diff --git a/x2paddle/decoder/caffe_decoder.py b/x2paddle/decoder/caffe_decoder.py
index 33b203cebb71eb16675e884b095d508596fcd57c..fee1abd017b6723548d133af0cb42a06f36bf965 100644
--- a/x2paddle/decoder/caffe_decoder.py
+++ b/x2paddle/decoder/caffe_decoder.py
@@ -246,9 +246,14 @@ class CaffeDecoder(object):
                 if layer.type == 'PReLU':
                     c_o, c_i, h, w = map(int, [1] + \
                         list(dims) + [1]* (3 - len(dims)))
+                elif layer.type == 'Normalize':
+                    data = np.asarray(list(blob.data), dtype=np.float32)
+                    transformed.append(data)
+                    continue
                 else:
                     c_o, c_i, h, w = map(int, [1] * (4 - len(dims)) \
                         + list(dims))
+
             else:
                 c_o = blob.num
                 c_i = blob.channels
diff --git a/x2paddle/op_mapper/caffe_custom_layer/normalize.py b/x2paddle/op_mapper/caffe_custom_layer/normalize.py
index a63dc62cf9b9fc0dcd0badb5b189e66cbc7e0cd3..577a674f7e70aebee78735611c11e7202b2ccf7e 100644
--- a/x2paddle/op_mapper/caffe_custom_layer/normalize.py
+++ b/x2paddle/op_mapper/caffe_custom_layer/normalize.py
@@ -12,16 +12,14 @@ def normalize_layer(inputs,
                     input_shape=None,
                     name=None):
     assert across_spatial == False, "Only support across_spatial == False for Normalize"
-
     input = inputs[0]
     l2_norm = fluid.layers.l2_normalize(input, axis=1, name=name + '_l2')
     scale_param = fluid.layers.create_parameter(
-        shape=[1]
-        if channel_shared else [input_shape[0][0], 1, 1, input_shape[0][1]],
+        shape=[1] if channel_shared else [input_shape[0][1]],
         dtype=input.dtype,
         attr=name + '_scale')
     scale_param = fluid.layers.reshape(x=scale_param, \
-                  shape=[1] if channel_shared else [input_shape[0][0], 1, 1, input_shape[0][1]])
+                  shape=[1] if channel_shared else [input_shape[0][1]])
     out = fluid.layers.elementwise_mul(x=l2_norm,
                                        y=scale_param,
                                        axis=-1 if channel_shared else 1)