diff --git a/PaddleCV/image_classification/README.md b/PaddleCV/image_classification/README.md
index 53f11a1da150d445d5c26bcfcbdf60cbd668cce2..9398c29d23389ca38e698674be7d806d899ebe55 100644
--- a/PaddleCV/image_classification/README.md
+++ b/PaddleCV/image_classification/README.md
@@ -718,13 +718,13 @@ python -m paddle.distributed.launch train.py \
 ### HRNet Series
 |Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
 |- |:-: |:-: |:-: |:-: |
-|[HRNet_W18_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W18_C_pretrained.tar) | 76.92% | 93.39% | 30.955 |  |
-|[HRNet_W30_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W30_C_pretrained.tar) | 78.04% | 94.02% | 33.336 |  |
-|[HRNet_W32_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W32_C_pretrained.tar) | 78.28% | 94.24% | 33.392 |  |
-|[HRNet_W40_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W40_C_pretrained.tar) | 78.77% | 94.47% | 38.316 |  |
-|[HRNet_W44_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W44_C_pretrained.tar) | 79.00% | 94.51% | 40.514 |  |
-|[HRNet_W48_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W48_C_pretrained.tar) | 78.95% | 94.42% | 34.667 |  |
-|[HRNet_W64_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W64_C_pretrained.tar) | 79.30% | 94.61% | 42.732 |  |
+|[HRNet_W18_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W18_C_pretrained.tar) | 76.92% | 93.39% | 23.013 | 11.601 |
+|[HRNet_W30_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W30_C_pretrained.tar) | 78.04% | 94.02% | 25.793 | 14.367 |
+|[HRNet_W32_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W32_C_pretrained.tar) | 78.28% | 94.24% | 29.564 | 14.328 |
+|[HRNet_W40_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W40_C_pretrained.tar) | 78.77% | 94.47% | 33.880 | 17.616 |
+|[HRNet_W44_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W44_C_pretrained.tar) | 79.00% | 94.51% | 36.021 | 18.990 |
+|[HRNet_W48_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W48_C_pretrained.tar) | 78.95% | 94.42% | 30.064 | 19.963 |
+|[HRNet_W64_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W64_C_pretrained.tar) | 79.30% | 94.61% | 38.921 | 24.742 |
 
 ## FAQ
 
diff --git a/PaddleCV/image_classification/README_en.md b/PaddleCV/image_classification/README_en.md
index 94748502541570aa22e83b7cd1d407dfc7886ccb..2ebea91d8bf51437662af51d9b5e20dc5b2d14ba 100644
--- a/PaddleCV/image_classification/README_en.md
+++ b/PaddleCV/image_classification/README_en.md
@@ -595,13 +595,13 @@ Pretrained models can be downloaded by clicking related model names.
 ### HRNet Series
 |Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
 |- |:-: |:-: |:-: |:-: |
-|[HRNet_W18_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W18_C_pretrained.tar) | 76.92% | 93.39% | 30.955 |  |
-|[HRNet_W30_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W30_C_pretrained.tar) | 78.04% | 94.02% | 33.336 |  |
-|[HRNet_W32_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W32_C_pretrained.tar) | 78.28% | 94.24% | 33.392 |  |
-|[HRNet_W40_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W40_C_pretrained.tar) | 78.77% | 94.47% | 38.316 |  |
-|[HRNet_W44_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W44_C_pretrained.tar) | 79.00% | 94.51% | 40.514 |  |
-|[HRNet_W48_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W48_C_pretrained.tar) | 78.95% | 94.42% | 34.667 |  |
-|[HRNet_W64_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W64_C_pretrained.tar) | 79.30% | 94.61% | 42.732 |  |
+|[HRNet_W18_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W18_C_pretrained.tar) | 76.92% | 93.39% | 23.013 | 11.601 |
+|[HRNet_W30_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W30_C_pretrained.tar) | 78.04% | 94.02% | 25.793 | 14.367 |
+|[HRNet_W32_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W32_C_pretrained.tar) | 78.28% | 94.24% | 29.564 | 14.328 |
+|[HRNet_W40_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W40_C_pretrained.tar) | 78.77% | 94.47% | 33.880 | 17.616 |
+|[HRNet_W44_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W44_C_pretrained.tar) | 79.00% | 94.51% | 36.021 | 18.990 |
+|[HRNet_W48_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W48_C_pretrained.tar) | 78.95% | 94.42% | 30.064 | 19.963 |
+|[HRNet_W64_C](https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W64_C_pretrained.tar) | 79.30% | 94.61% | 38.921 | 24.742 |
 
 ## FAQ