Latest Posts

20 Nov 2020 • 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.

16 Nov 2020 • 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.

15 Nov 2020 • 4 min read

Bringing Street Murals to Life with Computer Vision

In Bedford–Stuyvesant, Brooklyn (BedStuy), Yuri Fukuda regularly walks by a mural that showcases prominent female leaders. Since October 2005, a stunning 3,300 square foot mural, When Women Pursue Justice by ArtMakers-NYC, has had a central place in the BedStuy art scene. The mural celebrates 90 women who have

13 Nov 2020 • 5 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.

8 Nov 2020 • 3 min read

Hands on with the Roboflow Infer Web Application Interface Builder

After you train a model with Roboflow Train [https://docs.roboflow.com/train], you're provided with three immediate ways to use your model: a curl command, the direct URL, and an Example Web App. In this post, we'll demonstrate hands on how to use the web

6 Nov 2020 • 4 min read

Occlusion Techniques in Computer Vision

Computer vision models learn to model a task from a training set, however, like all deep learning models, they are prone to overfit the data they have been shown, making poor inferences in the wild. Computer vision models, like all machine learning models [https://blog.roboflow.com/computer-vision-model-tradeoff/], tend overfit

3 Nov 2020 • 3 min read

Evaluating Object Detection Models with mAP by Class

When evaluating an object detection model in computer vision, mean average precision [https://blog.roboflow.com/mean-average-precision/] is the most commonly cited metric for assessing performance. Remember, mean average precision is a measure of our model's ability to correctly predict bounding boxes at some confidence level – commonly mAP@

1 Nov 2020 • 3 min read

How to Use the Detectron2 Model Zoo (for Object Detection)

Detectron2 is Facebook's open source library for implementing state-of-the-art computer vision techniques in PyTorch. Facebook introduced Detectron2 [https://ai.facebook.com/blog/-detectron2-a-pytorch-based-modular-object-detection-library-/] in October 2019 as a complete rewrite of Detectron (which was implemented in Caffe). Facebook uses Detectron2 in a wide array of their products, including

30 Oct 2020 • 5 min read

How This Fulbright Scholar is Using Computer Vision to Protect Endangered Species

The below post is by Kasim Rafiq, a conservationist, Fulbright Scholar, and National Geographic Explorer studying at UC Santa Cruz. Kasim holds a PhD in Wildlife Ecology from Liverpool John Moores University. Introduction Nature underpins everything. From our global economy to our wellbeing and survival. Everything relies on nature. Unfortunately,

28 Oct 2020 • 2 min read

Train Test Split Guide and Overview

In order to ensure our models are generalizing well (rather than memorizing training data), it is best practice to create a train, test split. That is, absent rigor, our models can easily overfit to a small subset of examples we've collected. Look no further than Tesla using computer

26 Oct 2020 • 6 min read

Luxonis OAK-D - Deploy a Custom Object Detection Model with Depth

We are pretty excited about the Luxonis OpenCV AI Kit (OAK-D) device at Roboflow, and we're not alone. Our excitement has naturally led us to create another tutorial on how to train and deploy a custom object detection model leveraging Roboflow and DepthAI, to the edge, with depth, faster.

26 Oct 2020 • 6 min read

Behind the Design of an Augmented Reality Board Game App

During the summer of 2019, I received a Facebook message from Roboflow co-founder Brad Dwyer [https://twitter.com/braddwyer] asking me if I wanted to design a new mobile app he was working on. His previous app, Magic Sudoku [https://magicsudoku.com/], had recently generated some buzz online and even

25 Oct 2020 • 5 min read

How to Save and Load Model Weights in Google Colab

Google Colab is Google's hosted Jupyter Notebook product that provides a free compute environment, including GPU and TPU. Colab comes "batteries included" with many popular Python packages installed, making it a choice tool for easy model experimentation. For this reason, the Roboflow Model Library includes many

19 Oct 2020 • 9 min read

Using Computer Vision to Help Deaf and Hard of Hearing Communities

The below post is a lightly edited guest post by David Lee, a data scientist using computer vision to boost tech accessibility for communities that need it. David has open sourced all materials related to this project on his GitHub [https://github.com/insigh1/GA_Data_Science_Capstone]. The post

18 Oct 2020 • 7 min read

An Introduction to the COCO Dataset

The computer vision research community benchmarks new models and enhancements to existing models to test model performance. Benchmarking happens using standard datasets which can be used across models. With this approach, the efficacy of various models can be compared, in general, to show how one model is more or less

14 Oct 2020 • 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 easy.

12 Oct 2020 • 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.

12 Oct 2020 • 1 min read

Fighting Wildfires with Computer Vision

Abhishek Ghosh is training a computer vision model to detect the first signs of smoke from a forest fire with the ultimate hope of dispatching a drone to douse it with water before it gets out of control. It's all part of a project he's working

11 Oct 2020 • 6 min read

How Tesla Teaches Cars to Stop

Creating successful computer vision models requires handling an ever growing set of edge cases. At the 2020 Conference on Computer Vision and Pattern Recognition (CVPR), Tesla's Senior Director of AI, Andrej Karpathy, gave a talk on how Tesla is building autonomous vehicles. Karpathy's team is responsible

6 Oct 2020 • 2 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

5 Oct 2020 • 23 min read

Glossary of Common Computer Vision Terms

Computer Vision (and Machine Learning in general) is one of those fields that can seem hard to approach because there are so many industry-specific words (or common words used in novel ways) that it can feel a bit like you're trying to learn a new language when you're trying to get started.

4 Oct 2020 • 3 min read

Improving Cancer Research with Computer Vision

Computer vision is improving life sciences. From the early identification of cancer [https://venturebeat.com/2020/01/01/google-healths-ai-identifies-breast-cancer-in-mammogram-imagery-with-fewer-false-positives/] to improving plant health [https://public.roboflow.com/object-detection/plantdoc], machine vision is enabling us to create more accurate diagnoses, cures, and research methods. Mateo Sokac is advancing progress in cancer

2 Oct 2020 • 4 min read

What is a Label Map?

In this post, we will demystify the label map by discussing the role that it plays in the computer vision annotation process. Then we will get hands on with some real life examples using a label map.

27 Sep 2020 • 3 min read

Introducing Grayscale and Hue/Saturation Augmentations

Roboflow [https://roboflow.com] is constantly improving how developers can build better computer vision models based on better input data. One key piece to this puzzle is enabling users to select augmentations that best improve dataset representation through augmentation. Augmentation creates altered training data based on existing examples. Image augmentation