diff --git a/modules/image/classification/DriverStatusRecognition/README_en.md b/modules/image/classification/DriverStatusRecognition/README_en.md index cbf998ead76d5b6c7ba29946f7613e5b664bfbcb..1a05edb3421dbe6be9d51180d4ec4d71a62bd26b 100644 --- a/modules/image/classification/DriverStatusRecognition/README_en.md +++ b/modules/image/classification/DriverStatusRecognition/README_en.md @@ -4,7 +4,7 @@ | :--- | :---: | |Category|image classification| |Network|MobileNetV3_small_ssld| -|Dataset|分心司机检测Dataset| +|Dataset|Distractible Driver Dataset| |Fine-tuning supported or not|No| |Module Size|6MB| |Latest update date|-| @@ -17,7 +17,7 @@ - ### Module Introduction - - 驾驶员状态识别（DriverStatusRecognition），该模型可挖掘出人在疲劳状态下的表情特征，然后将这些定性的表情特征进行量化，提取出面部特征点及特征指标作为判断依据，再结合实验数据总结出基于这些Parameters的识别方法，最后输入获取到的状态数据进行识别和判断.该PaddleHub Module支持API预测及命令行预测. + - This module can be used for recognizing distractible drivers by analysing the expression on the face. ## II.Installation @@ -37,8 +37,8 @@ ``` - In case of any problems during installation, please refer to: [Windows_Quickstart]() | [Linux_Quickstart]() | [Mac_Quickstart]() -- ### 3、在线体验 - [AI Studio 快速体验](https://aistudio.baidu.com/aistudio/projectdetail/1649513) +- ### 3、Online experience + [AI Studio](https://aistudio.baidu.com/aistudio/projectdetail/1649513) ## III.Module API Prediction @@ -69,7 +69,7 @@ ``` - classification API. - **Parameters** - - images：list类型，待检测的图像. + - images (list\[numpy.ndarray\]): image data, ndarray.shape is in the format [H, W, C], BGR; - **Return** - result(list[dict]): classication results, each element in the list is dict, key is the label name, and value is the corresponding probability diff --git a/modules/image/classification/SnakeIdentification/README_en.md b/modules/image/classification/SnakeIdentification/README_en.md index 829f83d3be162a7547e43049bf47218e6ceed8be..d80db28647ccdc4a3f08f9abd6646a70e4125758 100644 --- a/modules/image/classification/SnakeIdentification/README_en.md +++ b/modules/image/classification/SnakeIdentification/README_en.md @@ -4,7 +4,7 @@ | :--- | :---: | |Category|image classification| |Network|ResNet50_vd_ssld| -|Dataset|蛇种Dataset| +|Dataset|Snake Dataset| |Fine-tuning supported or not|No| |Module Size|84MB| |Latest update date|-| @@ -17,7 +17,7 @@ - ### Module Introduction - - 蛇种识别（SnakeIdentification），该模型可准确识别蛇的种类，并精准判断蛇的毒性.该PaddleHub Module支持API预测及命令行预测. + - This module can be used to identify the kind of snake, and judge the toxicity. ## II.Installation @@ -37,8 +37,8 @@ ``` - In case of any problems during installation, please refer to: [Windows_Quickstart]() | [Linux_Quickstart]() | [Mac_Quickstart]() -- ### 3、在线体验 - [AI Studio 快速体验](https://aistudio.baidu.com/aistudio/projectdetail/1646951) +- ### 3、Online experience + [AI Studio](https://aistudio.baidu.com/aistudio/projectdetail/1646951) ## III.Module API Prediction @@ -69,7 +69,7 @@ ``` - classification API. - **Parameters** - - images：list类型，待检测的图像. + - images (list\[numpy.ndarray\]): image data, ndarray.shape is in the format [H, W, C], BGR; - **Return** - result(list[dict]): classication results, each element in the list is dict, key is the label name, and value is the corresponding probability diff --git a/modules/image/classification/alexnet_imagenet/README_en.md b/modules/image/classification/alexnet_imagenet/README_en.md index e4f57cfeceed8c5bcea9d79cdb97e031435cb284..c964dc961f2e9dd5de01528bf4b9c63cf9583b12 100644 --- a/modules/image/classification/alexnet_imagenet/README_en.md +++ b/modules/image/classification/alexnet_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - AlexNet是图像分类中的经典模型.模型由Alex Krizhevsky于2012年提出，并在2012年ILSVRC比赛中夺得冠军.该PaddleHub Module结构为AlexNet，基于ImageNet-2012数据集训练，接受输入图片大小为224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - AlexNet was a classification model proposed by Alex Krizhevsky in 2012, and gained the champion of ILSVRC 2012. This module is based on AlexNet, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/darknet53_imagenet/README_en.md b/modules/image/classification/darknet53_imagenet/README_en.md index 3dea4b920e598deb82896800e2165bbcbbaf43a0..d348207e198f22d0cbdc3162ba88fae683f9a5f7 100644 --- a/modules/image/classification/darknet53_imagenet/README_en.md +++ b/modules/image/classification/darknet53_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - DarkNet 是由 Joseph Redmon 提出的图像分类模型，并应用于Yolov3 中作为 Backbone 来完成特征提取.该网络采用连续的 3*3 和 1*1 卷积进行连接，并像ResNet 一样有ShortCut连接.该 PaddleHub Module 基于 ImageNet-2012 数据集训练，接受输入图片大小为 224 x 224 x 3，支持直接通过命令行或者 Python 接口进行预测. + - DarkNet is a classification model proposed by Joseph Redmon, which uses Yolov3 as backbone to extract features. This module is based on darknet53, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/densenet121_imagenet/README_en.md b/modules/image/classification/densenet121_imagenet/README_en.md index 8bf61900095f7ebf0b85187f4871ae977ac16c1b..40453f1d4e32630f91ab4c67d9a7e362861d42dc 100644 --- a/modules/image/classification/densenet121_imagenet/README_en.md +++ b/modules/image/classification/densenet121_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - DenseNet 是 CVPR 2017 最佳论文的模型，DenseNet 以前馈方式将每一层与其他层连接，从而 L 层网络就有 L(L+1)/2 个直接连接.