diff --git a/docs/en/tutorials/getting_started_en.md b/docs/en/tutorials/getting_started_en.md
index 1712dc3729106d5591356a5970d4aa9b1f1b744a..4150ba64d0623e946bcd4df4e690d30fc77a34bd 100644
--- a/docs/en/tutorials/getting_started_en.md
+++ b/docs/en/tutorials/getting_started_en.md
@@ -210,9 +210,13 @@ Among them:
 + `pretrained_model`: Weight file path, such as `./pretrained/MobileNetV3_large_x1_0_pretrained/`;
 + `use_gpu`: Whether to use the GPU, default by `True`;
 + `load_static_weights`: Whether to load the pre-trained model obtained from static image training, default by `False`;
++ `resize_short`: The length of the shortest side of the image that be scaled proportionally, default by `256`;
++ `resize`: The side length of the image that be center cropped from resize_shorted image, default by `224`;
 + `pre_label_image`: Whether to pre-label the image data, default value: `False`;
 + `pre_label_out_idr`: The output path of pre-labeled image data. When `pre_label_image=True`, a lot of subfolders will be generated under the path, each subfolder represent a category, which stores all the images predicted by the model to belong to the category.
 
+**Note**: If you want to use `Transformer series models`, such as `DeiT_***_384`, `ViT_***_384`, etc., please pay attention to the input size of model, and need to set `resize_short=384`, `reize=384`.
+
 About more detailed infomation, you can refer to [infer.py](../../../tools/infer/infer.py).
 
 <a name="model_inference"></a>
@@ -253,6 +257,9 @@ Among them:
 + `use_tensorrt`: Whether to use the TesorRT, default by `True`;
 + `use_gpu`: Whether to use the GPU, default by `True`
 + `enable_mkldnn`: Wheter to use `MKL-DNN`, default by `False`. When both `use_gpu` and `enable_mkldnn` are set to `True`, GPU is used to run and `enable_mkldnn` will be ignored.
++ `resize_short`: The length of the shortest side of the image that be scaled proportionally, default by `256`;
++ `resize`: The side length of the image that be center cropped from resize_shorted image, default by `224`;
 
+**Note**: If you want to use `Transformer series models`, such as `DeiT_***_384`, `ViT_***_384`, etc., please pay attention to the input size of model, and need to set `resize_short=384`, `reize=384`.
 
 If you want to evaluate the speed of the model, it is recommended to use [predict.py](../../../tools/infer/predict.py), and enable TensorRT to accelerate.
diff --git a/docs/en/whl_en.md b/docs/en/whl_en.md
index 16d6f694ac1afdafa0780b51389d4d0bcc85ab7b..7bd00c6c20302129c7ef93dc9c65da09154fd293 100644
--- a/docs/en/whl_en.md
+++ b/docs/en/whl_en.md
@@ -73,6 +73,8 @@ paddleclas --model_name=ResNet50 --top_k=5 --image_file='docs/images/whl/demo.jp
 * pre_label_image(bool): whether prelabel or not, default=False.
 * pre_label_out_idr(str): If prelabeling, the path of output.
 
+**Note**: If you want to use `Transformer series models`, such as `DeiT_***_384`, `ViT_***_384`, etc., please pay attention to the input size of model, and need to set `resize_short=384`, `reize=384`.
+
 ### 3. Different Usages of Codes
 
 **We provide two ways to use: 1. Python interative programming 2. Bash command line programming**
diff --git a/docs/zh_CN/tutorials/getting_started.md b/docs/zh_CN/tutorials/getting_started.md
index d7274fc7dead92e7e5c308b1e5912fc78b1c1406..6ad9968c9565639085f9f5bba37a73e5937f5559 100644
--- a/docs/zh_CN/tutorials/getting_started.md
+++ b/docs/zh_CN/tutorials/getting_started.md
@@ -224,9 +224,13 @@ python tools/infer/infer.py \
 + `pretrained_model`：模型权重文件路径，如 `./output/MobileNetV3_large_x1_0/best_model/ppcls`
 + `use_gpu` : 是否开启GPU训练，默认值：`True`
 + `load_static_weights` : 模型权重文件是否为静态图训练得到的，默认值：`False`
++ `resize_short`: 对输入图像进行等比例缩放，表示最短边的尺寸，默认值：`256`
++ `resize`: 对`resize_short`操作后的进行居中裁剪，表示裁剪的尺寸，默认值：`224`
 + `pre_label_image` : 是否对图像数据进行预标注，默认值：`False`
 + `pre_label_out_idr` : 预标注图像数据的输出文件夹，当`pre_label_image=True`时，会在该文件夹下面生成很多个子文件夹，每个文件夹名称为类别id，其中存储模型预测属于该类别的所有图像。
 
+**注意**: 如果使用`Transformer`系列模型，如`DeiT_***_384`, `ViT_***_384`等，请注意模型的输入数据尺寸，需要设置参数`resize_short=384`, `reize=384`。
+
 
 <a name="model_inference"></a>
 ## 4. 使用inference模型进行模型推理
@@ -265,5 +269,9 @@ python tools/infer/predict.py \
 + `use_tensorrt`：是否使用 TesorRT 预测引擎，默认值：`True`
 + `use_gpu`：是否使用 GPU 预测，默认值：`True`
 + `enable_mkldnn`：是否启用`MKL-DNN`加速，默认为`False`。注意`enable_mkldnn`与`use_gpu`同时为`True`时，将忽略`enable_mkldnn`，而使用GPU运行。
++ `resize_short`: 对输入图像进行等比例缩放，表示最短边的尺寸，默认值：`256`
++ `resize`: 对`resize_short`操作后的进行居中裁剪，表示裁剪的尺寸，默认值：`224`
+
+**注意**: 如果使用`Transformer`系列模型，如`DeiT_***_384`, `ViT_***_384`等，请注意模型的输入数据尺寸，需要设置参数`resize_short=384`, `reize=384`。
 
 * 如果你希望评测模型速度，建议使用该脚本(`tools/infer/predict.py`)，同时开启TensorRT加速预测。
diff --git a/docs/zh_CN/whl.md b/docs/zh_CN/whl.md
index 076cbdd7a34bdd7cf08f2cbf0303fe0abe9fff0d..57f633b20fceb1d85e7b7b7a1bb83aaba9b5e4e3 100644
--- a/docs/zh_CN/whl.md
+++ b/docs/zh_CN/whl.md
@@ -72,6 +72,8 @@ paddleclas --model_name=ResNet50 --top_k=5 --image_file='docs/images/whl/demo.jp
 * pre_label_image(bool): 是否需要进行预标注。
 * pre_label_out_idr(str): 进行预标注后，输出结果的文件路径，默认为None。
 
+**注意**: 如果使用`Transformer`系列模型，如`DeiT_***_384`, `ViT_***_384`等，请注意模型的输入数据尺寸，需要设置参数`resize_short=384`, `reize=384`。
+
 ### 3. 代码使用方法
 
 **提供两种使用方式：1、python交互式编程。2、bash命令行式编程**