Allen Institute for AI

Classification

Image classification is the task of assigning an input image, a single label drawn from a fixed set of categories. Image classification models are trained and evaluated on large classification datasets such as ImageNet that has 1000 image categories.

Try it for yourself
1. Upload an Image (or choose one from the examples)
Examples...
Image:
Click to upload your own image
2. Run a model

ResNet50

Deep Residual Learning for Image RecognitionKaiming HeXiangyu ZhangShaoqing RenJian SunICLR2016

A very popular model that is often used as a backbone CNN to extract visual representations. It achieves a Top 1 accuracy of 76.1 on ImageNet (1000 categories).

ResNeXt-101-32x8d

Aggregated Residual Transformations for Deep Neural NetworksSaining XieRoss B. GirshickPiotr DollárZhuowen TuKaiming HeCVPR2017

Achieves a very impressive Top 1 accuracy of 79.3 on ImageNet (1000 categories).

MobileNet V2

MobileNetV2: Inverted Residuals and Linear BottlenecksMark SandlerAndrew HowardMenglong ZhuAndrey ZhmoginovLiang-Chieh ChenCVPR2018

A lean mobile network that achieves a Top 1 accuracy of 72.0 on ImageNet (1000 categories) with just 3.4 Million parameters