对于每一层，其输入是之前的所有层的特征图，而自己的特征图作为之后所有层的输入.DenseNet 缓解了梯度消失问题，加强特征传播，促进了特征重用，并大幅减少了Parameters量.该PaddleHub Module结构为 DenseNet121，基于ImageNet-2012数据集训练，接受输入图片大小为 224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - DenseNet is the model in CVPR2017 best paper. Every layer outputs its result as input for the layer after it, and forms the dense connection topology. The dense connection ease the probblem of vanishing gradient and improve the information flow. This module is based on DenseNet121, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/densenet161_imagenet/README_en.md b/modules/image/classification/densenet161_imagenet/README_en.md index bac4c436ba8cf5568294bbf21a4706977e15f217..36907895c8e38f60770ce1df09e10322886e6df7 100644 --- a/modules/image/classification/densenet161_imagenet/README_en.md +++ b/modules/image/classification/densenet161_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - DenseNet 是 CVPR 2017 最佳论文的模型，DenseNet 以前馈方式将每一层与其他层连接，从而 L 层网络就有 L(L+1)/2 个直接连接.对于每一层，其输入是之前的所有层的特征图，而自己的特征图作为之后所有层的输入.DenseNet 缓解了梯度消失问题，加强特征传播，促进了特征重用，并大幅减少了Parameters量.该PaddleHub Module结构为 DenseNet161，基于ImageNet-2012数据集训练，接受输入图片大小为 224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - DenseNet is the model in CVPR2017 best paper. Every layer outputs its result as input for the layer after it, and forms the dense connection topology. The dense connection ease the probblem of vanishing gradient and improve the information flow. This module is based on DenseNet161, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/densenet169_imagenet/README_en.md b/modules/image/classification/densenet169_imagenet/README_en.md index 2acb3261992df4617a63c6ee57ef984416c274b1..6663f0e19d247baf4bc4116b7bd19196875e844e 100644 --- a/modules/image/classification/densenet169_imagenet/README_en.md +++ b/modules/image/classification/densenet169_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - DenseNet 是 CVPR 2017 最佳论文的模型，DenseNet 以前馈方式将每一层与其他层连接，从而 L 层网络就有 L(L+1)/2 个直接连接.对于每一层，其输入是之前的所有层的特征图，而自己的特征图作为之后所有层的输入.DenseNet 缓解了梯度消失问题，加强特征传播，促进了特征重用，并大幅减少了Parameters量.该PaddleHub Module结构为 DenseNet169，基于ImageNet-2012数据集训练，接受输入图片大小为 224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - DenseNet is the model in CVPR2017 best paper. Every layer outputs its result as input for the layer after it, and forms the dense connection topology. The dense connection ease the probblem of vanishing gradient and improve the information flow. This module is based on DenseNet169, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/densenet201_imagenet/README_en.md b/modules/image/classification/densenet201_imagenet/README_en.md index d460881a51cf105edaab7dd975d8aa654626a9f6..623f8e0157175687a686d61b4483c60f6a269282 100644 --- a/modules/image/classification/densenet201_imagenet/README_en.md +++ b/modules/image/classification/densenet201_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - DenseNet 是 CVPR 2017 最佳论文的模型，DenseNet 以前馈方式将每一层与其他层连接，从而 L 层网络就有 L(L+1)/2 个直接连接.对于每一层，其输入是之前的所有层的特征图，而自己的特征图作为之后所有层的输入.DenseNet 缓解了梯度消失问题，加强特征传播，促进了特征重用，并大幅减少了Parameters量.该PaddleHub Module结构为 DenseNet201，基于ImageNet-2012数据集训练，接受输入图片大小为 224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - DenseNet is the model in CVPR2017 best paper. Every layer outputs its result as input for the layer after it, and forms the dense connection topology. The dense connection ease the probblem of vanishing gradient and improve the information flow. This module is based on DenseNet201, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/densenet264_imagenet/README_en.md b/modules/image/classification/densenet264_imagenet/README_en.md index 7814db69259f40f568afc237b87f3994c0c35ddb..cd34997908da2a0c427802d712b7a9210708f91b 100644 --- a/modules/image/classification/densenet264_imagenet/README_en.md +++ b/modules/image/classification/densenet264_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - DenseNet 是 CVPR 2017 最佳论文的模型，DenseNet 以前馈方式将每一层与其他层连接，从而 L 层网络就有 L(L+1)/2 个直接连接.对于每一层，其输入是之前的所有层的特征图，而自己的特征图作为之后所有层的输入.DenseNet 缓解了梯度消失问题，加强特征传播，促进了特征重用，并大幅减少了Parameters量.该PaddleHub Module结构为 DenseNet264，基于ImageNet-2012数据集训练，接受输入图片大小为 224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - DenseNet is the model in CVPR2017 best paper. Every layer outputs its result as input for the layer after it, and forms the dense connection topology. The dense connection ease the probblem of vanishing gradient and improve the information flow. This module is based on DenseNet264, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/dpn107_imagenet/README_en.md b/modules/image/classification/dpn107_imagenet/README_en.md index 498dc84db8ab0c6489007b9971499b314d19284f..cc4362c106523dc0bb64cb7f627dab2c232a5cbd 100644 --- a/modules/image/classification/dpn107_imagenet/README_en.md +++ b/modules/image/classification/dpn107_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - DPN(Dual Path Networks) 是 ImageNet 2017 目标定位冠军的图像分类模型，融合了 ResNet 和 DenseNet 的核心思想.