• 7 min read
How to Train and Deploy a License Plate Detector to the Luxonis OAK
In this post, we will leverage Roboflow and the Luxonis OAK to train and deploy a custom license plate model to your OAK device.
Blog
Jacob Solawetz
Founding Engineer @ Roboflow - ascending the 1/loss
Latest Posts by Jacob Solawetz
• 2 min read
Introducing the Object Count Histogram
We are excited to announce the introduction of object count histograms, now available in the Roboflow dataset health check.
• 6 min read
How to Train Scaled-YOLOv4 to Detect Custom Objects
Object detection technology advances with the release of Scaled-YOLOv4. This blog is written to help you apply Scaled-YOLOv4 to your custom object detection task, to detect any object in the world, given the right training data.
• 8 min read
Scaled-YOLOv4 is Now the Best Model for Object Detection
SUMMARY
Scaled-YOLOv4 set a new state-of-the-art result for object detection on the Microsoft COCO benchmark at the time of its publication, surpassing Google's EfficientDet across both the speed and accuracy ends of the performance frontier. The model achieves this by scaling the depth, stages,
• 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.
• 6 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.
• 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.
• 4 min read
Deploy YOLOv5 to Jetson Xavier NX at 30FPS
Learn how to deploy a YOLOv5 model to a Jetson Xavier NX edge device.
• 7 min read
Use Resnet34 for Image Classification
SUMMARY
This tutorial walks through training a custom image classification model on the ResNet34 backbone using the fastai library and PyTorch, starting from an ImageNet pretrained checkpoint and fine-tuning it on a new dataset via transfer learning. The post uses a public flower classification dataset as a worked example,
• 4 min read
Fast.ai v2 Released - What's New?
SUMMARY
Fastai v2 brings a restructured three-layer API built on PyTorch, making it practical to move between computer vision and NLP tasks with minimal code changes. Key additions include a flexible infinite training loop, GPU-accelerated per-batch augmentation, and companion libraries (fastcore, fastscript, fastgpu) that extend Python and
• 14 min read
Deploy A Custom Model to the Luxonis OAK - A Quickstart Guide
This guide will take you the long distance from unlabeled images to a working computer vision model deployed and inferencing live at 15FPS on the affordable and scalable Luxonis OpenCV AI Kit (OAK) device.
• 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.
• 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)
• 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.
• 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
• 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
• 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.
• 6 min read
Train a YOLOv4-tiny Model on a Custom Dataset
Learn how to train a YOLOv4-tiny model on a custom dataset.
• 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.
• 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
• 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
• 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
• 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
• 7 min read
Data Augmentation in YOLOv4
Learn how data augmentation is used in training YOLOv4 computer vision models.
Stay Connected