diff --git a/slim/distillation/README.md b/slim/distillation/README.md
index fee4e96256c02f2ce16e0aa77f277e169fad24c8..90d1f28c3ea43d01164fd497d46768112d6987db 100644
--- a/slim/distillation/README.md
+++ b/slim/distillation/README.md
@@ -69,7 +69,10 @@ distill_loss = l2_loss('teacher_bilinear_interp_2.tmp_0', 'bilinear_interp_0.tmp
 在该脚本中定义了teacher_model和student_model，用teacher_model的输出指导student_model的训练
 
 ### 执行示例
-如下命令启动训练，每间隔```cfg.TRAIN.SNAPSHOT_EPOCH```会进行一次评估。
+
+下载teacher的预训练模型和student的预训练模型, 替换如下命令中的```your_tearcher_pretrained_model_path```和```your_student_pretrained_model```
+
+执行如下命令启动训练，每间隔```cfg.TRAIN.SNAPSHOT_EPOCH```会进行一次评估。
 ```shell
 CUDA_VISIBLE_DEVICES=0,1 
 python -m paddle.distributed.launch ./slim/distillation/train_distill.py \
@@ -77,7 +80,9 @@ python -m paddle.distributed.launch ./slim/distillation/train_distill.py \
 --teacher_cfg ./slim/distillation/cityscape_teacher.yaml \
 --use_gpu \
 --use_mpio \
---do_eval
+--do_eval \
+SLIM.KNOWLEDGE_DISTILL_TEACHER_MODEL_DIR your_tearcher_pretrained_model_path \
+TRAIN.PRETRAINED_MODEL_DIR your_student_pretrained_model
 ```
 
 ## 评估预测
diff --git a/slim/distillation/cityscape.yaml b/slim/distillation/cityscape.yaml
index b4adddc08d2ea2eb739c7a4401f4f00e9298714e..703a6a2483fcf68f9ea801369ff0675c41ad286c 100644
--- a/slim/distillation/cityscape.yaml
+++ b/slim/distillation/cityscape.yaml
@@ -49,7 +49,7 @@ TEST:
     TEST_MODEL: "snapshots/cityscape_v5/final/"
 TRAIN:
     MODEL_SAVE_DIR: "snapshots/cityscape_mbv2_kd_e100_1/"
-    PRETRAINED_MODEL_DIR: u"/workspace/pretrained_models/mobilenet_cityscapes"
+    PRETRAINED_MODEL_DIR: u"pretrained_model/mobilenet_cityscapes"
     SNAPSHOT_EPOCH: 5
     SYNC_BATCH_NORM: True
 SOLVER:
diff --git a/slim/distillation/cityscape_teacher.yaml b/slim/distillation/cityscape_teacher.yaml
index 64e1a20f20a08513dd170aa2939777ae7a8d6ab2..ff7df807bbb782e4d5862f8963104f07fa147bb1 100644
--- a/slim/distillation/cityscape_teacher.yaml
+++ b/slim/distillation/cityscape_teacher.yaml
@@ -61,5 +61,5 @@ SOLVER:
 SLIM:
     KNOWLEDGE_DISTILL_IS_TEACHER: True
     KNOWLEDGE_DISTILL: True
-    KNOWLEDGE_DISTILL_TEACHER_MODEL_DIR: "/workspace/pretrained_models/xception65_bn_cityscapes"
+    KNOWLEDGE_DISTILL_TEACHER_MODEL_DIR: "pretrained_model/xception65_bn_cityscapes"