该PaddleHub Module结构为 DPN107，基于ImageNet-2012数据集训练，接受输入图片大小为 224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - DPN(Dual Path Networks) is the champion of ILSVRC2017 in Object Localization Task. This module is based on DPN107, trained on ImageNet-2012, can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/dpn131_imagenet/README_en.md b/modules/image/classification/dpn131_imagenet/README_en.md index 2e6c7e777d6f3ab09fbb5f9dffef4aa0514f0e5f..6401b3fa5dbe82cccbd0d52ab70193669aae2cd8 100644 --- a/modules/image/classification/dpn131_imagenet/README_en.md +++ b/modules/image/classification/dpn131_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - DPN(Dual Path Networks) 是 ImageNet 2017 目标定位冠军的图像分类模型，融合了 ResNet 和 DenseNet 的核心思想.该PaddleHub Module结构为 DPN98，基于ImageNet-2012数据集训练，接受输入图片大小为 224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - DPN(Dual Path Networks) is the champion of ILSVRC2017 in Object Localization Task. This module is based on DPN131, trained on ImageNet-2012, can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/dpn68_imagenet/README_en.md b/modules/image/classification/dpn68_imagenet/README_en.md index a09d1845b0c7bb341d6bad17d6b052f53ff00d31..b70055f52b58dc4a6887642364d4f10a24c14cac 100644 --- a/modules/image/classification/dpn68_imagenet/README_en.md +++ b/modules/image/classification/dpn68_imagenet/README_en.md @@ -17,8 +17,7 @@ - ### Module Introduction - - DPN(Dual Path Networks) 是 ImageNet 2017 目标定位冠军的图像分类模型，融合了 ResNet 和 DenseNet 的核心思想.该PaddleHub Module结构为 DPN68，基于ImageNet-2012数据集训练，接受输入图片大小为 224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. - + - DPN(Dual Path Networks) is the champion of ILSVRC2017 in Object Localization Task. This module is based on DPN68, trained on ImageNet-2012, can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/dpn92_imagenet/README_en.md b/modules/image/classification/dpn92_imagenet/README_en.md index 138d6045bfe6b7fb8c0ae282faaa5e1f29f3497f..ba277a3b73a8b94c31329480a541b1c9acca1097 100644 --- a/modules/image/classification/dpn92_imagenet/README_en.md +++ b/modules/image/classification/dpn92_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - DPN(Dual Path Networks) 是 ImageNet 2017 目标定位冠军的图像分类模型，融合了 ResNet 和 DenseNet 的核心思想.该PaddleHub Module结构为 DPN92，基于ImageNet-2012数据集训练，接受输入图片大小为 224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - DPN(Dual Path Networks) is the champion of ILSVRC2017 in Object Localization Task. This module is based on DPN92, trained on ImageNet-2012, can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/dpn98_imagenet/README_en.md b/modules/image/classification/dpn98_imagenet/README_en.md index fb777e83a46b0a2ddbf06ed8e061b6e801b877bb..6e12eff9543c0960242602ef07b34a6c4f9f4a96 100644 --- a/modules/image/classification/dpn98_imagenet/README_en.md +++ b/modules/image/classification/dpn98_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - DPN(Dual Path Networks) 是 ImageNet 2017 目标定位冠军的图像分类模型，融合了 ResNet 和 DenseNet 的核心思想.该PaddleHub Module结构为 DPN98，基于ImageNet-2012数据集训练，接受输入图片大小为 224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - DPN(Dual Path Networks) is the champion of ILSVRC2017 in Object Localization Task. This module is based on DPN98, trained on ImageNet-2012, can predict an image of size 224*224*3. diff --git a/modules/image/classification/fix_resnext101_32x48d_wsl_imagenet/README_en.md b/modules/image/classification/fix_resnext101_32x48d_wsl_imagenet/README_en.md index e2ce336bdfe25682c8967912617fb32fe634bf30..4e632244709ba21e55272fa48dfbbe545e9ded0b 100644 --- a/modules/image/classification/fix_resnext101_32x48d_wsl_imagenet/README_en.md +++ b/modules/image/classification/fix_resnext101_32x48d_wsl_imagenet/README_en.md @@ -17,7 +17,8 @@ - ### Module Introduction - - ResNeXt 是由 UC San Diego 和 Facebook AI 研究所于2017年提出的图像分类模型，模型沿袭了 VGG/ResNets 的堆叠思想，并采用 split-transform-merge 策略来增加网络的分支数.该 PaddleHub Module 在包含数十亿张社交媒体图片的数据集上进行弱监督训练，并使用ImageNet-2012数据集finetune，接受输入图片大小为 224 x 224 x 3，支持直接通过命令行或者 Python 接口进行预测. + - ResNeXt is proposed by UC San Diego and Facebook AI Research in 2017. This module is based on ResNeXt model. It is weak-supervised trained on billions of socail images, finetuned on ImageNet-2012 dataset, and can predict an image of size 224*224*3. + ## II.Installation @@ -45,7 +46,7 @@ ``` - If you want to call the Hub module through the command line, please refer to: [PaddleHub Command Line Instruction](../../../../docs/docs_ch/tutorial/cmd_usage.rst) -- ### 2、预测Prediction Code Example +- ### 2、Prediction Code Example - ```python import paddlehub as hub diff --git a/modules/image/classification/food_classification/README_en.md b/modules/image/classification/food_classification/README_en.md index 867e34b48866be9220e0f4e4759e4a824cef9b51..c5c53f0337e0708512df4fe0c9e9c56eeda6087d 100644 --- a/modules/image/classification/food_classification/README_en.md +++ b/modules/image/classification/food_classification/README_en.md @@ -4,7 +4,7 @@ | :--- | :---: | |Category|image classification| |Network|ResNet50_vd_ssld| -|Dataset|美食Dataset| +|Dataset|Food Dataset| |Fine-tuning supported or not|No| |Module Size|91MB| |Latest update date|-| @@ -17,7 +17,7 @@ - ### Module Introduction - - 美食分类（food_classification），该模型可识别苹果派，小排骨，烤面包，牛肉馅饼，牛肉鞑靼.