未验证 提交 d7d5353b 编写于 作者: L littletomatodonkey 提交者: GitHub

Merge pull request #200 from littletomatodonkey/add_ghost_metric

add ghostnet metrics
......@@ -99,6 +99,9 @@ Currently there are 32 pretrained models of the mobile series open source by Pad
| ShuffleNetV2_x1_5 | 19.352 | 14.000 |
| ShuffleNetV2_x2_0 | 34.770 | 28.000 |
| ShuffleNetV2_swish | 16.023 | 9.100 |
| GhostNet_x0_5 | 5.714 | 10.000 |
| GhostNet_x1_0 | 13.558 | 20.000 |
| GhostNet_x1_3 | 19.982 | 29.000 |
## Inference speed based on T4 GPU
......
docs/images/models/mobile_arm_top1.png

148.0 KB | W: | H:

docs/images/models/mobile_arm_top1.png

140.6 KB | W: | H:

docs/images/models/mobile_arm_top1.png
docs/images/models/mobile_arm_top1.png
docs/images/models/mobile_arm_top1.png
docs/images/models/mobile_arm_top1.png
  • 2-up
  • Swipe
  • Onion skin
......@@ -100,6 +100,9 @@ GhosttNet是华为于2020年提出的一种全新的轻量化网络结构,通
| ShuffleNetV2_x1_5 | 19.352 | 14.000 |
| ShuffleNetV2_x2_0 | 34.770 | 28.000 |
| ShuffleNetV2_swish | 16.023 | 9.100 |
| GhostNet_x0_5 | 5.714 | 10.000 |
| GhostNet_x1_0 | 13.558 | 20.000 |
| GhostNet_x1_3 | 19.982 | 29.000 |
## 基于T4 GPU的预测速度
......
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