diff --git a/README.md b/README.md
index 790f9bf6e00e1cf8c6ce5e1aa9357537a31823f6..38aa6efc77f1f1ad4f5c26cf3b366813983c10c0 100644
--- a/README.md
+++ b/README.md
@@ -7,7 +7,8 @@
PaddleClas is a toolset for image classification tasks prepared for the industry and academia. It helps users train better computer vision models and apply them in real scenarios.
**Recent update**
-- 2020.10.12 Add Paddle-Lite demo。
+- 2020.11.09 Add `InceptionV3` architecture and pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 79.1%.
+- 2020.10.12 Add Paddle-Lite demo.
- 2020.10.10 Add cpp inference demo and improve FAQ tutorial.
- 2020.09.17 Add `HRNet_W48_C_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 83.62%. Add `ResNet34_vd_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 79.72%.
- 2020.09.07 Add `HRNet_W18_C_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 81.16%.
@@ -263,6 +264,7 @@ Accuracy and inference time metrics of Inception series models are shown as foll
| Xception65 | 0.8100 | 0.9549 | 7.26158 | 25.88778 | 25.95 | 35.48 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/Xception65_pretrained.tar) |
| Xception65_deeplab | 0.8032 | 0.9449 | 7.60208 | 26.03699 | 27.37 | 39.52 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/Xception65_deeplab_pretrained.tar) |
| Xception71 | 0.8111 | 0.9545 | 8.72457 | 31.55549 | 31.77 | 37.28 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/Xception71_pretrained.tar) |
+| InceptionV3 | 0.7914 | 0.9459 | 6.64054 | 13.53630 | 11.46 | 23.83 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/InceptionV3_pretrained.tar) |
| InceptionV4 | 0.8077 | 0.9526 | 12.99342 | 25.23416 | 24.57 | 42.68 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/InceptionV4_pretrained.tar) |
diff --git a/README_cn.md b/README_cn.md
index 151c8f30249b27b9bfb1e74ef3521b277d3d0bd3..a0dc71b8dfd6ec2a4353ae8e7d29241093a3587e 100644
--- a/README_cn.md
+++ b/README_cn.md
@@ -7,6 +7,7 @@
飞桨图像分类套件PaddleClas是飞桨为工业界和学术界所准备的一个图像分类任务的工具集，助力使用者训练出更好的视觉模型和应用落地。
**近期更新**
+- 2020.11.09 添加`InceptionV3 `结构和模型，在ImageNet-1k上Top-1 Acc可达79.14%。
- 2020.11.04 添加图像分类[常见问题2020第一季第一期](./docs/zh_CN/faq_series/faq_2020_s1.md) 7个新问题，并且计划以后每周一会更新，欢迎大家持续关注。
- 2020.10.12 添加Paddle-Lite demo。
- 2020.10.10 添加cpp inference demo，完善`FAQ 30问`教程。
@@ -268,6 +269,7 @@ Inception系列模型的精度、速度指标如下表所示，更多关于该
| Xception65 | 0.8100 | 0.9549 | 7.26158 | 25.88778 | 25.95 | 35.48 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/Xception65_pretrained.tar) |
| Xception65_deeplab | 0.8032 | 0.9449 | 7.60208 | 26.03699 | 27.37 | 39.52 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/Xception65_deeplab_pretrained.tar) |
| Xception71 | 0.8111 | 0.9545 | 8.72457 | 31.55549 | 31.77 | 37.28 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/Xception71_pretrained.tar) |
+| InceptionV3 | 0.7914 | 0.9459 | 6.64054 | 13.53630 | 11.46 | 23.83 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/InceptionV3_pretrained.tar) |
| InceptionV4 | 0.8077 | 0.9526 | 12.99342 | 25.23416 | 24.57 | 42.68 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/InceptionV4_pretrained.tar) |
diff --git a/docs/en/models/Inception_en.md b/docs/en/models/Inception_en.md
index 99b42dc452101b6eb5ef99ed4b1601163c8f3e22..324c281d0e2f7e24010bfa386e7766531cadc2eb 100644
--- a/docs/en/models/Inception_en.md
+++ b/docs/en/models/Inception_en.md
@@ -4,6 +4,9 @@
GoogLeNet is a new neural network structure designed by Google in 2014, which, together with VGG network, became the twin champions of the ImageNet challenge that year. GoogLeNet introduces the Inception structure for the first time, and stacks the Inception structure in the network so that the number of network layers reaches 22, which is also the mark of the convolutional network exceeding 20 layers for the first time. Since 1x1 convolution is used in the Inception structure to reduce the dimension of channel number, and Global pooling is used to replace the traditional method of processing features in multiple fc layers, the final GoogLeNet network has much less FLOPS and parameters than VGG network, which has become a beautiful scenery of neural network design at that time.
