diff --git a/official/cv/resnet/README_CN.md b/official/cv/resnet/README_CN.md
index 77b3f560efc56a9d94744df9881dad8127cef39e..dcaa4ea345900c0717f773d85e6316c6b3d928e6 100644
--- a/official/cv/resnet/README_CN.md
+++ b/official/cv/resnet/README_CN.md
@@ -453,16 +453,20 @@ bash run_parameter_server_train_gpu.sh [DATASET_PATH] [CONFIG_PATH] [PRETRAINED_
 
 ```bash
 # Ascend 鍒嗗竷寮忚缁冩椂鎺ㄧ悊绀轰緥:
+cd scripts/
 bash run_distribute_train.sh [RANK_TABLE_FILE] [DATASET_PATH] [CONFIG_PATH] [RUN_EVAL](optional) [EVAL_DATASET_PATH](optional)
 
 # Ascend 鍗曟満璁粌鏃舵帹鐞嗙ず渚�:
-bash run_standalone_train.sh [RANK_TABLE_FILE] [DATASET_PATH] [CONFIG_PATH] [RUN_EVAL](optional) [EVAL_DATASET_PATH](optional)
+cd scripts/
+bash run_standalone_train.sh [DATASET_PATH] [CONFIG_PATH] [RUN_EVAL](optional) [EVAL_DATASET_PATH](optional)
 
 # GPU 鍒嗗竷寮忚缁冩椂鎺ㄧ悊绀轰緥:
-bash run_distribute_train_gpu.sh [CONFIG_PATH] [RUN_EVAL](optional) [EVAL_DATASET_PATH](optional)
+cd scripts/
+bash run_distribute_train_gpu.sh [DATASET_PATH] [CONFIG_PATH] [RUN_EVAL](optional) [EVAL_DATASET_PATH](optional)
 
 # GPU 鍗曟満璁粌鏃舵帹鐞嗙ず渚�:
-bash run_standalone_train_gpu.sh [CONFIG_PATH] [RUN_EVAL](optional) [EVAL_DATASET_PATH](optional)
+cd scripts/
+bash run_standalone_train_gpu.sh [DATASET_PATH] [CONFIG_PATH] [RUN_EVAL](optional) [EVAL_DATASET_PATH](optional)
 ```
 
 璁粌鏃舵帹鐞嗛渶瑕佸湪璁剧疆`RUN_EVAL`涓篢rue锛屼笌姝ゅ悓鏃惰繕闇€瑕佽缃甡EVAL_DATASET_PATH`銆傛澶栵紝褰撹缃甡RUN_EVAL`涓篢rue鏃惰繕鍙负python鑴氭湰璁剧疆`save_best_ckpt`, `eval_start_epoch`, `eval_interval`绛夊弬鏁般€�
diff --git a/research/cv/RCAN/src/rcan_model.py b/research/cv/RCAN/src/rcan_model.py
index 0fd5020768cfc18ef43945bcb4557f2fb31270f7..6ffbf6680aa9513e1485e2715fbf3f1a77332b02 100644
--- a/research/cv/RCAN/src/rcan_model.py
+++ b/research/cv/RCAN/src/rcan_model.py
@@ -86,11 +86,12 @@ class Upsampler(nn.Cell):
         """rcan"""
         super(Upsampler, self).__init__()
         m = []
-        if (scale & (scale - 1)) == 0:
-            for _ in range(int(math.log(scale, 2))):
-                m.append(SmallUpSampler(conv, 2, n_feats, has_bias=has_bias))
-        elif scale == 3:
-            m.append(SmallUpSampler(conv, 3, n_feats, has_bias=has_bias))
+        for s in scale:
+            if (s & (s - 1)) == 0:
+                for _ in range(int(math.log(s, 2))):
+                    m.append(SmallUpSampler(conv, 2, n_feats, has_bias=has_bias))
+            elif s == 3:
+                m.append(SmallUpSampler(conv, 3, n_feats, has_bias=has_bias))
         self.net = nn.SequentialCell(m)
 
     def construct(self, x):