该PaddleHub Module支持API预测及命令行预测. + - This module can be used for food classification. ## II.Installation @@ -46,7 +46,7 @@ ``` - If you want to call the Hub module through the command line, please refer to: [PaddleHub Command Line Instruction](../../../../docs/docs_ch/tutorial/cmd_usage.rst) -- ### 2、预测Prediction Code Example +- ### 2、Prediction Code Example - ```python import paddlehub as hub @@ -66,13 +66,13 @@ ``` - classification API. - **Parameters** - - images：list类型，待检测的图像. + - images (list\[numpy.ndarray\]): image data, ndarray.shape is in the format [H, W, C], BGR; - **Return** - result(list[dict]): classication results, each element in the list is dict, key is the label name, and value is the corresponding probability - - category_id (int): 类别的id； - - category（str）: 类别; - - score（float）: 准确率 + - category_id (int): category id； + - category（str）: category name; + - score（float）: probability diff --git a/modules/image/classification/googlenet_imagenet/README_en.md b/modules/image/classification/googlenet_imagenet/README_en.md index a201a30f2badffa20cbefe551420c8d4ec02529e..75bae1b3e84059efbfb867cb92f998a65ff60cc3 100644 --- a/modules/image/classification/googlenet_imagenet/README_en.md +++ b/modules/image/classification/googlenet_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - GoogleNet是图像分类中的经典模型.由Christian Szegedy等人在2014年提出，并获得了2014年ILSVRC竞赛冠军.该PaddleHub Module结构为GoogleNet，基于ImageNet-2012数据集训练，接受输入图片大小为224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - GoogleNet was proposed by Christian Szegedy in 2014 and gained the champion of ILSVRC 2014. This module is based on GoogleNet, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/inception_v4_imagenet/README_en.md b/modules/image/classification/inception_v4_imagenet/README_en.md index 013b4def5ab0a6dfabbd48a0cca7aca3e3191dc8..4992c58301af3481b3e27bb1fc5ebb373e51d386 100644 --- a/modules/image/classification/inception_v4_imagenet/README_en.md +++ b/modules/image/classification/inception_v4_imagenet/README_en.md @@ -16,8 +16,7 @@ - ### Module Introduction - - - Inception 结构最初由 GoogLeNet 引入，因此 GoogLeNet 也被称为 Inception-v1，通过在 Inception-v1 的基础上引入Batch Normalization、分解、残差连接等技术，设计出了Inception-v4. + - Inception structure is first introduced in GoogLeNet, so GoogLeNet is named Inception-v1. Inception-v4 is an improvement on it, which takas advantage of sereral useful strategies such as batch normalization, residual learning. This module is based on Inception-v4, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/marine_biometrics/README_en.md b/modules/image/classification/marine_biometrics/README_en.md index 804e48b5d421e8b1dd892abe00c117ba885efabe..f2e2874e98f35bd6b3d8e24847d7c18ce99cabba 100644 --- a/modules/image/classification/marine_biometrics/README_en.md +++ b/modules/image/classification/marine_biometrics/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - 海洋生物识别（marine_biometrics），该模型可准确识别鱼的种类.该PaddleHub Module支持API预测及命令行预测. + - This module can be used to classify marine biometrics. ## II.Installation @@ -44,7 +44,7 @@ ``` - If you want to call the Hub module through the command line, please refer to: [PaddleHub Command Line Instruction](../../../../docs/docs_ch/tutorial/cmd_usage.rst) -- ### 2、预测Prediction Code Example +- ### 2、Prediction Code Example - ```python import paddlehub as hub @@ -64,7 +64,7 @@ ``` - classification API. - **Parameters** - - images：list类型，待检测的图像. + - images (list\[numpy.ndarray\]): image data, ndarray.shape is in the format [H, W, C], BGR; - **Return** - result(list[dict]): classication results, each element in the list is dict, key is the label name, and value is the corresponding probability diff --git a/modules/image/classification/mobilenet_v2_animals/README_en.md b/modules/image/classification/mobilenet_v2_animals/README_en.md index 32eb5f64239d0031060c9cc4b906989d4ee90bae..ad4071de18b1642e1c04aac14b58c2f9601eb7aa 100644 --- a/modules/image/classification/mobilenet_v2_animals/README_en.md +++ b/modules/image/classification/mobilenet_v2_animals/README_en.md @@ -4,7 +4,7 @@ | :--- | :---: | |Category|image classification| |Network|MobileNet_v2| -|Dataset|百度自建动物Dataset| +|Dataset|Baidu Animal Dataset| |Fine-tuning supported or not|No| |Module Size|50MB| |Latest update date|-| @@ -17,7 +17,9 @@ - ### Module Introduction - - MobileNet V2 是一个轻量化的卷积神经网络，它在 MobileNet 的基础上，做了 Inverted Residuals 和 Linear bottlenecks 这两大改进.该 PaddleHub Module 是在百度自建动物数据集上训练得到的，可用于图像分类和特征提取，当前已支持7978种动物的分类识别.模型的详情可参考[论文](https://arxiv.org/pdf/1801.04381.pdf). + - MobileNet is a light-weight convolution network. This module is trained on Baidu animal dataset, and can classify 7978 kinds of animals. + - For more information, please refer to：[MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/pdf/1801.04381.pdf) + diff --git a/modules/image/classification/mobilenet_v2_dishes/README_en.md b/modules/image/classification/mobilenet_v2_dishes/README_en.md index 9cc797a0d98e1257e66dec47379801e8219111e8..e5c802e2b6f1467fe4040b4a96ace3a2c1723474 100644 --- a/modules/image/classification/mobilenet_v2_dishes/README_en.md +++ b/modules/image/classification/mobilenet_v2_dishes/README_en.md @@ -4,7 +4,7 @@ | :--- | :---: | |Category|image classification| |Network|MobileNet_v2| -|Dataset|百度自建菜品Dataset| +|Dataset|Baidu food Dataset| |Fine-tuning supported or not|No| |Module Size|52MB| |Latest update date|-| @@ -17,13 +17,13 @@ - ### Module Introduction - - MobileNet V2 是一个轻量化的卷积神经网络，它在 MobileNet 的基础上，做了 Inverted Residuals 和 Linear bottlenecks 这两大改进.该 PaddleHub Module 是在百度自建菜品数据集上训练得到的，可用于图像分类和特征提取，当前已支持8416种菜品的分类识别. + - MobileNet is a light-weight convolution network. This module is trained on Baidu food dataset, and can classify 8416 kinds of food.


