Roboflow Changelog: November 2022
Mohamed TraorePublished Dec 1, 2022
Each month, we share a recap of product and company updates. If you missed the last edition of the Roboflow Changelog, you can find it here.
A note on licensing: YOLOv5 is released under AGPL-3.0, which affects commercial use:
- On Roboflow cloud: a commercial license is included for every user, including the free plan.
- Self-hosted: you need an Enterprise license add-on, or you must open-source your application under AGPL-3.0.
- Permissive alternative: RF-DETR (opens in a new tab) is Apache 2.0, free for commercial use anywhere.
Roboflow Organize and Annotate
- Added improvements to the Polygon and Smart Polygon labeling tools
Roboflow Train and Deploy
Roboflow Universe
- Published the Roboflow-100 (opens in a new tab) (RF-100) Research Paper (opens in a new tab), Datasets (opens in a new tab), and Evaluation Code (opens in a new tab) | Roboflow 100: A New Object Detection Benchmark (opens in a new tab) (YouTube) | Roboflow 100 Benchmarking Tutorial with Google Colab and Docker (opens in a new tab) (YouTube)
- Added over 30 new dataset aggregate pages (opens in a new tab) for different Industries, Categories, and Sub-Categories
New Tutorials
- How to Create Segmentation Masks with Roboflow
- Added more resources to help with learning computer vision:
Projects from New Employees
Projects from Roboflow Blog Contributors
- Top 6 Environment Datasets for Computer Vision Projects
- What is Transfer Learning? A Guide for Beginners.
- Using Computer Vision to Save Sea Lions
- Top 6 Gaming Datasets for Computer Vision Projects
- Top 7 Sports Datasets for Computer Vision Projects
- Detecting and Reading QR Codes Using Computer Vision
Other
- Released the Notebooks repository on GitHub (opens in a new tab)
- Roboflow Team Onsite in New Orleans, LA
- Updates to the in-app Roboflow Tutorial
- Celebrated 1 year anniversaries for 2 team members
- Team meet-ups in Des Moines, IA
- Opened several positions (come help us democratize computer vision!)
- 32 new discussions on the Roboflow Forum (opens in a new tab)
- 15k+ new Universe projects (opens in a new tab)
- 19 new blog posts
- 11 new YouTube videos (opens in a new tab)
- Roboflow-100 research sponsored by Intel
- Featured in/by (publications and webinars): Amazon SageMaker Studio Lab continues to democratize ML with more scale and functionality (opens in a new tab) (Amazon Web Services), Streamlit App to Customize Computer Vision Inference Results (opens in a new tab) (CometML, Cool Data Science Projects Show)
User projects
- Identifying Objects in Multimedia Databases with Computer Vision, Finding Instances of Objects in Aerial Images using Earth Vision Small Scale Dataset (opens in a new tab), Timothy Malche on LinkedIn (opens in a new tab) | (2) (opens in a new tab), ros2jsguy (Twitter) (opens in a new tab), See as a Bee: UV Sensor for Aerial Strawberry Crop Monitoring (opens in a new tab), Modification of YOLO with GhostNet to Reduce Parameters and Computing Resources for Detecting Acute Lymphoblastic Leukemia (opens in a new tab), Artificial intelligence-based visual inspection system for structural health monitoring of cultural heritage (opens in a new tab), Selvaganapathy Senthamaraikannan on LinkedIn (opens in a new tab), Clemens Behrend on LinkedIn (opens in a new tab), Seeed Studio Vision AI sensor detect cats, dogs, and person (opens in a new tab), mallapraveen/Document-Extractor (opens in a new tab), Meat Freshness Image Classification With OpenCV and Python (opens in a new tab), KDNuggets (Twitter) (opens in a new tab), Development of species recognition models using (opens in a new tab), A Real-time Kiwifruit Detection Based on Improved YOLOv7 (opens in a new tab), Allan Ngoma on LinkedIn (opens in a new tab), Wooden blocks classification using YOLOv5 algorithm, torch, cv2, roboflow (opens in a new tab), Real-Time On-Tree Coconut Fruit Maturity Detection using Deep Neural Network (opens in a new tab), Machine Learning without Coding: Upload Images (opens in a new tab), 513 A Deep Learning Computer Vision Injury Prediction tool (MALTA)-Pilot study (opens in a new tab), Mohamed Sabek on LinkedIn (opens in a new tab), Moritz Feuerpfeil (Twitter) (opens in a new tab), AUTOMATIC BONE FRACTURE DETECTION IN X-RAY IMAGES USING DEEP LEARNING (opens in a new tab), Fruits Classification and Detection Application Using Deep Learning (opens in a new tab), A cascaded approach for page-object detection in scientific papers (opens in a new tab), A Comparative Study on Deep Feature Extraction Approaches for Visual Tracking of Industrial Robots (opens in a new tab), Automatic Recognition of Draft Marks on a Ship’s Board Using Deep Learning System (opens in a new tab), Detection of Japanese Quails (Coturnix japonica) in Poultry Farms Using YOLOv5 and Detectron2 Faster R-CNN (opens in a new tab)
