提交 01052dae 编写于 作者: G gaotingquan 提交者: Tingquan Gao

fix format

上级 047c907d
...@@ -51,7 +51,7 @@ ViT(Vision Transformer)系列模型是 Google 在 2020 年提出的,该模 ...@@ -51,7 +51,7 @@ ViT(Vision Transformer)系列模型是 Google 在 2020 年提出的,该模
#### 1.3.1 基于 V100 GPU 的预测速度 #### 1.3.1 基于 V100 GPU 的预测速度
| Models | Size | Latency(ms)<br>bs=1 | Latency(ms)<br>bs=4 | Latency(ms)<br>bs=8 | | Models | Size | Latency(ms)<br>bs=1 | Latency(ms)<br>bs=4 | Latency(ms)<br>bs=8 |
| -------------------------- | --------- | ----------------- | ------------------------------ | ------------------------------ | ------------------------------ | | -------------------------- | --------- | ----------------- | ------------------------------ | ------------------------------ |
| ViT_small_<br/>patch16_224 | 224 | 3.71 | 9.05 | 16.72 | | ViT_small_<br/>patch16_224 | 224 | 3.71 | 9.05 | 16.72 |
| ViT_base_<br/>patch16_224 | 224 | 6.12 | 14.84 | 28.51 | | ViT_base_<br/>patch16_224 | 224 | 6.12 | 14.84 | 28.51 |
| ViT_base_<br/>patch16_384 | 384 | 14.15 | 48.38 | 95.06 | | ViT_base_<br/>patch16_384 | 384 | 14.15 | 48.38 | 95.06 |
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册