未验证 提交 1cd90f93 编写于 作者: W wuzewu 提交者: GitHub

Update model_zoo.md

上级 ea17e12b
...@@ -8,11 +8,11 @@ PaddleSeg对所有内置的分割模型都提供了公开数据集下的预训 ...@@ -8,11 +8,11 @@ PaddleSeg对所有内置的分割模型都提供了公开数据集下的预训
| 模型 | 数据集合 | Depth multiplier | 下载地址 | Accuray Top1/5 Error| | 模型 | 数据集合 | Depth multiplier | 下载地址 | Accuray Top1/5 Error|
|---|---|---|---|---| |---|---|---|---|---|
| MobieNetV2_1.0x | ImageNet | 1.0x | [MobileNetV2_1.0x](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar) | 72.15%/90.65% | | MobileNetV2_1.0x | ImageNet | 1.0x | [MobileNetV2_1.0x](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar) | 72.15%/90.65% |
| MobieNetV2_0.25x | ImageNet | 0.25x |[MobileNetV2_0.25x](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_25_pretrained.tar) | 53.21%/76.52% | | MobileNetV2_0.25x | ImageNet | 0.25x |[MobileNetV2_0.25x](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_25_pretrained.tar) | 53.21%/76.52% |
| MobieNetV2_0.5x | ImageNet | 0.5x | [MobileNetV2_0.5x](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_5_pretrained.tar) | 65.03%/85.72% | | MobileNetV2_0.5x | ImageNet | 0.5x | [MobileNetV2_0.5x](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_5_pretrained.tar) | 65.03%/85.72% |
| MobieNetV2_1.5x | ImageNet | 1.5x | [MobileNetV2_1.5x](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x1_5_pretrained.tar) | 74.12%/91.67% | | MobileNetV2_1.5x | ImageNet | 1.5x | [MobileNetV2_1.5x](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x1_5_pretrained.tar) | 74.12%/91.67% |
| MobieNetV2_2.0x | ImageNet | 2.0x | [MobileNetV2_2.0x](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x2_0_pretrained.tar) | 75.23%/92.58% | | MobileNetV2_2.0x | ImageNet | 2.0x | [MobileNetV2_2.0x](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x2_0_pretrained.tar) | 75.23%/92.58% |
用户可以结合实际场景的精度和预测性能要求,选取不同`Depth multiplier`参数的MobileNet模型。 用户可以结合实际场景的精度和预测性能要求,选取不同`Depth multiplier`参数的MobileNet模型。
......
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