Skip to content

Commit b4b3c81

Browse files
TingquanGaoTingquanGao
committed
update doc about PPHGNetV2
1 parent 5ca584f commit b4b3c81

File tree

1 file changed

+13
-3
lines changed

1 file changed

+13
-3
lines changed

‎docs/zh_CN/models/ImageNet1k/README.md

+13-3
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@
1212
- [2.3 Intel CPU 端知识蒸馏模型](#SSLD_intel_cpu)
1313
- [三、CNN 系列模型](#CNN_based)
1414
- [3.1 服务器端模型](#CNN_server)
15-
- [PP-HGNet 系列](#PPHGNet)
15+
- [PP-HGNet & PP-HGNetV2 系列](#PPHGNet)
1616
- [ResNet 系列](#ResNet)
1717
- [ResNeXt 系列](#ResNeXt)
1818
- [Res2Net 系列](#Res2Net)
@@ -136,9 +136,9 @@
136136

137137
<a name="PPHGNet"></a>
138138

139-
## PP-HGNet 系列
139+
## PP-HGNet & PP-HGNetV2 系列
140140

141-
PP-HGNet 系列模型的精度、速度指标如下表所示，更多关于该系列的模型介绍可以参考：[PP-HGNet 系列模型文档](PP-HGNet.md)。
141+
PP-HGNet & PP-HGNetV2 系列模型的精度、速度指标如下表所示，更多关于该系列的模型介绍可以参考：[PP-HGNet 系列模型文档](PP-HGNet.md)、[PP-HGNetV2 系列模型文档](PP-HGNetV2.md)。
142142

143143
| 模型 | Top-1 Acc | Top-5 Acc | time(ms)<br>bs=1 | time(ms)<br>bs=4 | time(ms)<br/>bs=8 | FLOPs(G) | Params(M) | 预训练模型下载地址 | inference模型下载地址 |
144144
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
@@ -148,6 +148,16 @@ PP-HGNet 系列模型的精度、速度指标如下表所示，更多关于该
148148
| PPHGNet_small_ssld | 0.8382 | 0.9681 | 2.46 | 5.12 | 8.77 | 8.53 | 24.38 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNet_small_ssld_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/PPHGNet_small_ssld_infer.tar) |
149149
| PPHGNet_base_ssld | 0.8500 | 0.9735 | 5.97 | - | - | 25.14 | 71.62 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNet_base_ssld_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/PPHGNet_base_ssld_infer.tar) |
150150

151+
| 模型 | Top-1 Acc | Top-5 Acc | time(ms)<br>bs=1 | time(ms)<br>bs=4 | time(ms)<br/>bs=8 | FLOPs(G) | Params(M) | stage-1预训练模型下载地址 | stage-2预训练模型下载地址 |inference模型下载地址(stage-2) |
152+
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
153+
| PPHGNetV2_B0 | 0.7777 | 0.9391 | 0.52 | - | - | - | - | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNet_tiny_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/PPHGNet_tiny_infer.tar) |
154+
| PPHGNetV2_B1 | 0.7918 | 0.9457 | 0.58 | - | - | - | - | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNetV2_B1_ssld_stage1_pretrained.pdparams)| [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNetV2_B1_ssld_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/PPHGNetV2_B1_ssld_infer.tar) |
155+
| PPHGNetV2_B2 | 0.8174 | 0.9588 | 0.95 | - | - | - | - | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNetV2_B2_ssld_stage1_pretrained.pdparams)| [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNetV2_B2_ssld_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/PPHGNetV2_B2_ssld_infer.tar) |
156+
| PPHGNetV2_B3 | 0.8298 | 0.9643 | 1.18 | - | - | - | - | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNetV2_B3_ssld_stage1_pretrained.pdparams)| [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNetV2_B3_ssld_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/PPHGNetV2_B3_ssld_infer.tar) |
157+
| PPHGNetV2_B4 | 0.8357 | 0.9672 | 1.46 | - | - | - | - | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNetV2_B4_ssld_stage1_pretrained.pdparams)| [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNetV2_B4_ssld_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/PPHGNetV2_B4_ssld_infer.tar) |
158+
| PPHGNetV2_B5 | 0.8475 | 0.9732 | 2.84 | - | - | - | - | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNetV2_B5_ssld_stage1_pretrained.pdparams)| [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNetV2_B5_ssld_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/PPHGNetV2_B5_ssld_infer.tar) |
159+
| PPHGNetV2_B6 | 0.8630 | 0.9784 | 5.29 | - | - | - | - | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNetV2_B6_ssld_stage1_pretrained.pdparams)| [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPHGNetV2_B6_ssld_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/PPHGNetV2_B6_ssld_infer.tar) |
160+
151161
<a name="ResNet"></a>
152162

153163
## ResNet 系列 <sup>[[1](#ref1)]</sup>

0 commit comments

Comments
 (0)