+
+InceptionV3 is an improvement of InceptionV2 by Google. First of all, the author optimized the Inception module in InceptionV3. At the same time, more types of Inception modules were designed and used. Further, the larger square two-dimensional convolution kernel in some Inception modules in InceptionV3 was disassembled into two smaller asymmetric convolution kernels, which can greatly save the amount of parameters.
+
Xception is another improvement to InceptionV3 that Google proposed after Inception. In Xception, the author used the depthwise separable convolution to replace the traditional convolution operation, which greatly saved the network FLOPS and the number of parameters, but improved the accuracy. In DeeplabV3+, the author further improved the Xception and increased the number of Xception layers, and designed the network of Xception65 and Xception71.
InceptionV4 is a new neural network designed by Google in 2016, when residual structure were all the rage, but the authors believe that high performance can be achieved using only Inception structure. InceptionV4 uses more Inception structure to achieve even greater precision on Imagenet-1k.
@@ -31,6 +34,7 @@ The figure above reflects the relationship between the accuracy of Xception seri
| Xception65 | 0.810 | 0.955 | | | 25.950 | 35.480 |
| Xception65
_deeplab | 0.803 | 0.945 | | | 27.370 | 39.520 |
| Xception71 | 0.811 | 0.955 | | | 31.770 | 37.280 |
+| InceptionV3 | 0.791 | 0.946 | 0.788 | 0.944 | 11.460 | 23.830 |
| InceptionV4 | 0.808 | 0.953 | 0.800 | 0.950 | 24.570 | 42.680 |
@@ -59,4 +63,5 @@ The figure above reflects the relationship between the accuracy of Xception seri
| Xception65 | 299 | 320 | 4.30126 | 11.58371 | 23.22213 | 7.26158 | 25.88778 | 53.45426 |
| Xception65_
deeplab | 299 | 320 | 4.06803 | 9.72694 | 19.477 | 7.60208 | 26.03699 | 54.74724 |
| Xception71 | 299 | 320 | 4.80889 | 13.5624 | 27.18822 | 8.72457 | 31.55549 | 69.31018 |
+| InceptionV3 | 299 | 320 | 3.67502 | 6.36071 | 9.82645 | 6.64054 | 13.53630 | 22.17355 |
| InceptionV4 | 299 | 320 | 9.50821 | 13.72104 | 20.27447 | 12.99342 | 25.23416 | 43.56121 |
diff --git a/docs/en/models/models_intro_en.md b/docs/en/models/models_intro_en.md
index 32fba01fefbb11f5185d341b2a69e62c689f40da..9782a8a63603e5534ec37902ea8dac72c0a1187c 100644
--- a/docs/en/models/models_intro_en.md
+++ b/docs/en/models/models_intro_en.md
@@ -137,7 +137,9 @@ python tools/infer/predict.py \
- Inception series
- GoogLeNet series[[10](#ref10)]([paper link](https://arxiv.org/pdf/1409.4842.pdf))
- [GoogLeNet](https://paddle-imagenet-models-name.bj.bcebos.com/GoogLeNet_pretrained.tar)
- - Inception series[[11](#ref11)]([paper link](https://arxiv.org/abs/1602.07261))
+ - InceptionV3 series[[26](#ref26)]([paper link](https://arxiv.org/abs/1512.00567))
+ - [InceptionV3](https://paddle-imagenet-models-name.bj.bcebos.com/InceptionV3_pretrained.tar)
+ - InceptionV4 series[[11](#ref11)]([paper link](https://arxiv.org/abs/1602.07261))
- [InceptionV4](https://paddle-imagenet-models-name.bj.bcebos.com/InceptionV4_pretrained.tar)
- Xception series[[12](#ref12)]([paper link](http://openaccess.thecvf.com/content_cvpr_2017/html/Chollet_Xception_Deep_Learning_CVPR_2017_paper.html))
- [Xception41](https://paddle-imagenet-models-name.bj.bcebos.com/Xception41_pretrained.tar)
@@ -278,3 +280,5 @@ python tools/infer/predict.py \
[24] Zhang H, Wu C, Zhang Z, et al. Resnest: Split-attention networks[J]. arXiv preprint arXiv:2004.08955, 2020.
