Qualcomm® AI HubAI Hub
HomeCompute ModelsSwin-Tiny

Swin-Tiny

Imagenet classifier and general purpose backbone.

SwinTiny is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.

Snapdragon® X Elite
Snapdragon X Elite CRD
11.0ms
Inference Time
91.3inferences / s
Throughput
57MB
Memory Usage
666NPU
Layers
See more metrics
Model RepositoryHugging FaceResearch Paper

Technical Details

Model checkpoint:Imagenet
Input resolution:224x224
Number of parameters:28.8M
Model size (float):110 MB
Model size (w8a16):29.9 MB

Applicable Scenarios

  • Medical Imaging
  • Anomaly Detection
  • Inventory Management

Licenses

Source Model:BSD-3-CLAUSE
Deployable Model:AI-HUB-MODELS-LICENSE

Tags

  • backbone

Supported Compute Devices

  • Snapdragon X Elite CRD
  • Snapdragon X Plus 8-Core CRD

Supported Compute Chipsets

  • Snapdragon® X Elite
  • Snapdragon® X Plus 8-Core

Related Models

See all models
View details for the Swin-Small model.

Swin-Small

Imagenet classifier and general purpose backbone.

View details for the Swin-Base model.

Swin-Base

Imagenet classifier and general purpose backbone.

View details for the MobileNet-v2 model.

MobileNet-v2

Imagenet classifier and general purpose backbone.

View details for the DenseNet-121 model.

DenseNet-121

Imagenet classifier and general purpose backbone.

View details for the GoogLeNet model.

GoogLeNet

Imagenet classifier and general purpose backbone.

Looking for more? See models created by industry leaders.

Discover Model Makers