Ambarella
/

TopFormer

cooper_robot commited on 16 days ago

Commit

259dea3

1 Parent(s): f014efc

Add release note for v1.1.0

Files changed (1) hide show

README.md CHANGED Viewed

@@ -2,13 +2,13 @@
 library_name: pytorch
 ---
-![topformer_logo](resource/TopFormer.png)
 TopFormer introduces a lightweight token–pyramid transformer that progressively merges local and global representations, achieving strong accuracy–efficiency trade-offs for mobile and edge vision tasks.
 Original paper: [TopFormer: Token Pyramid Transformer for Mobile Vision](https://arxiv.org/abs/2204.05525)
-#TopFormer-B
 This model uses the TopFormer-Base variant, which balances representational capacity and computational efficiency through a hierarchical token pyramid. It is well suited for on-device image classification and as an efficient backbone for downstream tasks where low latency and power efficiency are critical.

 library_name: pytorch
 ---
+![topformer_logo](resource/Topformer.png)
 TopFormer introduces a lightweight token–pyramid transformer that progressively merges local and global representations, achieving strong accuracy–efficiency trade-offs for mobile and edge vision tasks.
 Original paper: [TopFormer: Token Pyramid Transformer for Mobile Vision](https://arxiv.org/abs/2204.05525)
+# TopFormer-B
 This model uses the TopFormer-Base variant, which balances representational capacity and computational efficiency through a hierarchical token pyramid. It is well suited for on-device image classification and as an efficient backbone for downstream tasks where low latency and power efficiency are critical.