Roboflow Blog

3 Aug 2020 • 8 min read

PP-YOLO Surpasses YOLOv4 - State of the Art Object Detection Techniques

Baidu publishes PP-YOLO and pushes the state of the art in object detection research by building on top of YOLOv3, the PaddlePaddle deep learning framework, and cutting edge computer vision research.

3 Aug 2020 • 5 min read

Ontology Management for Computer Vision

SUMMARY Choosing class names at the start of a computer vision project and then needing to change them later is one of the most time-consuming parts of iterating on a dataset. This post covers practical ontology management strategies: labeling at the most specific level possible so classes can be

29 Jul 2020 • 2 min read

Advanced Augmentations in Roboflow

SUMMARY Roboflow added two augmentations to its platform, Mosaic and Cutout, that were central to accuracy gains in recent detection model research. Mosaic combines four training images into one, simulating random crops, mixing classes that rarely appear together, and varying object counts per image. Cutout overlays randomly placed black boxes

28 Jul 2020 • 14 min read

Benchmarking the Major Cloud Vision AutoML Tools

Until now, there has been little independent research published on the performance of AutoML tools - (both relative to each other and against state of the art open source models)

23 Jul 2020 • 1 min read

Roboflow can now ingest video!

SUMMARY Roboflow now accepts video file uploads directly, removing the manual step of extracting frames with command-line tools. Users select a sample rate to pull a subset of frames from the video, then annotate those frames using Roboflow's integrated labeling tools or by outsourcing the job in

21 Jul 2020 • 6 min read

Improving Infrastructure Asset Management with Computer Vision

SUMMARY Result! Data built a mobile app called Spobber that uses computer vision to detect hectometre signs along Dutch highways, verifying whether field assets match database records and flagging missing or damaged signs automatically. This guest post walks through their full pipeline: data collection from a moving vehicle, annotation, augmentation

18 Jul 2020 • 9 min read

Retail Store Item Detection using YOLOv5

SUMMARY This tutorial trains a YOLOv5 model on the SKU110k dataset to detect and localize products on retail store shelves, with dataset preparation handled through Roboflow and model training run in Google Colab. The resulting detector draws bounding boxes around shelf items and can support inventory tracking or automated checkout

16 Jul 2020 • 9 min read

How to Train a TensorFlow 2 Object Detection Model

Learn how to train a TensorFlow 2 object detection model on a custom dataset.

14 Jul 2020 • 3 min read

The TensorFlow 2 Object Detection Library is Here

SUMMARY The TensorFlow 2 Object Detection API brings EfficientDet models, eager execution, and improved training distribution strategies into the TensorFlow ecosystem, making it substantially easier to build and export custom object detection models. Roboflow's integration with the TF2 OD library lets developers point the data import step at

10 Jul 2020 • 5 min read

Convert Supervisely Annotations in Two Minutes

SUMMARY This guide walks through exporting an annotated dataset from Supervisely and converting its custom JSON format to YOLO Darknet format for use outside the Supervisely platform. The process involves downloading a tar archive of images and per-image annotation files, parsing the bounding box coordinates from Supervisely's

7 Jul 2020 • 4 min read

Introducing Class Label Remapping and Omission

With Roboflow Pro, you can now remap and omit class labels within Roboflow as a preprocessing step for your dataset version. Class management is a powerful tool to get the most out of your training data and your hard earned class label annotations.

5 Jul 2020 • 1 min read

Roboflow vs Scale

SUMMARY Roboflow and Scale serve different stages of the computer vision pipeline: Scale and similar services (LabelBox, SuperAnnotate, SageMaker Ground Truth) handle outsourced annotation, while Roboflow takes over after labeling to manage preprocessing, augmentation, dataset versioning, and training integrations. Roboflow imports annotations directly from most of these services, and its

1 Jul 2020 • 3 min read

How AI Acts as a Human Rights Watchdog for the Maasai People

SUMMARY A team of students built a computer vision system that processes satellite imagery from Google Earth Engine to monitor Maasai villages in Kenya and Tanzania, tracking settlement size, health, and evidence of burning to document land displacement by government and conservation interests. The model was trained using Roboflow'

1 Jul 2020 • 6 min read

Train a YOLOv4-tiny Model on a Custom Dataset

Learn how to train a YOLOv4-tiny model on a custom dataset.