- - 更多详情参考：[MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/pdf/1801.04381.pdf) + - For more information, please refer to：[MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/pdf/1801.04381.pdf) ## II.Installation diff --git a/modules/image/classification/mobilenet_v2_imagenet/README_en.md b/modules/image/classification/mobilenet_v2_imagenet/README_en.md index 5bbe506044a4168f0db14db550e39f5b2388c53e..50acae7a5a8ea39e3a170e1d75a00d2aa0ed23ad 100644 --- a/modules/image/classification/mobilenet_v2_imagenet/README_en.md +++ b/modules/image/classification/mobilenet_v2_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - MobileNet V2是Mark Sandler, Andrew Howard等人在2018年提出的一个图像分类模型，该系列模型（MobileNet）是为移动和嵌入式设备提出的高效模型，在模型Parameters较少的情况下仍然保持了较高的分类准确率.该PaddleHub Module基于ImageNet-2012数据集训练，接受输入图片大小为224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - MobileNet V2 is an image classification model proposed by Mark Sandler, Andrew Howard et al. in 2018. This model is a light-weight model for mobile and embedded device, and can reach high accurary with a few parameters. This module is based on MobileNet V2, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/mobilenet_v2_imagenet_ssld/README_en.md b/modules/image/classification/mobilenet_v2_imagenet_ssld/README_en.md index d5e0f9d283911fe2c2bbe2fe7f64d3aa824d777f..3eef11aa5d3398ce5d61e3309482691de4fbb9ea 100644 --- a/modules/image/classification/mobilenet_v2_imagenet_ssld/README_en.md +++ b/modules/image/classification/mobilenet_v2_imagenet_ssld/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - MobileNet V2是Mark Sandler, Andrew Howard等人在2018年提出的一个图像分类模型，该系列模型（MobileNet）是为移动和嵌入式设备提出的高效模型，在模型Parameters较少的情况下仍然保持了较高的分类准确率.该PaddleHub Module基于ImageNet-2012数据集并采用PaddleClas提供的SSLD蒸馏方法训练得到，接受输入图片大小为224 x 224 x 3，支持finetune，也可以直接通过命令行或者Python接口进行预测. + - MobileNet V2 is an image classification model proposed by Mark Sandler, Andrew Howard et al. in 2018. This model is a light-weight model for mobile and embedded device, and can reach high accurary with a few parameters. This module is based on MobileNet V2, trained on ImageNet-2012 with SSLD distillation strategy, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/mobilenet_v3_large_imagenet_ssld/README_en.md b/modules/image/classification/mobilenet_v3_large_imagenet_ssld/README_en.md index 2b43ecfcab7c18d9bfa252d96356b3a8b8774872..c426fb799b506a96162f218136028bc9533685cd 100644 --- a/modules/image/classification/mobilenet_v3_large_imagenet_ssld/README_en.md +++ b/modules/image/classification/mobilenet_v3_large_imagenet_ssld/README_en.md @@ -17,8 +17,7 @@ - ### Module Introduction - - MobileNetV3是Google在2019年发布的新模型，作者通过结合NAS与NetAdapt进行搜索得到该网络结构，提供了Large和Small两个版本，分别适用于对资源不同要求的情况.对比于MobileNetV2，新的模型在速度和精度方面均有提升.该PaddleHubModule的模型结构为MobileNetV3 Large，基于ImageNet-2012数据集并采用PaddleClas提供的SSLD蒸馏方法训练得到，接受输入图片大小为224 x 224 x 3，支持finetune，也可以直接通过命令行或者Python接口进行预测. - + - MobileNetV3 is an image classification model proposed by Google in 2019. The authors proposed to search the network architecture by combination of NAS and NetAdapt, and provide two versions of this model, i.e. Large and Small version. This module is based on MobileNetV3 Large, trained on ImageNet-2012 with SSLD distillation strategy, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/mobilenet_v3_small_imagenet_ssld/README_en.md b/modules/image/classification/mobilenet_v3_small_imagenet_ssld/README_en.md index 0ba3efb6b11485e04890191f3ac023fe0f3c1769..44fa376091c692112a384bd03860df164e19eaa4 100644 --- a/modules/image/classification/mobilenet_v3_small_imagenet_ssld/README_en.md +++ b/modules/image/classification/mobilenet_v3_small_imagenet_ssld/README_en.md @@ -17,7 +17,8 @@ - ### Module Introduction - - MobileNetV3是Google在2019年发布的新模型，作者通过结合NAS与NetAdapt进行搜索得到该网络结构，提供了Large和Small两个版本，分别适用于对资源不同要求的情况.对比于MobileNetV2，新的模型在速度和精度方面均有提升.该PaddleHubModule的模型结构为MobileNetV3 Small，基于ImageNet-2012数据集并采用PaddleClas提供的SSLD蒸馏方法训练得到，接受输入图片大小为224 x 224 x 3，支持finetune，也可以直接通过命令行或者Python接口进行预测. + - MobileNetV3 is an image classification model proposed by Google in 2019. The authors proposed to search the network architecture by combination of NAS and NetAdapt, and provide two versions of this model, i.e. Large and Small version. This module is based on MobileNetV3 Small, trained on ImageNet-2012 with SSLD distillation strategy, and can predict an image of size 224*224*3. + ## II.Installation diff --git a/modules/image/classification/nasnet_imagenet/README_en.md b/modules/image/classification/nasnet_imagenet/README_en.md index 4626ebba889bba9e0682428ea8b91c800a302a89..942d5c966f02d27c8f46e1737bc9efc16dc35fa6 100644 --- a/modules/image/classification/nasnet_imagenet/README_en.md +++ b/modules/image/classification/nasnet_imagenet/README_en.md @@ -16,8 +16,7 @@ - ### Module Introduction - - - NASNet是Google通过AutoML自动训练出来的图像分类模型.