diff --git a/docs/en/PULC/PULC_traffic_sign_en.md b/docs/en/PULC/PULC_traffic_sign_en.md
new file mode 100644
index 0000000000000000000000000000000000000000..9bd8ec3a778897eb314bd9d5547588eaadb7d2e8
--- /dev/null
+++ b/docs/en/PULC/PULC_traffic_sign_en.md
@@ -0,0 +1,476 @@
+# PULC Classification Model of Traffic Sign
+
+------
+
+## Catalogue
+
+- [1. Introduction](#1)
+- [2. Quick Start](#2)
+ - [2.1 PaddlePaddle Installation](#2.1)
+ - [2.2 PaddleClas Installation](#2.2)
+ - [2.3 Prediction](#2.3)
+- [3. Training, Evaluation and Inference](#3)
+ - [3.1 Installation](#3.1)
+ - [3.2 Dataset](#3.2)
+ - [3.2.1 Dataset Introduction](#3.2.1)
+ - [3.2.2 Getting Dataset](#3.2.2)
+ - [3.3 Training](#3.3)
+ - [3.4 Evaluation](#3.4)
+ - [3.5 Inference](#3.5)
+- [4. Model Compression](#4)
+ - [4.1 SKL-UGI Knowledge Distillation](#4.1)
+ - [4.1.1 Teacher Model Training](#4.1.1)
+ - [4.1.2 Knowledge Distillation Training](#4.1.2)
+- [5. SHAS](#5)
+- [6. Inference Deployment](#6)
+ - [6.1 Getting Paddle Inference Model](#6.1)
+ - [6.1.1 Exporting Paddle Inference Model](#6.1.1)
+ - [6.1.2 Downloading Inference Model](#6.1.2)
+ - [6.2 Prediction with Python](#6.2)
+ - [6.2.1 Image Prediction](#6.2.1)
+ - [6.2.2 Images Prediction](#6.2.2)
+ - [6.3 Deployment with C++](#6.3)
+ - [6.4 Deployment as Service](#6.4)
+ - [6.5 Deployment on Mobile](#6.5)
+ - [6.6 Converting To ONNX and Deployment](#6.6)
+
+
+
+## 1. Introduction
+
+This case provides a way for users to quickly build a lightweight, high-precision and practical classification model of traffic sign using PaddleClas PULC (Practical Ultra Lightweight Classification). The model can be widely used in automatic driving, road monitoring, etc.
+
+The following table lists the relevant indicators of the model. The first two lines means that using SwinTransformer_tiny and MobileNetV3_small_x0_35 as the backbone to training. The third to sixth 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 | Top-1 Acc(%) | Latency(ms) | Size(M)| Training Strategy |
+|-------|-----------|----------|---------------|---------------|
+| SwinTranformer_tiny | 98.11 | 89.45 | 111 | using ImageNet pretrained model |
+| MobileNetV3_small_x0_35 | 93.88 | 3.01 | 3.9 | using ImageNet pretrained model |
+| PPLCNet_x1_0 | 97.78 | 2.10 | 8.2 | using ImageNet pretrained model |
+| PPLCNet_x1_0 | 97.84 | 2.10 | 8.2 | using SSLD pretrained model |
+| PPLCNet_x1_0 | 98.14 | 2.10 | 8.2 | using SSLD pretrained model + EDA strategy |
+| PPLCNet_x1_0 | 98.35 | 2.10 | 8.2 | using SSLD pretrained model + EDA strategy + SKL-UGI knowledge distillation strategy|
+
+It can be seen that high accuracy can be getted when backbone is SwinTranformer_tiny, but the speed is slow. Replacing backbone with the lightweight model MobileNetV3_small_x0_35, the speed can be greatly improved, but the accuracy will be greatly reduced. Replacing backbone with faster backbone PPLCNet_x1_0, the accuracy is lower 3.9 percentage points than MobileNetv3_small_x0_35. At the same time, the speed can be more than 43% faster. After additional using the SSLD pretrained model, the accuracy can be improved by about 0.06 percentage points without affecting the inference speed. Further, additional using the EDA strategy, the accuracy can be increased by 0.3 percentage points. Finally, after additional using the SKL-UGI knowledge distillation, the accuracy can be further improved by 0.21 percentage points. At this point, the accuracy exceeds that of SwinTranformer_tiny, but the speed is more than 41 times faster. The training method and deployment instructions of PULC will be introduced in detail below.
+
+**Note**:
+
+* The Latency is tested on Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz. The MKLDNN is enabled and the number of threads is 10.
+* About PP-LCNet, please refer to [PP-LCNet Introduction](../models/PP-LCNet_en.md) and [PP-LCNet Paper](https://arxiv.org/abs/2109.15099).
+
+
+
+## 2. Quick Start
+
+
+
+### 2.1 PaddlePaddle Installation
+
+- Run the following command to install if CUDA9 or CUDA10 is available.
+
+```bash
+python3 -m pip install paddlepaddle-gpu -i https://mirror.baidu.com/pypi/simple
+```
+
+- Run the following command to install if GPU device is unavailable.
+
+```bash
+python3 -m pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple
+```
+
+Please refer to [PaddlePaddle Installation](https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/en/install/pip/linux-pip_en.html) for more information about installation, for examples other versions.
+
+
+
+### 2.2 PaddleClas wheel Installation
+
+The command of PaddleClas installation as bellow:
+
+```bash
+pip3 install paddleclas
+```
+
+
+
+### 2.3 Prediction
+
+First, please click [here](https://paddleclas.bj.bcebos.com/data/PULC/pulc_demo_imgs.zip) to download and unzip to get the test demo images.
+
+* Prediction with CLI
+
+```bash
+paddleclas --model_name=traffic_sign --infer_imgs=pulc_demo_imgs/traffic_sign/100999_83928.jpg
+```
+
+Results:
+
+```
+>>> result
+class_ids: [182, 179, 162, 128, 24], scores: [0.98623, 0.01255, 0.00022, 0.00021, 0.00012], label_names: ['pl110', 'pl100', 'pl120', 'p26', 'pm10'], filename: pulc_demo_imgs/traffic_sign/100999_83928.jpg
+Predict complete!
+```
+
+**Note**: If you want to test other images, only need to specify the `--infer_imgs` argument, and the directory containing images is also supported.
+
+* Prediction in Python
+
+```python
+import paddleclas
+model = paddleclas.PaddleClas(model_name="traffic_sign")
+result = model.predict(input_data="pulc_demo_imgs/traffic_sign/100999_83928.jpg")
+print(next(result))
+```
+
+**Note**: The `result` returned by `model.predict()` is a generator, so you need to use the `next()` function to call it or `for` loop to loop it. And it will predict with `batch_size` size batch and return the prediction results when called. The default `batch_size` is 1, and you also specify the `batch_size` when instantiating, such as `model = paddleclas.PaddleClas(model_name="traffic_sign", batch_size=2)`. The result of demo above:
+
+```
+>>> result
+[{'class_ids': [182, 179, 162, 128, 24], 'scores': [0.98623, 0.01255, 0.00022, 0.00021, 0.00012], 'label_names': ['pl110', 'pl100', 'pl120', 'p26', 'pm10'], 'filename': 'pulc_demo_imgs/traffic_sign/100999_83928.jpg'}]
+```
+
+
+
+## 3. Training, Evaluation and Inference
+
+
+
+### 3.1 Installation
+
+Please refer to [Installation](../installation/install_paddleclas_en.md) to get the description about installation.
+
+
+
+### 3.2 Dataset
+
+
+
+#### 3.2.1 Dataset Introduction
+
+All datasets used in this case are open source data. Train data is the subset of [MS-COCO](https://cocodataset.org/#overview) training data. And the validation data is the subset of [Object365](https://www.objects365.org/overview.html) training data. ImageNet_val is [ImageNet-1k](https://www.image-net.org/) validation data.
+
+The dataset used in this case is based on the [Tsinghua-Tencent 100K dataset (CC-BY-NC license), TT100K](https://cg.cs.tsinghua.edu.cn/traffic-sign/) randomly expanded and cropped according to the bounding box.
+
+
+
+#### 3.2.2 Getting Dataset
+
+The processing to `TT00K` includes randomly expansion and cropping, details are shown below.
+
+```python
+def get_random_crop_box(xmin, ymin, xmax, ymax, img_height, img_width, ratio=1.0):
+ h = ymax - ymin
+ w = ymax - ymin
+
+ xmin_diff = random.random() * ratio * min(w, xmin/ratio)
+ ymin_diff = random.random() * ratio * min(h, ymin/ratio)
+ xmax_diff = random.random() * ratio * min(w, (img_width-xmin-1)/ratio)
+ ymax_diff = random.random() * ratio * min(h, (img_height-ymin-1)/ratio)
+
+ new_xmin = round(xmin - xmin_diff)
+ new_ymin = round(ymin - ymin_diff)
+ new_xmax = round(xmax + xmax_diff)
+ new_ymax = round(ymax + ymax_diff)
+
+ return new_xmin, new_ymin, new_xmax, new_ymax
+```
+
+Some image of the processed dataset is as follows:
+
+
+
+