Models

What is MobileNet V2 Classification?

MobileNet is a GoogleAI model well-suited for on-device, real-time classification (distinct from MobileNetSSD, Single Shot Detector). This implementation leverages transfer learning from ImageNet to your dataset.

About the model

Here is an overview of the

MobileNet V2 Classification

model:

Date of Release
Model Type Classification
Architecture
Framework Used
Annotation Format
Stars on GitHub +

What is MobileNetV2?

MobileNetV2 is a classification model (distinct from MobileNetSSDv2) developed by Google. It provides real-time classification capabilities under computing constraints in devices like smartphones. This implementation leverages transfer learning from ImageNet to your dataset.

MobileNetV2 Architecture

The MobileNetV2 architecture utilizes an inverted residual structure where the input and output of the residual blocks are thin bottleneck layers. MobileNetV2 also uses lightweight convolutions to filter features in the expansion layer. Finally, it removes non-linearities in the narrow layers.

MobileNetV2 Architecture


Image in Courtesy of Papers With Code

MobileNetV2 Results

MobileNet V2 outperforms MobileNet V1 with higher accuracies and lower latencies.

MobileNetSSDv2 Performance


Image in Courtesy of Google AI

Further Reading

How to Train MobileNetV2 On a Custom Dataset: https://blog.roboflow.com/how-to-train-mobilenetv2-on-a-custom-dataset/
MobileNetV2 Paper: https://arxiv.org/abs/1801.04381v4

Check out YOLOv8, defining a new state-of-the-art in computer vision

YOLOv8 is here, setting a new standard for performance in object detection and image segmentation tasks. Roboflow has developed a library of resources to help you get started with YOLOv8, covering guides on how to train YOLOv8, how the model stacks up against v5 and v7, and more.

Learn about YOLOv8

Check out YOLOv8, defining a new state-of-the-art in computer vision

YOLOv8 is here, setting a new standard for performance in object detection and image segmentation tasks. Roboflow has developed a library of resources to help you get started with YOLOv8, covering guides on how to train YOLOv8, how the model stacks up against v5 and v7, and more.

Learn about YOLOv8

Check out YOLOv8, defining a new state-of-the-art in computer vision

YOLOv8 is here, setting a new standard for performance in object detection and image segmentation tasks. Roboflow has developed a library of resources to help you get started with YOLOv8, covering guides on how to train YOLOv8, how the model stacks up against v5 and v7, and more.

Learn about YOLOv8

Check out YOLOv8, defining a new state-of-the-art in computer vision

YOLOv8 is here, setting a new standard for performance in object detection and image segmentation tasks. Roboflow has developed a library of resources to help you get started with YOLOv8, covering guides on how to train YOLOv8, how the model stacks up against v5 and v7, and more.

Learn about YOLOv8

Model Performance

Explore this model on Roboflow

MobileNet V2 Classification Annotation Format

MobileNet V2 Classification

uses the

annotation format. If your annotation is in a different format, you can use Roboflow's annotation conversion tools to get your data into the right format.

Convert data between formats

Deploy a computer vision model today

Join 100k developers curating high quality datasets and deploying better models with Roboflow.

Get started