Blog

Jacob Solawetz

Founding Engineer @ Roboflow - ascending the 1/loss

Latest Posts by Jacob Solawetz

learn all about instance segmentation in computer vision

25 Mar 2026 • 14 min read

A Complete Guide to Instance Segmentation

We are excited to release support for instance segmentation projects on Roboflow. In this guide, you will learn the key concepts and practical tools behind instance segmentation

how to pick the right computer vision model size, model size tradeoffs

1 Mar 2026 • 4 min read

What to Think About When Choosing Vision Model Sizes

When training any machine learning model, you must trade off inference speed for accuracy. Larger models with more parameters are uniformly more accurate, and smaller models with fewer parameters are uniformly faster to infer.

mean average precision

30 May 2025 • 10 min read

What is Mean Average Precision (mAP) in Object Detection?

What is mean average precision? How do we calculate mAP?

What is YOLOv8? A Complete Guide

23 Oct 2024 • 12 min read

What is YOLOv8? A Complete Guide

YOLOv8 is a computer vision model architecture that you can use for object detection, segmentation, keypoint detection, and more.

How to Use Your GPU in a Docker Container

22 Oct 2024 • 10 min read

How to Use Your GPU in a Docker Container

Learn how to use your GPU in a Docker container and measure upir application's performance.

What is YOLOv6? The Ultimate Guide.

4 Jan 2024 • 7 min read

What is YOLOv6? The Ultimate Guide.

In this guide, we discuss what YOLOv6 is, how the model works, and the architectural improvements made in YOLOv6 over its predecessors.

What is YOLOv4? A Detailed Breakdown

4 Jan 2024 • 10 min read

What is YOLOv4? A Detailed Breakdown

In this guide, we discuss what YOLOv4 is, the architecture of YOLOv4, and how the model performs.

What is YOLOv7? A Complete Guide.

4 Jan 2024 • 7 min read

What is YOLOv7? A Complete Guide.

In this guide, we discuss what YOLOv7 is, how the model works, and the novel model architecture changes in YOLOv7.

ViT

14 Sep 2023 • 9 min read

Scaling up ViT Image Classification on Gaudi2 HPUs

Training large image transformers comes with heavy compute requirements - enter the Gaudi2 from Habana Labs, an Intel company.

cvpr

23 Jun 2023 • 3 min read

CVPR 2023 Highlights

Three members of the Roboflow team attended CVPR this year. Read our highlights from the conference and what trends we noticed.

What is Segment Anything Model (SAM)? A Breakdown.

7 Apr 2023 • 5 min read

What is Segment Anything Model (SAM)? A Breakdown.

Learn how Meta Research's new Segment Anything Model works to achieve high performance on image segmentation tasks.

Preview: Roboflow + GPT-4

29 Mar 2023 • 4 min read

Preview: Roboflow + GPT-4

Roboflow and GPT-4 will be even more powerful when used in conjunction. In this post we preview some of the new features that will be coming to Roboflow in the coming weeks.

Speculating on How GPT-4 Changes Computer Vision

16 Mar 2023 • 10 min read

Speculating on How GPT-4 Changes Computer Vision

OpenAI released GPT-4 showcasing strong multi-modal general AI capabilities in addition to impressive logical reasoning capability. Are general models going to obviate the need to label images and train models?

HPU vs GPU - Benchmarking the Frontier of AI Hardware

30 Dec 2022 • 5 min read

HPU vs GPU - Benchmarking the Frontier of AI Hardware

When you are training machine learning models, it is essential to pick hardware that optimizes your models performance relative to cost. In training, the name of the game is speed per epoch – how fast can your hardware run the calculations it needs to train your model on your data.

📸 Roboflow 100: A Multi-Domain Object Detection Benchmark

28 Nov 2022 • 5 min read

📸 Roboflow 100: A Multi-Domain Object Detection Benchmark

Roboflow 100 (RF100) is a crowdsourced object detection benchmark. The dataset consists of 100 datasets, 7 imagery domains, 224,714 images, and 829 class labels with over 11,170 labeling hours.

CVPR 2022 - Best Papers and Highlights

24 Jun 2022 • 3 min read

CVPR 2022 - Best Papers and Highlights

In this post, we take the opportunity to reflect on the computer vision research landscape at CVPR 2022 and highlight our favorite research papers and themes.

Train and Deploy YOLOS Transformer On a Custom Dataset

15 Jun 2022 • 9 min read

Train and Deploy YOLOS Transformer On a Custom Dataset

In this post, we showcase training and deploying YOLOS end to end, from labeling your data, to training your model, to deploying your model on AWS for inference.

How to Train Detectron2 for Custom Instance Segmentation

13 Apr 2022 • 6 min read

How to Train Detectron2 for Custom Instance Segmentation

A walk through on how to train Detectron2 to segment your custom objects from any image by providing our model with example training data.

What is CVAT (Computer Vision Annotation Tool)?

21 Mar 2022 • 7 min read

What is CVAT (Computer Vision Annotation Tool)?

Learn how to annotate images in CVAT, an open-source, web-based tool for labeling data for object detection, segmentation, classification, and other tasks.

Introducing New and Improved Roboflow Train

9 Mar 2022 • 3 min read

Introducing New and Improved Roboflow Train

Over the last year, thousands of custom computer vision models have been trained with Roboflow Train and millions of inferences have been made via Roboflow Deploy. Recently, we took a big step back to incorporate advancements in computer vision research and our learnings from working with our users into new

computer vision research internship

18 Jan 2022 • 2 min read

Introducing the Roboflow Universe Dataset Research Internship

We are seeking an intern who would be interested in first-authoring the paper that introduces the Roboflow Universe Datasets.

Google Colab vs AWS SageMaker

27 Dec 2021 • 5 min read

SageMaker Studio Lab vs Google Colab

Recently, AWS released SageMaker Studio Lab, its competitor service to Google Colab. I dove into comparing Google Colab to Studio Lab and here is what I found.

inference widget

22 Dec 2021 • 1 min read

Introducing the Roboflow Inference Widget

Now, you can easily test any model that has been trained with Roboflow Train by dragging an image file onto your dataset version page.

florence

9 Dec 2021 • 5 min read

Florence: A New Foundation for Computer Vision

Microsoft Research recently released the foundational Florence model, setting the state of the art across a wide array of computer vision tasks.

Stay Connected

Get the Latest in Computer Vision First