Blog

Latest Posts

Latest Posts Case Studies Product Updates Logistics Manufacturing

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

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

types

27 Feb 2020 • 4 min read

How to Select the Right Computer Vision Model Architecture

SUMMARY Choosing a computer vision model architecture for object detection involves trading off speed, accuracy, and deployment constraints. This post compares three architectures: YOLOv3, a single-shot detector optimized for speed at 60+ FPS with lower accuracy; MobileNet SSD, a single-shot detector slightly slower than YOLOv3 but stronger on

pioneer leaderboard post

20 Feb 2020 • 3 min read

How to Win Pioneer

SUMMARY Roboflow held the number one spot on the Pioneer.app global leaderboard for 18 consecutive weeks by following a consistent discipline: set concrete, completable goals each Sunday (not open-ended ones like "continue X"), then exceed them by focusing on controllable inputs rather than unpredictable outputs like

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

14 Feb 2020 • 2 min read

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

SUMMARY The Blood Count and Cell Detection (BCCD) dataset, a widely used object detection benchmark with 364 microscope images across three classes (WBC, RBC, and Platelets), had significant annotation gaps in its original release. The Roboflow team reviewed each image and added 187 missing labels, 183 of them red blood

boilerplate

12 Feb 2020 • 4 min read

Eliminating Boilerplate Code with Roboflow to Monitor Security Camera Footage

SUMMARY Data scientist Alaa Senjab built a real-time gun detection model for security camera footage using a 2,973-image handgun dataset from the University of Grenada, and reported that Roboflow cut roughly half of his project code by handling annotation validation, preprocessing, augmentation, and format conversion automatically. Roboflow

dataset

11 Feb 2020 • 2 min read

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

SUMMARY A hand-check of the 15,000 images in the widely used Udacity Dataset 2 found problems in 4,986 of them (33%), including thousands of unlabeled vehicles, hundreds of unlabeled pedestrians, dozens of unlabeled cyclists, and 217 completely unannotated images that contained real objects. Phantom annotations, duplicated bounding

public

27 Jan 2020 • 2 min read

Introducing Public Datasets

SUMMARY Getting access to clean, labeled data is one of the hardest parts of starting a computer vision project. Roboflow Public Datasets (public.roboflow.com) addresses this by hosting free, downloadable datasets covering domains from board games to aerial drone imagery, each available in formats including VOC XML, COCO JSON,

Stay Connected

Get the Latest in Computer Vision First