28 Jun 2020 • 6 min read

Improving Uno with Computer Vision (Plus the Dataset so You Can Too)

SUMMARY Software engineer Adam Crawshaw built an Android app that uses object detection to automatically score Uno hands, handling the multi-round point system most players overlook. Starting from 41 source card images, he used OpenCV to synthetically composite cards into stacked groups, producing a dataset of 8,992 images

25 Jun 2020 • 7 min read

Creating BoardBoss: A Mobile Application that Improves Boggle

SUMMARY BoardBoss is a free iOS app, built by the Roboflow team, that scans a Boggle board with a smartphone camera, identifies letters in any orientation across more than 30 classes, and overlays all valid word solutions in augmented reality. The post walks through the full pipeline: collecting 355 images

24 Jun 2020 • 9 min read

How to Train Detectron2 on Custom Object Detection Data

Learn how to train a Detectron2 model on a custom object detection dataset.

19 Jun 2020 • 5 min read

How to Convert Annotations from PASCAL VOC to YOLO Darknet

SUMMARY PASCAL VOC stores bounding box annotations as XML files with absolute pixel coordinates, while YOLO Darknet uses plain text files with class index and normalized center coordinates. Converting between them means restructuring both the file format and the coordinate representation. This post walks through both formats with concrete examples

18 Jun 2020 • 4 min read

How to Build a Custom Open Images Dataset for Object Detection

SUMMARY Google's Open Images dataset contains millions of labeled images across hundreds of object classes, all under a CC BY 4.0 license, but downloading the full dataset requires over 500 GB of storage. This post shows how to use the OIDv4_ToolKit to query specific classes and

12 Jun 2020 • 16 min read

Responding to the Controversy about YOLOv5

SUMMARY When Roboflow published an early YOLOv5 benchmark in June 2020, the machine learning community raised two substantive objections: whether naming Glenn Jocher's repository YOLOv5 was appropriate given no paper was published, and whether the benchmark methodology was reproducible and fair. This post documents the full history of

10 Jun 2020 • 4 min read

YOLOv5 is Here: State-of-the-Art Object Detection at 140 FPS

SUMMARY Released in June 2020, YOLOv5 is a PyTorch-based object detection model from Ultralytics that differs from YOLOv4 in several practical ways: it uses a lighter Ultralytics PyTorch framework instead of Darknet, its smallest variant (YOLOv5s) weighs 27 MB compared to 244 MB for YOLOv4, and it offers faster

3 Jun 2020 • 3 min read

Teaching a Drone to Fly on Auto Pilot with Roboflow

SUMMARY Victor Antony, a data scientist at the University of Rochester, built a computer vision autopilot system to detect gates that a drone must fly through, starting from only 300 images captured in a warehouse. Using Roboflow, he applied augmentations for rotation, lighting, and blur to expand the dataset to

2 Jun 2020 • 7 min read

Getting Started with Data Augmentation in Computer Vision

SUMMARY Data augmentation artificially expands training sets by applying flips, crops, rotations, noise, and occlusion techniques, and it has a measurable impact on object detection accuracy even when collecting more labeled images is not practical. RF-DETR relies heavily on augmentation to achieve its COCO benchmark results, and the same

31 May 2020 • 1 min read

A New Video Tutorial: YOLOv4 in PyTorch

SUMMARY This post introduces a 20-minute video tutorial covering how to use Roboflow to prepare a custom dataset and train a YOLOv4 model in PyTorch. It accompanies the team's earlier written guides on the YOLOv4 architecture and Darknet-based training, extending them to the PyTorch framework for