该PaddleHub Module基于ImageNet-2012数据集训练，接受输入图片大小为224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - NASNet is proposed by Google, which is trained by AutoML. This module is based on NASNet, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/pnasnet_imagenet/README_en.md b/modules/image/classification/pnasnet_imagenet/README_en.md index 6ec189f26a79a6f80ddc120e0c6b9177e376f0cc..4c8ca8c1d9b8151b5ea5fa167bc4299e9cd2c6d4 100644 --- a/modules/image/classification/pnasnet_imagenet/README_en.md +++ b/modules/image/classification/pnasnet_imagenet/README_en.md @@ -17,7 +17,8 @@ - ### Module Introduction - - PNASNet是Google通过AutoML自动训练出来的图像分类模型.该PaddleHub Module基于ImageNet-2012数据集训练，接受输入图片大小为224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - PNASNet is proposed by Google, which is trained by AutoML. This module is based on PNASNet, trained on ImageNet-2012, and can predict an image of size 224*224*3. + ## II.Installation diff --git a/modules/image/classification/res2net101_vd_26w_4s_imagenet/README_en.md b/modules/image/classification/res2net101_vd_26w_4s_imagenet/README_en.md index 6b7b0dc16c6b337cfafc6e86c43fd9ab8be5a03c..068a160615a34c715811c51127fb1103fcd4d5f1 100644 --- a/modules/image/classification/res2net101_vd_26w_4s_imagenet/README_en.md +++ b/modules/image/classification/res2net101_vd_26w_4s_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - Res2Net是2019年提出的一种全新的对ResNet的改进方案，该方案可以和现有其他优秀模块轻松整合，在不增加计算负载量的情况下，在ImageNet、CIFAR-100等数据集上的测试性能超过了ResNet.Res2Net结构简单，性能优越，进一步探索了CNN在更细粒度级别的多尺度表示能力. 该 PaddleHub Module 使用 ImageNet-2012数据集训练，接受输入图片大小为 224 x 224 x 3，支持直接通过命令行或者 Python 接口进行预测. + - Res2Net is an improvement on ResNet, which can improve performance without increasing computation. This module is based on Res2Net, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation @@ -45,7 +45,7 @@ ``` - If you want to call the Hub module through the command line, please refer to: [PaddleHub Command Line Instruction](../../../../docs/docs_ch/tutorial/cmd_usage.rst) -- ### 2、预测Prediction Code Example +- ### 2、Prediction Code Example - ```python import paddlehub as hub diff --git a/modules/image/classification/resnet18_vd_imagenet/README_en.md b/modules/image/classification/resnet18_vd_imagenet/README_en.md index e812c02e29452197ae51c5368eecf675b39e5f6f..9e7b755d5f695a6390a21e7b724ff2c8dbc12bea 100644 --- a/modules/image/classification/resnet18_vd_imagenet/README_en.md +++ b/modules/image/classification/resnet18_vd_imagenet/README_en.md @@ -17,7 +17,8 @@ - ### Module Introduction - - ResNet系列模型是图像分类领域的重要模型之一，模型中提出的残差单元有效地解决了深度网络训练困难的问题，通过增加模型的深度提升了模型的准确率，ResNet-vd 其实就是 ResNet-D，是ResNet 原始结构的变种.该PaddleHub Module结构为ResNet_vd，基于ImageNet-2012数据集训练得到，接受输入图片大小为224 x 224 x 3，支持finetune，也可以直接通过命令行或者Python接口进行预测. + - ResNet proposed a residual unit to solve the problem of training an extremely deep network, and improved the prediction accuracy of models. ResNet-vd is a variant of ResNet. This module is based on ResNet_vd, trained on ImageNet-2012 dataset, and can predict an image of size 224*224*3. + ## II.Installation diff --git a/modules/image/classification/resnet50_vd_10w/README_en.md b/modules/image/classification/resnet50_vd_10w/README_en.md index dc0e1b98bd3cee639f43d81737f27e3cc5b1d2e2..7dfaf3b7f097afcd30d63585a0e0b1bdc0a95481 100644 --- a/modules/image/classification/resnet50_vd_10w/README_en.md +++ b/modules/image/classification/resnet50_vd_10w/README_en.md @@ -4,7 +4,7 @@ | :--- | :---: | |Category|image classification| |Network|ResNet_vd| -|Dataset|百度自建Dataset| +|Dataset|Baidu Dataset| |Fine-tuning supported or not|No| |Module Size|92MB| |Latest update date|-| @@ -17,7 +17,7 @@ - ### Module Introduction - - ResNet系列模型是图像分类领域的重要模型之一，模型中提出的残差单元有效地解决了深度网络训练困难的问题，通过增加模型的深度提升了模型的准确率，ResNet-vd 其实就是 ResNet-D，是ResNet 原始结构的变种.该PaddleHub Module结构为ResNet_vd，使用百度自研的基于10万种类别、4千多万的有标签数据进行训练，接受输入图片大小为224 x 224 x 3，支持finetune. + - ResNet proposed a residual unit to solve the problem of training an extremely deep network, and improved the prediction accuracy of models. ResNet-vd is a variant of ResNet. This module is based on ResNet_vd, trained on Baidu dataset(consists of 100 thousand classes, 40 million pairs of data), and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/resnet50_vd_dishes/README_en.md b/modules/image/classification/resnet50_vd_dishes/README_en.md index 4076ffdf2962cb81d22652a55bf11b6b841747e2..48c38672ebe4b49894635d452bf4a1dbc4a53194 100644 --- a/modules/image/classification/resnet50_vd_dishes/README_en.md +++ b/modules/image/classification/resnet50_vd_dishes/README_en.md @@ -4,7 +4,7 @@ | :--- | :---: | |Category|image classification| |Network|ResNet50_vd| -|Dataset|百度自建菜品Dataset| +|Dataset|Baidu Food Dataset| |Fine-tuning supported or not|No| |Module Size|158MB| |Latest update date|-| @@ -17,13 +17,13 @@ - ### Module Introduction - - ResNet-vd是ResNet原始结构的变种，可用于图像分类和特征提取.该 PaddleHub Module 采用百度自建菜品数据集训练得到，支持8416种菜品的分类识别. + - ResNet proposed a residual unit to solve the problem of training an extremely deep network, and improved the prediction accuracy of models. ResNet-vd is a variant of ResNet. This module is based on ResNet-vd and can classify 8416 kinds of food.


