Latest Posts

2 Jun 2020 • 7 min read

Getting Started with Data Augmentation in Computer Vision

Data augmentation in computer vision is not new, but recently data augmentation has emerged on the forefront of state of the art modeling. YOLOv4, a new state of the art image detection model, uses a variety of data augmentation techniques to boost the models performance on COCO, a popular image

31 May 2020 • 1 min read

A New Video Tutorial: YOLOv4 in PyTorch

We heard your feedback! More video walkthroughs. Many users report that video tutorials help round out the edges of their knowledge to get the most from Roboflow. Seeing how others use Roboflow in real-time aids their own comprehension. Make YOLOv4 more accessible. YOLOv4 is a mere month old, and given

27 May 2020 • 2 min read

Introducing An Even Better Way to Preview Image Preprocessing and Augmentation

Knowing what preprocessing and augmentation steps to apply is hard. We've written many individual posts about the steps required to make informed resize decisions (how to resize images in image preprocessing) to random crop augmentation (how to implement random crop augmentation) and many steps in between. Show, Don&

25 May 2020 • 3 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.

24 May 2020 • 3 min read

Thermal Infrared Dataset for Object Detection

Computer vision is performed on a wide array of imaging data: photographs, screenshots [https://public.roboflow.com/object-detection/website-screenshots], videos [https://blog.roboflow.com/using-video-computer-vision/]. Commonly, this data is captured in similar perception to how humans see – along the visible red, green, and blue (RGB) color spectrum. However, there'

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.

15 May 2020 • 4 min read

When to Use Contrast as a Preprocessing Step

Adding contrast to images is a simple yet powerful technique to improve our computer vision models. But why? When considering how to add contrast to images and why we add contrast to images in computer vision, we must start with the basics. What is contrast? How contrast preprocessing improve our

13 May 2020 • 7 min read

Data Augmentation in YOLOv4

Learn how data augmentation is used in training YOLOv4 computer vision models.

8 May 2020 • 2 min read

When Should I Auto-Orient My Images?

Learn when you should auto-orient images for use in training computer vision models.

4 May 2020 • 5 min read

Breaking Down the Technology Behind Self-Driving Cars

In May 2016, Joshua Brown died in the Tesla's first autopilot crash [https://news.sky.com/story/tesla-driver-in-first-self-drive-fatal-crash-10330121] . The crash was attributed to the self-driving cars system not recognizing the difference between a truck and the bright sky above it. The system did not recognize the difference between

1 May 2020 • 6 min read

YOLOv3 Versus EfficientDet for State-of-the-Art Object Detection

YOLOv3 [https://models.roboflow.ai/object-detection/yolo-v3-pytorch] is known to be an incredibly performant, state-of-the-art model architecture: fast, accurate, and reliable. So how does the "new kid on the block," EfficientDet [https://blog.roboflow.com/breaking-down-efficientdet/], compare? Without spoilers, we were surprised by these results. NOTE: YOLO v5

29 Apr 2020 • 3 min read

Breaking Down Roboflow's Health Check Dimension Insights

Roboflow [https://roboflow.ai] improves datasets without any user effort. This includes dropping zero-pixel bounding boxes and cropping out-of-frame bounding boxes to be in-line with the edge of an image. Roboflow also notifies users of potential areas requiring attention like severely underrepresented classes (as was present in the original hard

28 Apr 2020 • 1 min read

Introducing the Roboflow Model Library

Over the past few months we've been building up a library of easy to use, open source computer vision models [https://models.roboflow.ai/]. We've now given them a home: the Roboflow Model Library [https://models.roboflow.ai]. https://models.roboflow.ai has an overview of

24 Apr 2020 • 4 min read

The Difference Between Missing and Null Annotations

A discussion of missing versus null annotations [https://blog.roboflow.com/glossary/#:~:text=annotation] and how VOC XML and COCO JSON handle them. Preparing data for computer vision models [https://models.roboflow.com/] is a tedious task. Even assuming training images are appropriately representative for inference, managing annotations quickly becomes

22 Apr 2020 • 7 min read

EfficientDet for Object Detection

In this post, we do a deep dive into the neural magic of EfficientDet [https://models.roboflow.ai/object-detection/efficientdet] for object detection [https://models.roboflow.ai/object-detection], focusing on the model's motivation, design, and architecture. Recently, the Google Brain team published [https://arxiv.org/abs/1911.09070]

16 Apr 2020 • 2 min read

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

The Open Data Science Conference (East) looked a bit different this year. While typically 6,000+ data science professionals gather in Boston for the Expo, the team at ODSC moved the entire event online. Still, over 3,000 "attendees" gathered in a shared Slack Workspace and online livestream

15 Apr 2020 • 12 min read

How to Create a Synthetic Dataset for Computer Vision

The appeals of synthetic data are alluring: you can rapidly generate a vast amount of diverse, perfectly labeled images for very little cost and without ever leaving the comfort of your office. The good news is: it's easy to try! And we're about to show you how.

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.

10 Apr 2020 • 3 min read

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

In a given year, approximately 65,000 workers wearing hard hats incur head injuries in the workplace, of which over one thousand ultimately die. Workplace safety regulations exist to protect and promote wellbeing in the workplace, yet ensuring awareness and compliance can be a challenge. Even in cases of accidental

8 Apr 2020 • 1 min read

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

We're introducing a new experiment this week: Roboflow is launching a Roboflow YouTube channel. We've been encouraged by the popularity of our computer vision tutorials. When Googling for some architectures, Roboflow content ranks at the top of what researchers, developers, and aspiring computer vision practitioners are

6 Apr 2020 • 6 min read

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

TensorFlow expedites the machine learning process markedly. From abstracting complex linear algebra to including pre-trained models and weights, getting the most out of TensorFlow is a full-time job. However, when it comes to loading data in ways that TensorFlow expects in order to perform as efficiently as it does, every

3 Apr 2020 • 2 min read

Using Computer Vision to Fight Coronavirus (COVID-19)

As global coronavirus case numbers continue to climb, troubling stories of hospital shortages, deaths, and disrupted communities fill the news. Frankly, it can leave one feeling disempowered – especially when the primary calls to action are staying home and wearing masks. Amid the global illness, there have been uplifting stories. Apple

1 Apr 2020 • 2 min read

Releasing a New YOLOv3 Implementation in PyTorch

At Roboflow, we're constantly adapting our product to make it as easy as possible for users to create custom computer vision models on high quality data. While we have an implementation of YOLOv3 in Keras, we continuously heard requests for support of YOLOv3 in PyTorch. Update: YOLO v5

30 Mar 2020 • 1 min read

Introducing Image Preprocessing and Augmentation Previews

Knowing how an image preprocessing step or augmentation is going to appear before you write the code for it is essential. Is it worth it to figure out the right amount of brightness? Will rotation increase variability appropriately? Roboflow is introducing features to take out the guesswork: preprocessing and augmentation