diff --git a/paddle/fluid/operators/norm_op.h b/paddle/fluid/operators/norm_op.h
index 6c95d3f3bf3a3b0448a8f39915f8b025f7d3bd46..f81cbc2c733af2a42f27e2ecb05ee2f8e2f8c17b 100644
--- a/paddle/fluid/operators/norm_op.h
+++ b/paddle/fluid/operators/norm_op.h
@@ -99,10 +99,10 @@ class NormGradKernel : public framework::OpKernel<T> {
     auto dx_e = framework::EigenVector<T>::Flatten(*out_dx);
 
     Eigen::DSizes<int, 3> shape(pre, n, post);
-    Eigen::DSizes<int, 2> norm_shape(pre, post);
+    Eigen::DSizes<int, 3> rshape(pre, 1, post);
     auto x = x_e.reshape(shape);
     auto dy = dy_e.reshape(shape);
-    auto norm = norm_e.reshape(norm_shape);
+    auto norm = norm_e.reshape(rshape);
     auto dx = dx_e.reshape(shape);
 
     framework::Tensor rsum;
@@ -111,7 +111,6 @@ class NormGradKernel : public framework::OpKernel<T> {
 
     Eigen::DSizes<int, 1> rdim(1);
     Eigen::DSizes<int, 3> bcast(1, n, 1);
-    Eigen::DSizes<int, 3> rshape(pre, 1, post);
 
     // dx = ( dy/sqrt(sum(x*x)) ) * [1 - x*sum(x) / (sum(x*x) + e)]
     //    = [dy - dy * x * sum(x) / (sum(x*x) + e)] / sqrt(sum(x*x))
diff --git a/python/paddle/fluid/tests/unittests/test_eager_deletion_transformer.py b/python/paddle/fluid/tests/unittests/test_eager_deletion_transformer.py
index 754d5fd40953311a5deb466fa42216f72671a65a..603c8e74885d2a050e6e1e3101dce880b6eabe9c 100644
--- a/python/paddle/fluid/tests/unittests/test_eager_deletion_transformer.py
+++ b/python/paddle/fluid/tests/unittests/test_eager_deletion_transformer.py
@@ -16,12 +16,10 @@ import os
 import unittest
 os.environ['FLAGS_eager_delete_tensor_gb'] = "0.0"
 
-from test_parallel_executor_transformer import TestTransformer
-
-
-class EagerDeletionTestTransformer(TestTransformer):
-    pass
+os.environ[
+    'RECORDIO_FILENAME'] = '/tmp/eager_deletion_transformer.wmt16.recordio'
 
+from test_parallel_executor_transformer import TestTransformer
 
 if __name__ == '__main__':
     unittest.main()
diff --git a/python/paddle/fluid/tests/unittests/test_parallel_executor_transformer.py b/python/paddle/fluid/tests/unittests/test_parallel_executor_transformer.py
index 3827743908c1d76931572277323d1dd5ddd05523..aacc1c3ecda8c25dec9f08827a856d38c37b1b2f 100644
--- a/python/paddle/fluid/tests/unittests/test_parallel_executor_transformer.py
+++ b/python/paddle/fluid/tests/unittests/test_parallel_executor_transformer.py
@@ -24,7 +24,7 @@ import paddle.fluid.core as core
 import paddle.dataset.wmt16 as wmt16
 import os
 
-WMT16_RECORDIO_FILE = "/tmp/wmt16.recordio"
+WMT16_RECORDIO_FILE = os.environ.get('RECORDIO_FILENAME', '/tmp/wmt16.recordio')
 
 
 class ModelHyperParams(object):
diff --git a/python/paddle/fluid/tests/unittests/transformer_model.py b/python/paddle/fluid/tests/unittests/transformer_model.py
index 143d187edc3a154418f9e639b7d492c8ce994d42..905b7d6fe75ab0080e3e97fbd4710ad913a05a38 100644
--- a/python/paddle/fluid/tests/unittests/transformer_model.py
+++ b/python/paddle/fluid/tests/unittests/transformer_model.py
@@ -17,6 +17,7 @@ from __future__ import print_function
 from functools import partial
 import numpy as np
 
+import os
 import paddle.fluid as fluid
 import paddle.fluid.layers as layers
 from paddle.fluid.layers.io import open_recordio_file
@@ -408,7 +409,7 @@ def transformer(
         trg_pad_idx,
         pos_pad_idx, ):
     file_obj = open_recordio_file(
-        filename='/tmp/wmt16.recordio',
+        filename=os.environ.get('RECORDIO_FILENAME', '/tmp/wmt16.recordio'),
         shapes=[
             [batch_size * max_length, 1],
             [batch_size * max_length, 1],