Model card for davit tiny.msft in1k A DaViT image classification model. Trained on ImageNet 1k by paper authors. Thanks to Fredo Guan for bringing the classification backbone to timm . Model Details Model Type: Image classification / feature backbone Model Stats: Params (M): 28.4 GMACs: 4.5 Activations (M): 18.9 Image size: 224 x 224 Papers: DaViT: Dual Attention Vision Transformers: https://arxiv.org/abs/2204.03645 Original: https://github.com/dingmyu/davit Dataset: ImageNet 1k Model Usage Image Classification Feature Map Extraction Image Embeddings Model Comparison By Top 1 model top1 top1 err top5 top5 err param count img size crop pct interpolation davit base.msft in1k 84.634 15.366 97.014 2.986 87.95 224 0.95 bicubic davit small.msft in1k 84.25 15.75 96.94 3.06 49.75 224 0.95 bicubic davit tiny.msft in1k 82.676 17.324 96.276 3.724 28.36 224 0.95 bicubic Citation
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy