update attribute docs

docs/en/PULC/PULC_person_attribute_en.md

@@ -44,7 +44,7 @@ Pedestrian analysis scenarios, pedestrian tracking scenarios, etc.
 The following table lists the relevant indicators of the model. The first three lines means that using Res2Net200_vd_26w_4s, SwinTransformer_tiny and MobileNetV3_small_x0_35 as the backbone to training. The fourth to seventh lines means that the backbone is replaced by PPLCNet, additional use of EDA strategy and additional use of EDA strategy and SKL-UGI knowledge distillation strategy.
     
     
-| Backbone | ma（%） | Latency(ms)） | Size(M) | Training Strategy |
+| Backbone | ma（%） | Latency(ms) | Size(M) | Training Strategy |
 |-------|-----------|----------|---------------|---------------|
 | Res2Net200_vd_26w_4s  | 81.25 | 77.51  | 293 | using ImageNet pretrained |
 | SwinTransformer_tiny  | 80.17 | 89.51  | 107 | using ImageNet pretrained |
@@ -157,7 +157,7 @@ The data used in this case is the [pa100k dataset](https://www.v7labs.com/open-d
 
 Some image of the processed dataset is as follows:
 
-![](./../images/PULC/docs/person_attribute_data_demo.png)
+![](../../images/PULC/docs/person_attribute_data_demo.png)
 
 
 We converted the data into a PaddleClas multi-label readable data format that can be downloaded directly.

docs/en/PULC/PULC_vehicle_attribute_en.md

@@ -157,6 +157,13 @@ The data used in this case is the [pa100k dataset](https://www.v7labs.com/open-d
 
 #### 3.2.2 Getting Dataset
 
+
+Part of the data visualization is shown below.
+
+<div align="center">
+<img src="../../images/PULC/docs/vehicle_attribute_data_demo.png"  width = "500" />
+</div>
+    
 First, apply for and download data from [VeRi dataset official website](https://www.v7labs.com/open-datasets/veri-dataset), put it in the `dataset` directory of PaddleClas, the dataset directory name is `VeRi `, use the following command to enter the folder.
     
 

docs/zh_CN/PULC/PULC_vehicle_attribute.md

@@ -40,7 +40,7 @@
 
 ## 1. 模型和应用场景介绍
 
-该案例提供了用户使用 PaddleClas 的超轻量图像分类方案（PULC，Practical Ultra Lightweight Classification）快速构建轻量级、高精度、可落地的车辆属性识别模型。该模型可以广泛应用于车辆识别、道路监控等场景。
+该案例提供了用户使用 PaddleClas 的超轻量图像分类方案（PULC，Practical Ultra Lightweight image Classification）快速构建轻量级、高精度、可落地的车辆属性识别模型。该模型可以广泛应用于车辆识别、道路监控等场景。
 
 下表列出了不同车辆属性识别模型的相关指标，前三行展现了使用 Res2Net200_vd_26w_4s、 ResNet50、MobileNetV3_small_x0_35 作为 backbone 训练得到的模型的相关指标，第四行至第七行依次展现了替换 backbone 为 PPLCNet_x1_0、使用 SSLD 预训练模型、使用 SSLD 预训练模型 + EDA 策略、使用 SSLD 预训练模型 + EDA 策略 + SKL-UGI 知识蒸馏策略训练得到的模型的相关指标。