From e7ade6cd5ffc44a0b7ff0c822ecf20960935e39b Mon Sep 17 00:00:00 2001 From: Tingquan Gao Date: Thu, 19 Nov 2020 09:34:17 +0800 Subject: [PATCH] Add brief information about other models (#407) --- README.md | 21 +++++++++++++++++++++ README_cn.md | 24 +++++++++++++++++++++++- 2 files changed, 44 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index c1033a6a..31dbfbe2 100644 --- a/README.md +++ b/README.md @@ -61,6 +61,7 @@ PaddleClas is a toolset for image classification tasks prepared for the industry - [Inception series](#Inception_series) - [EfficientNet and ResNeXt101_wsl series](#EfficientNet_and_ResNeXt101_wsl_series) - [ResNeSt and RegNet series](#ResNeSt_and_RegNet_series) + - [Others](#Others) - HS-ResNet: arxiv link: [https://arxiv.org/pdf/2010.07621.pdf](https://arxiv.org/pdf/2010.07621.pdf). Code and models are coming soon! - Model training/evaluation - [Data preparation](./docs/en/tutorials/data_en.md) @@ -311,6 +312,26 @@ Accuracy and inference time metrics of ResNeSt and RegNet series models are show | RegNetX_4GF | 0.785 | 0.9416 | 6.46478 | 11.19862 | 8 | 22.1 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/RegNetX_4GF_pretrained.pdparams) | + +### Others + +Accuracy and inference time metrics of AlexNet, SqueezeNet series, VGG series, DarkNet53, ResNet50_ACNet and ResNet50_ACNet_deploy models are shown as follows. More detailed information can be refered to [Others](./docs/en/models/Others_en.md). + + +| Model | Top-1 Acc | Top-5 Acc | time(ms)
bs=1 | time(ms)
bs=4 | Flops(G) | Params(M) | Download Address | +|------------------------|-----------|-----------|------------------|------------------|----------|-----------|------------------------------------------------------------------------------------------------------| +| AlexNet | 0.567 | 0.792 | 1.44993 | 2.46696 | 1.370 | 61.090 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/AlexNet_pretrained.tar) | +| SqueezeNet1_0 | 0.596 | 0.817 | 0.96736 | 2.53221 | 1.550 | 1.240 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/SqueezeNet1_0_pretrained.tar) | +| SqueezeNet1_1 | 0.601 | 0.819 | 0.76032 | 1.877 | 0.690 | 1.230 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/SqueezeNet1_1_pretrained.tar) | +| VGG11 | 0.693 | 0.891 | 3.90412 | 9.51147 | 15.090 | 132.850 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/VGG11_pretrained.tar) | +| VGG13 | 0.700 | 0.894 | 4.64684 | 12.61558 | 22.480 | 133.030 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/VGG13_pretrained.tar) | +| VGG16 | 0.720 | 0.907 | 5.61769 | 16.40064 | 30.810 | 138.340 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/VGG16_pretrained.tar) | +| VGG19 | 0.726 | 0.909 | 6.65221 | 20.4334 | 39.130 | 143.650 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/VGG19_pretrained.tar) | +| DarkNet53 | 0.780 | 0.941 | 4.10829 | 12.1714 | 18.580 | 41.600 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_ImageNet1k_pretrained.tar) | +| ResNet50_ACNet | 0.767 | 0.932 | 5.33395 | 10.96843 | 10.730 | 33.110 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_ACNet_pretrained.tar) | +| ResNet50_ACNet
_deploy | 0.767 | 0.932 | 3.49161 | 7.78374 | 8.190 | 25.550 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_ACNet_deploy_pretrained.tar) | + + ## License diff --git a/README_cn.md b/README_cn.md index 3e136d26..2a2f296d 100644 --- a/README_cn.md +++ b/README_cn.md @@ -63,10 +63,11 @@ - [移动端系列](#移动端系列) - [SEResNeXt与Res2Net系列](#SEResNeXt与Res2Net系列) - [DPN与DenseNet系列](#DPN与DenseNet系列) - - [HRNet](HRNet系列) + - [HRNet](#HRNet系列) - [Inception系列](#Inception系列) - [EfficientNet与ResNeXt101_wsl系列](#EfficientNet与ResNeXt101_wsl系列) - [ResNeSt与RegNet系列](#ResNeSt与RegNet系列) + - [其他模型](#其他模型) - HS-ResNet: arxiv文章链接: [https://arxiv.org/pdf/2010.07621.pdf](https://arxiv.org/pdf/2010.07621.pdf)。 代码和预训练模型即将开源，敬请期待。 - 模型训练/评估 - [数据准备](./docs/zh_CN/tutorials/data.md) @@ -318,6 +319,27 @@ ResNeSt与RegNet系列模型的精度、速度指标如下表所示，更多关 | RegNetX_4GF | 0.785 | 0.9416 | 6.46478 | 11.19862 | 8 | 22.1 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/RegNetX_4GF_pretrained.pdparams) | + +### 其他模型 + +AlexNet、SqueezeNet系列、VGG系列、DarkNet53、ResNet50_ACNet与ResNet50_ACNet +_deploy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](./docs/zh_CN/models/Others.md)。 + + +| 模型 | Top-1 Acc | Top-5 Acc | time(ms)
bs=1 | time(ms)
bs=4 | Flops(G) | Params(M) | 下载地址 | +|------------------------|-----------|-----------|------------------|------------------|----------|-----------|------------------------------------------------------------------------------------------------------| +| AlexNet | 0.567 | 0.792 | 1.44993 | 2.46696 | 1.370 | 61.090 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/AlexNet_pretrained.tar) | +| SqueezeNet1_0 | 0.596 | 0.817 | 0.96736 | 2.53221 | 1.550 | 1.240 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/SqueezeNet1_0_pretrained.tar) | +| SqueezeNet1_1 | 0.601 | 0.819 | 0.76032 | 1.877 | 0.690 | 1.230 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/SqueezeNet1_1_pretrained.tar) | +| VGG11 | 0.693 | 0.891 | 3.90412 | 9.51147 | 15.090 | 132.850 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/VGG11_pretrained.tar) | +| VGG13 | 0.700 | 0.894 | 4.64684 | 12.61558 | 22.480 | 133.030 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/VGG13_pretrained.tar) | +| VGG16 | 0.720 | 0.907 | 5.61769 | 16.40064 | 30.810 | 138.340 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/VGG16_pretrained.tar) | +| VGG19 | 0.726 | 0.909 | 6.65221 | 20.4334 | 39.130 | 143.650 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/VGG19_pretrained.tar) | +| DarkNet53 | 0.780 | 0.941 | 4.10829 | 12.1714 | 18.580 | 41.600 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_ImageNet1k_pretrained.tar) | +| ResNet50_ACNet | 0.767 | 0.932 | 5.33395 | 10.96843 | 10.730 | 33.110 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_ACNet_pretrained.tar) | +| ResNet50_ACNet
_deploy | 0.767 | 0.932 | 3.49161 | 7.78374 | 8.190 | 25.550 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_ACNet_deploy_pretrained.tar) | + + ## 许可证书 本项目的发布受Apache 2.0 license许可认证。 -- GitLab