- - 更多详情参考：[Bag of Tricks for Image Classification with Convolutional Neural Networks](https://arxiv.org/pdf/1812.01187.pdf) + - For more information, please refer to：[Bag of Tricks for Image Classification with Convolutional Neural Networks](https://arxiv.org/pdf/1812.01187.pdf) ## II.Installation diff --git a/modules/image/classification/resnet50_vd_wildanimals/README_en.md b/modules/image/classification/resnet50_vd_wildanimals/README_en.md index 72312f25308f006001a757260ad501906f71f0d0..0424be2897f4261dcc7976814173c4812d7f451b 100644 --- a/modules/image/classification/resnet50_vd_wildanimals/README_en.md +++ b/modules/image/classification/resnet50_vd_wildanimals/README_en.md @@ -4,7 +4,7 @@ | :--- | :---: | |Category|image classification| |Network|ResNet_vd| -|Dataset|IFAW 自建野生动物Dataset| +|Dataset|IFAW Wild Animal Dataset| |Fine-tuning supported or not|No| |Module Size|92MB| |Latest update date|-| @@ -17,7 +17,8 @@ - ### Module Introduction - - ResNet-vd 其实就是 ResNet-D，是ResNet 原始结构的变种，可用于图像分类和特征提取.该 PaddleHub Module 采用百度自建野生动物数据集训练得到，支持'象牙制品','象牙', '大象', '虎皮', '老虎', '虎牙/虎爪/虎骨', '穿山甲甲片', '穿山甲', '穿山甲爪子', '其他' 这十个标签的识别.模型的详情可参考[论文](https://arxiv.org/pdf/1812.01187.pdf). + - ResNet proposed a residual unit to solve the problem of training an extremely deep network, and improved the prediction accuracy of models. ResNet-vd is a variant of ResNet. This module is based on ResNet_vd, trained on IFAW Wild Animal dataset, and can predict ten kinds of wild animal components. + diff --git a/modules/image/classification/se_resnext101_32x4d_imagenet/README_en.md b/modules/image/classification/se_resnext101_32x4d_imagenet/README_en.md index fc57fb1619b0ef0f654fbbc485dc1cab7e7b49cd..a725971695c1946e2252fca36e1a1c650ca93b95 100644 --- a/modules/image/classification/se_resnext101_32x4d_imagenet/README_en.md +++ b/modules/image/classification/se_resnext101_32x4d_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - Squeeze-and-Excitation Networks是由Momenta在2017年提出的一种图像分类结构.该结构通过对特征通道间的相关性进行建模，把重要的特征进行强化来提升准确率.SE_ResNeXt基于ResNeXt模型添加了SE Block，并获得了2017 ILSVR竞赛的冠军.该PaddleHub Module结构为SE_ResNeXt101_32x4d，基于ImageNet-2012数据集训练，接受输入图片大小为224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - Squeeze-and-Excitation Network is proposed by Momenta in 2017. This model learns the weight to strengthen important channels of features and improves classification accuracy, which is the champion of ILSVR 2017. This module is based on se_resnext101_32x4d, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/se_resnext50_32x4d_imagenet/README_en.md b/modules/image/classification/se_resnext50_32x4d_imagenet/README_en.md index ff10563a440a8bdddde8396ea959fe33c864dfdd..91fd44b398961db6606715bc4477c5f96c0d837a 100644 --- a/modules/image/classification/se_resnext50_32x4d_imagenet/README_en.md +++ b/modules/image/classification/se_resnext50_32x4d_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - Squeeze-and-Excitation Networks是由Momenta在2017年提出的一种图像分类结构.该结构通过对特征通道间的相关性进行建模，把重要的特征进行强化来提升准确率.SE_ResNeXt基于ResNeXt模型添加了SE Block，并获得了2017 ILSVR竞赛的冠军.该PaddleHub Module结构为SE_ResNeXt50_32x4d，基于ImageNet-2012数据集训练，接受输入图片大小为224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - Squeeze-and-Excitation Network is proposed by Momenta in 2017. This model learns the weight to strengthen important channels of features and improves classification accuracy, which is the champion of ILSVR 2017. This module is based on SE_ResNeXt50_32x4d, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/shufflenet_v2_imagenet/README_en.md b/modules/image/classification/shufflenet_v2_imagenet/README_en.md index b6422fb559e7e3b95ccd4e7a8c75be5950358eb2..5ef66a8173c5205fddac0de35c2e7806a822c0c2 100644 --- a/modules/image/classification/shufflenet_v2_imagenet/README_en.md +++ b/modules/image/classification/shufflenet_v2_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - ShuffleNet V2是由旷视科技在2018年提出的轻量级图像分类模型，该模型通过pointwise group convolution和channel shuffle两种方式，在保持精度的同时大大降低了模型的计算量.该PaddleHub Module结构为ShuffleNet V2，基于ImageNet-2012数据集训练，接受输入图片大小为224 x 224 x 3，支持直接通过命令行或者Python接口进行预测. + - ShuffleNet V2 is a light-weight model proposed by MEGVII in 2018. This model proposed pointwise group convolution and channel shuffle to keep accurary and reduce the amount of computation. This module is based on ShuffleNet V2, trained on ImageNet-2012, and can predict an image of 224*224*3. ## II.Installation diff --git a/modules/image/classification/spinalnet_res101_gemstone/README_en.md b/modules/image/classification/spinalnet_res101_gemstone/README_en.md index d56f944aed7e4faa76b1ff0b2a5a7471c4e18d0d..c59d1fbf33e5f5c4e3a592351ab89520bb8a1982 100644 --- a/modules/image/classification/spinalnet_res101_gemstone/README_en.md +++ b/modules/image/classification/spinalnet_res101_gemstone/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - 使用PaddleHub的SpinalNet预训练模型进行宝石识别或finetune并完成宝石的预测任务. + - This module is based on