[25] Radosavovic I, Kosaraju R P, Girshick R, et al. Designing network design spaces[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 10428-10436.
+
+[26] C.Szegedy, V.Vanhoucke, S.Ioffe, J.Shlens, and Z.Wojna. Rethinking the inception architecture for computer vision. arXiv preprint arXiv:1512.00567, 2015.
diff --git a/docs/en/update_history_en.md b/docs/en/update_history_en.md
index b5cc56820f08e1e3c268f687abc7b483811de4ea..4caa94937335cbcbd30e04437b7c320a16aa63b2 100644
--- a/docs/en/update_history_en.md
+++ b/docs/en/update_history_en.md
@@ -1,5 +1,8 @@
# Release Notes
+- 2020.11.09
+ * Add `InceptionV3` architecture and pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 79.1%.
+
- 2020.10.12
* Add Paddle-Lite demo.
diff --git a/docs/zh_CN/models/Inception.md b/docs/zh_CN/models/Inception.md
index b85c2bf1b5068936daa3091215540b866d4d31b3..e811852679d88bda3bfefa025936582694671569 100644
--- a/docs/zh_CN/models/Inception.md
+++ b/docs/zh_CN/models/Inception.md
@@ -4,6 +4,8 @@
GoogLeNet是2014年由Google设计的一种新的神经网络结构，其与VGG网络并列成为当年ImageNet挑战赛的双雄。GoogLeNet首次引入Inception结构，在网络中堆叠该结构使得网络层数达到了22层，这也是卷积网络首次超过20层的标志。由于在Inception结构中使用了1x1的卷积用于通道数降维，并且使用了Global-pooling代替传统的多fc层加工特征的方式，最终的GoogLeNet网络的FLOPS和参数量远小于VGG网络，成为当时神经网络设计的一道亮丽风景线。
+InceptionV3是Google 对InceptionV2的一种改进。首先，InceptionV3 对 Inception模块进行了优化，同时设计和使用了更多种类的Inception模块，与此同时，InceptionV3中的部分Inception模块将较大的方形二维卷积拆成两个较小的非对称卷积，这样可以大幅度节省参数量。
+
Xception 是 Google 继 Inception 后提出的对 InceptionV3 的另一种改进。在Xception中，作者使用了深度可分离卷积代替了传统的卷积操作，该操作大大节省了网络的FLOPS和参数量，但是精度反而有所提升。在DeeplabV3+中，作者将Xception做了进一步的改进，同时增加了Xception的层数，设计出了Xception65和Xception71的网络。
InceptionV4是2016年由Google设计的新的神经网络，当时残差结构风靡一时，但是作者认为仅使用Inception 结构也可以达到很高的性能。InceptionV4使用了更多的Inception module，在ImageNet上的精度再创新高。
@@ -33,6 +35,7 @@ InceptionV4是2016年由Google设计的新的神经网络，当时残差结构
| Xception65 | 0.810 | 0.955 | | | 25.950 | 35.480 |
| Xception65
_deeplab | 0.803 | 0.945 | | | 27.370 | 39.520 |
| Xception71 | 0.811 | 0.955 | | | 31.770 | 37.280 |
+| InceptionV3 | 0.791 | 0.946 | 0.788 | 0.944 | 11.460 | 23.830 |
| InceptionV4 | 0.808 | 0.953 | 0.800 | 0.950 | 24.570 | 42.680 |
@@ -61,4 +64,5 @@ InceptionV4是2016年由Google设计的新的神经网络，当时残差结构
| Xception65 | 299 | 320 | 4.30126 | 11.58371 | 23.22213 | 7.26158 | 25.88778 | 53.45426 |
| Xception65_
