diff --git a/README.md b/README.md
index b6e97fd..872095e 100644
--- a/README.md
+++ b/README.md
@@ -87,7 +87,7 @@ Following models are implemented.
 
 The .wts files can be downloaded from model zoo for quick evaluation. But it is recommended to convert .wts from pytorch/mxnet/tensorflow model, so that you can retrain your own model.
 
-[BaiduPan](https://pan.baidu.com/s/19s6hO8esU7-TtZEXN7G3OA) pwd: uvv2
+[GoogleDrive](https://drive.google.com/drive/folders/1Ri0IDa5OChtcA3zjqRTW57uG6TnfN4Do?usp=sharing) | [BaiduPan](https://pan.baidu.com/s/19s6hO8esU7-TtZEXN7G3OA) pwd: uvv2
 
 ## Tricky Operations
 
diff --git a/retinaface/README.md b/retinaface/README.md
index da111e6..059a550 100644
--- a/retinaface/README.md
+++ b/retinaface/README.md
@@ -46,7 +46,7 @@ sudo ./retina_r50 -d  // deserialize model file and run inference.
 
 # INT8 Quantization
 
-1. Prepare calibration images, you can randomly select 1000s images from your train set. For widerface, you can also download my calibration images `widerface_calib` from [BaiduPan](https://pan.baidu.com/s/1GOm_-JobpyLMAqZWCDUhKg) pwd: a9wh
+1. Prepare calibration images, you can randomly select 1000s images from your train set. For widerface, you can also download my calibration images `widerface_calib` from [GoogleDrive](https://drive.google.com/drive/folders/1s7jE9DtOngZMzJC1uL307J2MiaGwdRSI?usp=sharing) or [BaiduPan](https://pan.baidu.com/s/1GOm_-JobpyLMAqZWCDUhKg) pwd: a9wh
 
 2. unzip it in retinaface/build
 
diff --git a/yolov3/README.md b/yolov3/README.md
index ee4eafc..8830c58 100644
--- a/yolov3/README.md
+++ b/yolov3/README.md
@@ -45,7 +45,7 @@ sudo ./yolov3 -d ../../yolov3-spp/samples // deserialize plan file and run infer
 
 # INT8 Quantization
 
-1. Prepare calibration images, you can randomly select 1000s images from your train set. For coco, you can also download my calibration images `coco_calib` from [BaiduPan](https://pan.baidu.com/s/1GOm_-JobpyLMAqZWCDUhKg) pwd: a9wh
+1. Prepare calibration images, you can randomly select 1000s images from your train set. For coco, you can also download my calibration images `coco_calib` from [GoogleDrive](https://drive.google.com/drive/folders/1s7jE9DtOngZMzJC1uL307J2MiaGwdRSI?usp=sharing) or [BaiduPan](https://pan.baidu.com/s/1GOm_-JobpyLMAqZWCDUhKg) pwd: a9wh
 
 2. unzip it in yolov3/build
 
diff --git a/yolov5/README.md b/yolov5/README.md
index cf937ec..a55fe11 100644
--- a/yolov5/README.md
+++ b/yolov5/README.md
@@ -69,7 +69,7 @@ python yolov5_trt.py
 
 # INT8 Quantization
 
-1. Prepare calibration images, you can randomly select 1000s images from your train set. For coco, you can also download my calibration images `coco_calib` from [BaiduPan](https://pan.baidu.com/s/1GOm_-JobpyLMAqZWCDUhKg) pwd: a9wh
+1. Prepare calibration images, you can randomly select 1000s images from your train set. For coco, you can also download my calibration images `coco_calib` from [GoogleDrive](https://drive.google.com/drive/folders/1s7jE9DtOngZMzJC1uL307J2MiaGwdRSI?usp=sharing) or [BaiduPan](https://pan.baidu.com/s/1GOm_-JobpyLMAqZWCDUhKg) pwd: a9wh
 
 2. unzip it in yolov5/build