microsoft-swinv2-base-patch4-window12-192-22k · azureml v17
The Swin Transformer V2 model is a type of Vision Transformer, pre-trained on ImageNet-21k with a resolution of 192x192, is introduced in the <a href="https://arxiv.org/abs/2111.09883" target="_blank…
azureFoundry/azureml/microsoft-swinv2-base-patch4-window12-192-22k@17
The Swin Transformer V2 model is a type of Vision Transformer, pre-trained on ImageNet-21k with a resolution of 192x192, is introduced in the research-paper titled "Swin Transformer V2: Scaling Up Capacity and Resolution" authored by Liu et al. This model tries to resolve training instability, resolution gaps between pre-training and fine-tuning, and large labelled data issues in training and application of large vision models. This model generates hierarchical feature maps by merging image patches and computes self attention within a local window resulting in a linear computational complexity relative to input image size which is a significant improvement over vision transformers that take quadratic computational complexity.
Swin Transformer V2 introduces three improvements:
- a residual-post-norm method with cosine attention to improve training stability
- a log-spaced continuous position bias method, aiding the transfer
Specifications & capabilities
Provider specifications & access
1–1 / 1
- source model id
- azureml/microsoft-swinv2-base-patch4-window12-192-22k@17
- hosting
- foundry-managed-compute
- license
- apache-2.0
Explore more models