Skip to content

Commit eb87d54

Browse files
authored
Update model_zoo.md
1 parent 84819ed commit eb87d54

File tree

1 file changed

+5
-5
lines changed

1 file changed

+5
-5
lines changed

docs/model_zoo.md

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -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
88

99
| 模型 | 数据集合 | Depth multiplier | 下载地址 | Accuray Top1/5 Error|
1010
|---|---|---|---|---|
11-
| MobieNetV2_1.0x | ImageNet | 1.0x | [MobileNetV2_1.0x](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar) | 72.15%/90.65% |
12-
| 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% |
13-
| 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% |
14-
| 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% |
15-
| 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% |
11+
| MobileNetV2_1.0x | ImageNet | 1.0x | [MobileNetV2_1.0x](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar) | 72.15%/90.65% |
12+
| 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% |
13+
| 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% |
14+
| 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% |
15+
| 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% |
1616

1717
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。
1818

0 commit comments

Comments
 (0)