using Computer Vision to Protect Endangered Species
SUMMARY
Kasim Rafiq, a Fulbright Scholar and National Geographic Explorer at UC Santa Cruz, is building a vehicle-mounted computer vision system that automatically detects and photographs wildlife during safari game drives, then uses those detections for species population surveys at a fraction of the cost of traditional field methods.
• 2 min read
Train Test Split Guide and Overview
SUMMARY
Splitting a dataset into training, validation, and test sets is a core practice for detecting overfitting and ensuring a computer vision model generalizes beyond its training examples. Roboflow defaults to a 70/20/10 split at upload time but gives you direct control: you can assign individual image batches
• 31 min read
Software Engineering Daily Podcast
Roboflow co-founder Brad Dwyer was a guest on the Software Engineering Daily podcast. Listen on your favorite podcast app (Apple Podcasts, Spotify, Overcast, Stitcher), or see the full transcript below.
Software Engineering Daily: Roboflow: Computer Vision Models with Brad Dwyer on Apple PodcastsTraining a computer vision model is not
• 2 min read
Introducing an Improved Shear Augmentation
Today, we introduce a new and improved shear augmentation. We'll walk through some details on the change, as well as some intuition and results backing up our reasoning.
• 2 min read
Fighting Wildfires with Computer Vision
SUMMARY
Abhishek Ghosh, a graduate student at Texas A&M working with AI For Mankind, trained an EfficientDet D0 computer vision model to detect early smoke from forest fires using images from weather towers. Using Roboflow Pro, he applied advanced augmentations and a static crop along the horizon line
• 6 min read
How Tesla Teaches Cars to Stop
SUMMARY
Tesla Senior Director of AI Andrej Karpathy's CVPR 2020 talk reveals that even a seemingly straightforward computer vision task like stop sign detection involves dozens of edge cases: occluded signs, non-standard mounting, signs that do not require stopping, and conditionally active signs. Tesla handles this by
• 1 min read
Roboflow Wins $15,000 Award
Roboflow is honored to be named as one of Iowa's most promising startups and one of the top 3 winners of the Pappajohn Entrepreneurial Venture Competition. The annual awards honor companies with innovative technology that have grown quickly.
Since launching in January, Roboflow has helped over 8,000
Stay Connected