SpinalNet trained on gemstone dataset, and can be used to classify a gemstone. ## II.Installation - ### 1、Environmental Dependence @@ -61,7 +61,7 @@ ``` - classification API. - **Parameters** - - images: list类型，待预测的图像. + - images(list[numpy.ndarray]): image data. - **Return** - result(list[dict]): classication results, each element in the list is dict, key is the label name, and value is the corresponding probability diff --git a/modules/image/classification/spinalnet_res50_gemstone/README_en.md b/modules/image/classification/spinalnet_res50_gemstone/README_en.md index 19aa3519a8f90a81cb9419b574cd45e95d0991e1..c3150dfa6dfdfc981aa986236aeb96af1e8eb994 100644 --- a/modules/image/classification/spinalnet_res50_gemstone/README_en.md +++ b/modules/image/classification/spinalnet_res50_gemstone/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - 使用PaddleHub的SpinalNet预训练模型进行宝石识别或finetune并完成宝石的预测任务. + - This module is based on SpinalNet trained on gemstone dataset, and can be used to classify a gemstone. ## II.Installation - ### 1、Environmental Dependence diff --git a/modules/image/classification/spinalnet_vgg16_gemstone/README.md b/modules/image/classification/spinalnet_vgg16_gemstone/README.md index 5ca6eacd550179c5cb0c838d0c2451eb3d61f02f..34de23e6766539360c28826fbe3f7e3528a15b55 100644 --- a/modules/image/classification/spinalnet_vgg16_gemstone/README.md +++ b/modules/image/classification/spinalnet_vgg16_gemstone/README.md @@ -18,6 +18,7 @@ - ### 模型介绍 - 使用PaddleHub的SpinalNet预训练模型进行宝石识别或finetune并完成宝石的预测任务。 + ## 二、安装 - ### 1、环境依赖 diff --git a/modules/image/classification/spinalnet_vgg16_gemstone/README_en.md b/modules/image/classification/spinalnet_vgg16_gemstone/README_en.md index 664cb1b17c90bd31c5f2d5f694caeb29656edf20..0d217bd7a87d4a3a2325ec450d5e88587e16a703 100644 --- a/modules/image/classification/spinalnet_vgg16_gemstone/README_en.md +++ b/modules/image/classification/spinalnet_vgg16_gemstone/README_en.md @@ -17,7 +17,8 @@ - ### Module Introduction - - 使用PaddleHub的SpinalNet预训练模型进行宝石识别或finetune并完成宝石的预测任务. + - This module is based on SpinalNet trained on gemstone dataset, and can be used to classify a gemstone. + ## II.Installation - ### 1、Environmental Dependence @@ -61,7 +62,7 @@ ``` - classification API. - **Parameters** - - images: list类型，待预测的图像. + - images (list\[numpy.ndarray\]): image data, ndarray.shape is in the format [H, W, C], BGR; - **Return** - result(list[dict]): classication results, each element in the list is dict, key is the label name, and value is the corresponding probability diff --git a/modules/image/classification/xception41_imagenet/README_en.md b/modules/image/classification/xception41_imagenet/README_en.md index d4d4d8b74329ab2218e0fe655dd307e81ee54c5c..0736b6910abe77ffbb69dc0a693276b2e6c09e89 100644 --- a/modules/image/classification/xception41_imagenet/README_en.md +++ b/modules/image/classification/xception41_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - Xception 全称为 Extreme Inception，是 Google 于 2016年提出的 Inception V3 的改进模型.Xception 采用了深度可分离卷积(depthwise separable convolution) 来替换原来 Inception V3 中的卷积操作，整体的网络结构是带有残差连接的深度可分离卷积层的线性堆叠.该PaddleHub Module结构为Xception41，基于ImageNet-2012数据集训练，接受输入图片大小为224 x 224 x 3，支持直接通过命令行或者 Python 接口进行预测. + - Xception is a model proposed by Google in 2016, which is an improvement on Inception V3. This module is based on Xception41, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/xception65_imagenet/README_en.md b/modules/image/classification/xception65_imagenet/README_en.md index d851a8b1ce7ea98d50f9387bd35f6e3e5643772c..a92b741536298d766765269e55742f7b6c203b99 100644 --- a/modules/image/classification/xception65_imagenet/README_en.md +++ b/modules/image/classification/xception65_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - Xception 全称为 Extreme Inception，是 Google 于 2016年提出的 Inception V3 的改进模型.Xception 采用了深度可分离卷积(depthwise separable convolution) 来替换原来 Inception V3 中的卷积操作，整体的网络结构是带有残差连接的深度可分离卷积层的线性堆叠.该PaddleHub Module结构为Xception65，基于ImageNet-2012数据集训练，接受输入图片大小为224 x 224 x 3，支持直接通过命令行或者 Python 接口进行预测. + - Xception is a model proposed by Google in 2016, which is an improvement on Inception V3. This module is based on Xception65, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation diff --git a/modules/image/classification/xception71_imagenet/README_en.md b/modules/image/classification/xception71_imagenet/README_en.md index 3912996c2df3e840398c9884602fad35c2f7e790..f3f17e30b0abc10c0740752069a8b9d61318175e 100644 --- a/modules/image/classification/xception71_imagenet/README_en.md +++ b/modules/image/classification/xception71_imagenet/README_en.md @@ -17,7 +17,7 @@ - ### Module Introduction - - Xception 全称为 Extreme Inception，是 Google 于 2016年提出的 Inception V3 的改进模型.Xception 采用了深度可分离卷积(depthwise separable convolution) 来替换原来 Inception V3 中的卷积操作，整体的网络结构是带有残差连接的深度可分离卷积层的线性堆叠.该PaddleHub Module结构为Xception71，基于ImageNet-2012数据集训练，接受输入图片大小为224 x 224 x 3，支持直接通过命令行或者 Python 接口进行预测. + - Xception is a model proposed by Google in 2016, which is an improvement on Inception V3. This module is based on Xception71, trained on ImageNet-2012, and can predict an image of size 224*224*3. ## II.Installation