This is Microsoft's Swin Transformer base model with patch size 4 and window size 12, pretrained on ImageNet-22k at 384x384 resolution. It can be used for image classification or as a feature extractor in computer vision applications.
In the Other AI space, Swin Base Patch4 Window12 384 In22k takes a focused approach. It focuses on delivering strong performance on image classification and providing a robust backbone for downstream vision tasks. Swin Base Patch4 Window12 384 In22k is an open-source project aimed at developers. The project is open source (MIT). The product ships for the web and API.
It is developed by microsoft, and the product first shipped in 2021. The project is developed in the open on GitHub with 16k stars.
Latest indexed changes and source events
microsoft/swin-base-patch4-window12-384-in22k verified by the PulseGate indexer
Other apps tracked under the same category.
