diff --git a/example/alexnet_cifar10/README.md b/example/alexnet_cifar10/README.md
index e6649e4055..f3333ccabd 100644
--- a/example/alexnet_cifar10/README.md
+++ b/example/alexnet_cifar10/README.md
@@ -39,7 +39,7 @@ epoch: 1 step: 1538, loss is 1.0221305
 Then, evaluate AlexNet according to network model
 ```python
 # evaluate AlexNet, 1 epoch training accuracy is up to 51.1%; 10 epoch training accuracy is up to 81.2%
-python eval.py --data_path cifar-10-verify-bin --mode test --ckpt_path checkpoint_alexnet-1_1562.ckpt
+python eval.py --data_path cifar-10-verify-bin --ckpt_path checkpoint_alexnet-1_1562.ckpt
 ```
 
 ## Note
diff --git a/example/lenet_mnist/README.md b/example/lenet_mnist/README.md
index 88c8769e05..750956e74b 100644
--- a/example/lenet_mnist/README.md
+++ b/example/lenet_mnist/README.md
@@ -44,7 +44,7 @@ epoch: 1 step: 1741, loss is 0.05018193
 Then, evaluate LeNet according to network model
 ```python
 # evaluate LeNet, after 1 epoch training, the accuracy is up to 96.5%
-python eval.py --data_path MNIST_Data --mode test --ckpt_path checkpoint_lenet-1_1875.ckpt
+python eval.py --data_path MNIST_Data --ckpt_path checkpoint_lenet-1_1875.ckpt
 ```
 
 ## Note