Blog

Joseph Nelson

Roboflow cofounder and CEO. On a mission to transform every industry by democratizing computer vision. Previously founded and sold a machine learning company.

Latest Posts by Joseph Nelson

boggle

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

How to Convert Annotations from PASCAL VOC to YOLO Darknet

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

Responding to the Controversy about YOLOv5

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

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

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

How to Train a YOLOv5 Model On a Custom Dataset

10 Jun 2020 • 10 min read

How to Train a YOLOv5 Model On a Custom Dataset

Learn how to train a YOLOv5 model on a custom dataset.

drone flying with computer vision

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

YOLOv4 in PyTorch

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

image preprocessing

27 May 2020 • 3 min read

Introducing An Even Better Way to Preview Image Preprocessing and Augmentation

SUMMARY Roboflow's revamped preprocessing and augmentation previews let you see exactly what each step does to your images before committing to a pipeline, replacing guesswork and boilerplate transformation code with a visual interface. The update covers choices like aspect-ratio-preserving resize strategies (padding, crop, reflect) and the

How to Train a VGG-16 Image Classification Model on Your Own Dataset

25 May 2020 • 4 min read

How to Train a VGG-16 Image Classification Model on Your Own Dataset

Learn how to train a VGG-16 image classification model on a custom dataset.

Thermal Infrared Dataset for Object Detection

24 May 2020 • 3 min read

Thermal Infrared Dataset for Object Detection

SUMMARY Thermal infrared cameras detect surface temperature rather than reflected light, which makes them useful for detecting people and objects in darkness, smoke, or other low-visibility conditions where RGB cameras fail. Roboflow released a free 203-image thermal dataset of people and dogs, captured with a Seek Compact XR

How to Train YOLOv4 on a Custom Dataset

21 May 2020 • 9 min read

How to Train YOLOv4 on a Custom Dataset

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

Breaking Down Roboflow's Health Check Dimension Insights

29 Apr 2020 • 4 min read

Breaking Down Roboflow's Health Check Dimension Insights

SUMMARY Resizing images for computer vision is not a simple stretch-to-fill operation: aspect ratio distortion, small image outliers, and extreme width-to-height ratios all affect what a model can learn. Roboflow's Dimension Insights tool, part of the Dataset Health Check, visualizes every image in a

Roboflow Presents at Open Data Science Conference (ODSC) East 2020

16 Apr 2020 • 2 min read

Roboflow Presents at Open Data Science Conference (ODSC) East 2020

SUMMARY At ODSC East 2020, Roboflow delivered a three-hour online tutorial walking through the full object detection workflow: framing a good problem, collecting and labeling images, preprocessing, selecting augmentations, training a model, and running inference. Slides, a Colab notebook, and additional resources from the session are publicly available for

How to Train an EfficientDet Object Detection Model with a Custom Dataset

13 Apr 2020 • 5 min read

How to Train an EfficientDet Object Detection Model with a Custom Dataset

Learn how to train an EfficientDet object detection model with a custom dataset.

hard hat

10 Apr 2020 • 3 min read

Introducing an Improved Hard Hat Dataset for Computer Vision in Workplace Safety

SUMMARY Detecting hard hat compliance with computer vision requires a well-annotated dataset that reflects the variety of real construction environments. This post introduces a cleaned version of the Northeastern University hard hat dataset, now available on Roboflow Universe with 7,035 images and 27,039 bounding box annotations across

Our First Video Tutorial: YOLOv3 in PyTorch on a Custom Dataset

8 Apr 2020 • 1 min read

Our First Video Tutorial: YOLOv3 in PyTorch on a Custom Dataset

SUMMARY This post announces the launch of Roboflow's YouTube channel with a debut video tutorial on training YOLOv3 in PyTorch on a custom dataset, using an Ultralytics implementation and Roboflow for data preparation. The video format was introduced to provide more guided support as the volume and variety

How to Create to a TFRecord File for Computer Vision and Object Detection

6 Apr 2020 • 7 min read

How to Create to a TFRecord File for Computer Vision and Object Detection

SUMMARY TFRecord is TensorFlow's binary serialized data format: it reduces disk footprint, supports streaming subsets of large datasets, and is required by many TensorFlow-based object detection pipelines. Creating one from PASCAL VOC XML or COCO JSON labels involves writing protocol buffer definitions and serialization code, which is

computer vision to fight covid-19

3 Apr 2020 • 2 min read

Using Computer Vision to Fight Coronavirus (COVID-19)

SUMMARY Chest X-rays and CT scans show patterns associated with COVID-19 that computer vision models can learn to flag, offering a supplementary diagnostic path in settings where PCR testing infrastructure is limited. Early open datasets combined COVID-19 scans with existing pneumonia radiology data to give models enough

1 Apr 2020 • 2 min read

Releasing a New YOLOv3 Implementation in PyTorch

SUMMARY Roboflow released a PyTorch implementation of YOLOv3 built on the Ultralytics codebase, complementing the existing Keras version that users had requested an alternative to. In testing on a 12-class chess piece detection task, 300 epochs on Google Colab produced 0.93 recall and 0.978 mAP@50 in

image preprocessing

30 Mar 2020 • 1 min read

Introducing Image Preprocessing and Augmentation Previews

SUMMARY Choosing augmentation settings without previewing the result means iterating blind, generating dataset versions only to discover the brightness shift was too aggressive or the rotation too extreme. Roboflow added preprocessing and augmentation previews so you can hover over an image in the dataset builder and see exactly how each

How Flip Augmentation Improves Model Performance

20 Mar 2020 • 2 min read

How Flip Augmentation Improves Model Performance

SUMMARY Convolutional neural networks can learn orientation-specific pixel patterns rather than the underlying object, causing them to miss detections when an object appears mirrored from its training examples. Flip augmentation creates horizontally or vertically reflected copies of training images alongside their remapped bounding box annotations, giving the model more

Introducing Bounding Box Level Augmentations

18 Mar 2020 • 3 min read

Introducing Bounding Box Level Augmentations

SUMMARY Standard image augmentation applies transforms to the entire frame, but bounding box level augmentation applies transforms only to the pixels inside each labeled bounding box, letting you vary brightness, blur, or other properties of a target object independently from its background. This technique, drawn from a 2019 Google research

LabelImg for Labeling Object Detection Data

16 Mar 2020 • 4 min read

LabelImg for Labeling Object Detection Data

SUMMARY LabelImg is a free, open source Python-based tool for drawing bounding box annotations on images and exporting them in VOC XML or YOLO text format, making it a common starting point for small object detection labeling projects. The post walks through installing via pip, labeling best practices (keeping

The Importance of Blur as an Image Augmentation Technique

13 Mar 2020 • 3 min read

The Importance of Blur as an Image Augmentation Technique

Learn about the efficacy of blur as an image augmentation step in computer vision model training.

Stay Connected

Get the Latest in Computer Vision First