deeplab | 299 | 320 | 4.06803 | 9.72694 | 19.477 | 7.60208 | 26.03699 | 54.74724 |
| Xception71 | 299 | 320 | 4.80889 | 13.5624 | 27.18822 | 8.72457 | 31.55549 | 69.31018 |
+| InceptionV3 | 299 | 320 | 3.67502 | 6.36071 | 9.82645 | 6.64054 | 13.53630 | 22.17355 |
| InceptionV4 | 299 | 320 | 9.50821 | 13.72104 | 20.27447 | 12.99342 | 25.23416 | 43.56121 |
diff --git a/docs/zh_CN/models/models_intro.md b/docs/zh_CN/models/models_intro.md
index eb8c723d84a626eb06397e2d7cefd0ab010637bc..33c6b248b75b68dc307e702744b999cfdc0acdbc 100644
--- a/docs/zh_CN/models/models_intro.md
+++ b/docs/zh_CN/models/models_intro.md
@@ -137,7 +137,9 @@ python tools/infer/predict.py \
- Inception系列
- GoogLeNet系列[[10](#ref10)]([论文地址](https://arxiv.org/pdf/1409.4842.pdf))
- [GoogLeNet](https://paddle-imagenet-models-name.bj.bcebos.com/GoogLeNet_pretrained.tar)
- - Inception系列[[11](#ref11)]([论文地址](https://arxiv.org/abs/1602.07261))
+ - InceptionV3系列[[26](#ref26)]([论文地址](https://arxiv.org/abs/1512.00567))
+ - [InceptionV3](https://paddle-imagenet-models-name.bj.bcebos.com/InceptionV3_pretrained.tar)
+ - InceptionV4系列[[11](#ref11)]([论文地址](https://arxiv.org/abs/1602.07261))
- [InceptionV4](https://paddle-imagenet-models-name.bj.bcebos.com/InceptionV4_pretrained.tar)
- Xception系列[[12](#ref12)]([论文地址](http://openaccess.thecvf.com/content_cvpr_2017/html/Chollet_Xception_Deep_Learning_CVPR_2017_paper.html))
- [Xception41](https://paddle-imagenet-models-name.bj.bcebos.com/Xception41_pretrained.tar)
@@ -275,3 +277,5 @@ python tools/infer/predict.py \
[24] Zhang H, Wu C, Zhang Z, et al. Resnest: Split-attention networks[J]. arXiv preprint arXiv:2004.08955, 2020.
[25] Radosavovic I, Kosaraju R P, Girshick R, et al. Designing network design spaces[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 10428-10436.
+
+[26] C.Szegedy, V.Vanhoucke, S.Ioffe, J.Shlens, and Z.Wojna. Rethinking the inception architecture for computer vision. arXiv preprint arXiv:1512.00567, 2015.
diff --git a/docs/zh_CN/update_history.md b/docs/zh_CN/update_history.md
index 232c18b75151389c41ca4e80c13d3b26b5c00767..346838b89a47ec0b5931bafc38f2816445fb98a0 100644
--- a/docs/zh_CN/update_history.md
+++ b/docs/zh_CN/update_history.md
@@ -1,5 +1,8 @@
# 更新日志
+- 2020.11.09
+ * 添加InceptionV3结构和模型，在ImageNet上Top-1 Acc可达0.791。
+
- 2020.10.12
* 添加Paddle-Lite demo。