Latest Posts

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 [https://www.safetyandhealthmagazine.com/articles/13407-hard-hats-know-the-facts] incur head injuries in the workplace, of which over one thousand [https://www.hexarmor.com/posts/the-hard-truth-about-safety-helmet-injuries-and-statistics] ultimately die. Workplace safety regulations exist to protect and promote wellbeing in the workplace, yet ensuring

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 [https://roboflow.ai], we're constantly adapting our product to make it as easy as possible for users to create custom computer vision models [https://models.roboflow.ai] on high quality data. While we have an implementation of YOLOv3 in Keras [https://models.roboflow.ai/object-detection/yolov3-keras]

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

20 Mar 2020 • 2 min read

How Flip Augmentation Improves Model Performance

Flipping an image (and its annotations) is a deceivingly simple technique that can improve model performance in substantial ways. Our models [https://models.roboflow.ai] are learning what collection of pixels and the relationship between those collections of pixels denote an object is in-frame. But machine learning models (like convolutional

18 Mar 2020 • 3 min read

Introducing Bounding Box Level Augmentations

Having training data that matches the diversity of your task is paramount to the success of your models. At Roboflow, we’re committed to providing you with state-of-the-art techniques that can improve your deep learning model [https://models.roboflow.com]’s performance -- without needing to collect any more data

16 Mar 2020 • 3 min read

LabelImg for Labeling Object Detection Data

Accurately labeled data is essential to successful machine learning, and computer vision is no exception. In this walkthrough, we’ll demonstrate how you can use LabelImg [https://github.com/tzutalin/labelImg] to get started with labeling your own data for object detection models [https://models.roboflow.ai/object-detection]. Label and

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.

11 Mar 2020 • 9 min read

Training a TensorFlow Faster R-CNN Object Detection Model on a Custom Dataset

Following this tutorial, you only need to change a couple lines of code to train an object detection model to your own dataset. Computer vision is revolutionizing medical imaging. Algorithms are helping doctors identify 1 in ten cancer patients they may have missed. There are even early indications that radiological

9 Mar 2020 • 3 min read

Why to Add Noise to Images for Machine Learning

Learn why adding noise can be effective as an image augmentation in computer vision modeling.

27 Feb 2020 • 4 min read

How to Select the Right Computer Vision Model Architecture

The success of your machine learning model [https://roboflow.ai] starts well before you ever begin training. Ensuring you have representative images, high quality labels [https://blog.roboflow.com/getting-started-with-labelimg-for-labeling-object-detection-data/] , appropriate preprocessing steps [https://blog.roboflow.com/tag/preprocessing/], and augmentations [https://blog.roboflow.com/tag/augmentation/] to guard against

25 Feb 2020 • 3 min read

Introducing an Improved PlantDoc Dataset for Plant Disease Object Detection

The world population is expected to reach 9.7 billion by 2050. That’s a lot of mouths to feed. Technology is powering the next generation of yield increases. Computer vision is especially critical to greener, more efficient production. For example, Blue River’s (John Deere) “See & Spray [https:

21 Feb 2020 • 4 min read

Why and How to Implement Random Crop Data Augmentation

Learn how to apply a random crop data augmentation to images for use in training computer vision models.

20 Feb 2020 • 2 min read

How to Win Pioneer

Pioneer.app is an online startup accelerator where companies are chosen based (partially) on weekly peer-review of progress updates. Roboflow has now been #1 on the global leaderboard for 18 consecutive weeks. In this post, I'm going to reveal our secrets and tell you how you can dethrone

14 Feb 2020 • 1 min read

Releasing an Improved Blood Count and Cell Detection (BCCD) Dataset

Computer vision is revolutionizing medical diagnoses by assisting doctors with patterns they may not have seen or identifying an error they may have overlooked. Thus, it's unsurprising one of the more popular "hello world" datasets of object detection is the blood count and cell detection dataset

12 Feb 2020 • 4 min read

Eliminating Boilerplate Code with Roboflow to Monitor Security Camera Footage

By using Roboflow [https://roboflow.ai], data scientist Alaa Senjab [https://alaasenjab.github.io/site/] reduced his time to train a custom object detection model [https://models.roboflow.ai/object-detection] detecting guns in security camera footage [https://public.roboflow.ai/object-detection/pistols] while increasing machine learning model accuracy [https://blog.

11 Feb 2020 • 2 min read

A popular self-driving car dataset is missing labels for hundreds of pedestrians

And that's a problem that is extremely dangerous. Machine learning, the process of teaching computer algorithms to perform new tasks by example, is poised to transform industries from agriculture [https://www.forbes.com/sites/bernardmarr/2019/03/15/the-amazing-ways-john-deere-uses-ai-and-machine-vision-to-help-feed-10-billion-people/] to insurance [https://news.microsoft.com/apac/features/ai-takes-the-pain-out-of-car-insurance-in-india/

9 Feb 2020 • 7 min read

Training a TensorFlow MobileNet Object Detection Model with a Custom Dataset

Change two lines of code and have a custom trained object detection model leveraging the TensorFlow 1.5 API.

5 Feb 2020 • 2 min read

When to Use Grayscale as a Preprocessing Step

Grayscale allows our models to be more computationally efficient. So when **shouldn't** we grayscale our images?

31 Jan 2020 • 4 min read

You Might Be Resizing Your Images Incorrectly

Resizing images is a critical preprocessing step in computer vision. Principally, our machine learning models [https://models.roboflow.ai] train faster on smaller images. An input image that is twice as large requires our network to learn from four times as many pixels — and that time adds up. Moreover, many

29 Jan 2020 • 9 min read

How to Convert Annotations from PASCAL VOC XML to COCO JSON

Convert from VOC XML to COCO JSON (or any format!) in four clicks.

27 Jan 2020 • 2 min read

Introducing Public Datasets

One of the most painstaking components of getting started with computer vision [https://blog.roboflow.com/getting-started-with-roboflow/] is getting access to clean, labeled data. For example, when the Roboflow [https://roboflow.ai] team built BoardBoss [https://boardboss.com], we painstakingly collected hundreds of Boggle board images [https://public.roboflow.ai/