Skip to content

Commit 177e4be

Browse files
TingquanGaoTingquanGao
committed
docs: fix
1 parent c667d10 commit 177e4be

File tree

2 files changed

+20
-9
lines changed

2 files changed

+20
-9
lines changed

‎docs/zh_CN/models/ImageNet1k/VGG.md

+4-4
Original file line numberDiff line numberDiff line change
@@ -61,10 +61,10 @@ VGG 由牛津大学计算机视觉组和 DeepMind 公司研究员一起研发的
6161

6262
| Models | Size | Latency(ms)<br>FP16<br>bs=1 | Latency(ms)<br>FP16<br>bs=4 | Latency(ms)<br>FP16<br>bs=8 | Latency(ms)<br>FP32<br>bs=1 | Latency(ms)<br>FP32<br>bs=4 | Latency(ms)<br>FP32<br>bs=8 |
6363
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
64-
| VGG11 | 224 | 256 | 2.24408 | 4.67794 | 7.6568 | 3.90412 | 9.51147 | 17.14168 |
65-
| VGG13 | 224 | 256 | 2.58589 | 5.82708 | 10.03591 | 4.64684 | 12.61558 | 23.70015 |
66-
| VGG16 | 224 | 256 | 3.13237 | 7.19257 | 12.50913 | 5.61769 | 16.40064 | 32.03939 |
67-
| VGG19 | 224 | 256 | 3.69987 | 8.59168 | 15.07866 | 6.65221 | 20.4334 | 41.55902 |
64+
| VGG11 | 224 | 2.24408 | 4.67794 | 7.6568 | 3.90412 | 9.51147 | 17.14168 |
65+
| VGG13 | 224 | 2.58589 | 5.82708 | 10.03591 | 4.64684 | 12.61558 | 23.70015 |
66+
| VGG16 | 224 | 3.13237 | 7.19257 | 12.50913 | 5.61769 | 16.40064 | 32.03939 |
67+
| VGG19 | 224 | 3.69987 | 8.59168 | 15.07866 | 6.65221 | 20.4334 | 41.55902 |
6868

6969
**备注：** 推理过程使用 TensorRT。
7070

‎docs/zh_CN/models/ImageNet1k/model_list.md

+16-5
Original file line numberDiff line numberDiff line change
@@ -35,6 +35,7 @@
3535
- [VAN](#VAN)
3636
- [PeleeNet](#PeleeNet)
3737
- [CSPNet](#CSPNet)
38+
- [VGG](#VGG)
3839
- [其他模型](#Others)
3940
- [3.2 轻量级模型](#CNN_lite)
4041
- [移动端系列](#Mobile)
@@ -470,21 +471,31 @@ RegNet 系列模型的精度、速度指标如下表所示，更多关于该系
470471
| ---------- | --------- | --------- | ---------------- | ---------------- | -------- | --------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
471472
| CSPDarkNet53 | 0.7725 | 0.9355 | - | - | - | 5.041 | 27.678 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/CSPDarkNet53_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/CSPDarkNet53_infer.tar) |
472473

474+
475+
<a name="VGG"></a>
476+
477+
## VGG 系列 <sup>[[20](#ref20)]</sup>
478+
479+
关于 VGG 系列模型的精度、速度指标如下表所示，更多介绍可以参考：[VGG 系列模型文档](VGG.md)。
480+
481+
| 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 |
482+
|------------------------|-----------|-----------|------------------|------------------|----------|-----------|------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------|
483+
| VGG11 | 0.693 | 0.891 | 1.72 | 4.15 | 7.24 | 7.61 | 132.86 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/VGG11_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/VGG11_infer.tar) |
484+
| VGG13 | 0.700 | 0.894 | 2.02 | 5.28 | 9.54 | 11.31 | 133.05 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/VGG13_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/VGG13_infer.tar) |
485+
| VGG16 | 0.720 | 0.907 | 2.48 | 6.79 | 12.33 | 15.470 | 138.35 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/VGG16_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/VGG16_infer.tar) |
486+
| VGG19 | 0.726 | 0.909 | 2.93 | 8.28 | 15.21 | 19.63 | 143.66 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/VGG19_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/VGG19_infer.tar) |
487+
473488
<a name="Others"></a>
474489

475490
## 其他模型
476491

477-
关于 AlexNet <sup>[[18](#ref18)]</sup>、SqueezeNet 系列 <sup>[[19](#ref19)]</sup>、VGG 系列 <sup>[[20](#ref20)]</sup>、DarkNet53 <sup>[[21](#ref21)]</sup> 等模型的精度、速度指标如下表所示，更多介绍可以参考：[其他模型文档](Others.md)。
492+
关于 AlexNet <sup>[[18](#ref18)]</sup>、SqueezeNet 系列 <sup>[[19](#ref19)]</sup>、DarkNet53 <sup>[[21](#ref21)]</sup> 等模型的精度、速度指标如下表所示，更多介绍可以参考：[其他模型文档](Others.md)。
478493

479494
| 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 |
480495
|------------------------|-----------|-----------|------------------|------------------|----------|-----------|------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------|
481496
| AlexNet | 0.567 | 0.792 | 0.81 | 1.50 | 2.33 | 0.71 | 61.10 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/AlexNet_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/AlexNet_infer.tar) |
482497
| SqueezeNet1_0 | 0.596 | 0.817 | 0.68 | 1.64 | 2.62 | 0.78 | 1.25 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SqueezeNet1_0_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/SqueezeNet1_0_infer.tar) |
483498
| SqueezeNet1_1 | 0.601 | 0.819 | 0.62 | 1.30 | 2.09 | 0.35 | 1.24 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SqueezeNet1_1_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/SqueezeNet1_1_infer.tar) |
484-
| VGG11 | 0.693 | 0.891 | 1.72 | 4.15 | 7.24 | 7.61 | 132.86 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/VGG11_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/VGG11_infer.tar) |
485-
| VGG13 | 0.700 | 0.894 | 2.02 | 5.28 | 9.54 | 11.31 | 133.05 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/VGG13_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/VGG13_infer.tar) |
486-
| VGG16 | 0.720 | 0.907 | 2.48 | 6.79 | 12.33 | 15.470 | 138.35 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/VGG16_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/VGG16_infer.tar) |
487-
| VGG19 | 0.726 | 0.909 | 2.93 | 8.28 | 15.21 | 19.63 | 143.66 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/VGG19_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/VGG19_infer.tar) |
488499
| DarkNet53 | 0.780 | 0.941 | 2.79 | 6.42 | 10.89 | 9.31 | 41.65 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/DarkNet53_pretrained.pdparams) | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/DarkNet53_infer.tar) |
489500

490501
<a name="CNN_lite"></a>

0 commit comments

Comments
 (0)