diff --git a/demo/auto_prune/train.py b/demo/auto_prune/train.py
index d65dd875a8d650b57bbe429514e99dc6fa46e630..ff55a54597ce7e923764f9e6f8dff232d2d28658 100644
--- a/demo/auto_prune/train.py
+++ b/demo/auto_prune/train.py
@@ -116,8 +116,8 @@ def compress(args):
 
         fluid.io.load_vars(exe, args.pretrained_model, predicate=if_exist)
 
-    val_reader = paddle.batch(val_reader, batch_size=args.batch_size)
-    train_reader = paddle.batch(
+    val_reader = paddle.fluid.io.batch(val_reader, batch_size=args.batch_size)
+    train_reader = paddle.fluid.io.batch(
         train_reader, batch_size=args.batch_size, drop_last=True)
 
     train_feeder = feeder = fluid.DataFeeder([image, label], place)
diff --git a/demo/auto_prune/train_finetune.py b/demo/auto_prune/train_finetune.py
index 6508f435bb52cfc0421c77bc0c893bff7f315d03..0dcb56bfe7988475cc7c63ebde257897456bfb22 100644
--- a/demo/auto_prune/train_finetune.py
+++ b/demo/auto_prune/train_finetune.py
@@ -34,12 +34,12 @@ add_arg('config_file',      str, None,                 "The config file for comp
 
 model_list = [m for m in dir(models) if "__" not in m]
 ratiolist = [
-#    [0.06, 0.0, 0.09, 0.03, 0.09, 0.02, 0.05, 0.03, 0.0, 0.07, 0.07, 0.05, 0.08],
-#    [0.08, 0.02, 0.03, 0.13, 0.1, 0.06, 0.03, 0.04, 0.14, 0.02, 0.03, 0.02, 0.01],
-        ]
+    #    [0.06, 0.0, 0.09, 0.03, 0.09, 0.02, 0.05, 0.03, 0.0, 0.07, 0.07, 0.05, 0.08],
+    #    [0.08, 0.02, 0.03, 0.13, 0.1, 0.06, 0.03, 0.04, 0.14, 0.02, 0.03, 0.02, 0.01],
+]
 
 
-def save_model(args, exe, train_prog, eval_prog,info):
+def save_model(args, exe, train_prog, eval_prog, info):
     model_path = os.path.join(args.model_save_dir, args.model, str(info))
     if not os.path.isdir(model_path):
         os.makedirs(model_path)
@@ -58,29 +58,31 @@ def piecewise_decay(args):
         regularization=fluid.regularizer.L2Decay(args.l2_decay))
     return optimizer
 
+
 def cosine_decay(args):
     step = int(math.ceil(float(args.total_images) / args.batch_size))
     learning_rate = fluid.layers.cosine_decay(
-        learning_rate=args.lr,
-        step_each_epoch=step,
-        epochs=args.num_epochs)
+        learning_rate=args.lr, step_each_epoch=step, epochs=args.num_epochs)
     optimizer = fluid.optimizer.Momentum(
         learning_rate=learning_rate,
         momentum=args.momentum_rate,
         regularization=fluid.regularizer.L2Decay(args.l2_decay))
     return optimizer
 
+
 def create_optimizer(args):
     if args.lr_strategy == "piecewise_decay":
         return piecewise_decay(args)
     elif args.lr_strategy == "cosine_decay":
         return cosine_decay(args)
 
+
 def compress(args):
-    class_dim=1000
-    image_shape="3,224,224"
+    class_dim = 1000
+    image_shape = "3,224,224"
     image_shape = [int(m) for m in image_shape.split(",")]
-    assert args.model in model_list, "{} is not in lists: {}".format(args.model, model_list)
+    assert args.model in model_list, "{} is not in lists: {}".format(
+        args.model, model_list)
     image = fluid.layers.data(name='image', shape=image_shape, dtype='float32')
     label = fluid.layers.data(name='label', shape=[1], dtype='int64')
     # model definition
@@ -98,18 +100,22 @@ def compress(args):
     exe.run(fluid.default_startup_program())
 
     if args.pretrained_model:
+
         def if_exist(var):
-            exist =  os.path.exists(os.path.join(args.pretrained_model, var.name))
-            print("exist",exist)
+            exist = os.path.exists(
+                os.path.join(args.pretrained_model, var.name))
+            print("exist", exist)
             return exist
+
         #fluid.io.load_vars(exe, args.pretrained_model, predicate=if_exist)
 
-    val_reader = paddle.batch(reader.val(), batch_size=args.batch_size)
-    train_reader = paddle.batch(
+    val_reader = paddle.fluid.io.batch(reader.val(), batch_size=args.batch_size)
+    train_reader = paddle.fluid.io.batch(
         reader.train(), batch_size=args.batch_size, drop_last=True)
 
     train_feeder = feeder = fluid.DataFeeder([image, label], place)
-    val_feeder = feeder = fluid.DataFeeder([image, label], place, program=val_program)
+    val_feeder = feeder = fluid.DataFeeder(
+        [image, label], place, program=val_program)
 
     def test(epoch, program):
         batch_id = 0
@@ -117,80 +123,99 @@ def compress(args):
         acc_top5_ns = []
         for data in val_reader():
             start_time = time.time()
-            acc_top1_n, acc_top5_n = exe.run(program,
-                                           feed=train_feeder.feed(data),
-                                           fetch_list=[acc_top1.name, acc_top5.name])
+            acc_top1_n, acc_top5_n = exe.run(
+                program,
+                feed=train_feeder.feed(data),
+                fetch_list=[acc_top1.name, acc_top5.name])
             end_time = time.time()
-            print("Eval epoch[{}] batch[{}] - acc_top1: {}; acc_top5: {}; time: {}".format(epoch, batch_id, np.mean(acc_top1_n), np.mean(acc_top5_n), end_time-start_time))
+            print(
+                "Eval epoch[{}] batch[{}] - acc_top1: {}; acc_top5: {}; time: {}".
+                format(epoch, batch_id,
+                       np.mean(acc_top1_n),
+                       np.mean(acc_top5_n), end_time - start_time))
             acc_top1_ns.append(np.mean(acc_top1_n))
             acc_top5_ns.append(np.mean(acc_top5_n))
             batch_id += 1
 
-        print("Final eval epoch[{}] - acc_top1: {}; acc_top5: {}".format(epoch, np.mean(np.array(acc_top1_ns)), np.mean(np.array(acc_top5_ns))))
-
+        print("Final eval epoch[{}] - acc_top1: {}; acc_top5: {}".format(
+            epoch,
+            np.mean(np.array(acc_top1_ns)), np.mean(np.array(acc_top5_ns))))
 
     def train(epoch, program):
 
         build_strategy = fluid.BuildStrategy()
         exec_strategy = fluid.ExecutionStrategy()
         train_program = fluid.compiler.CompiledProgram(
-                                   program).with_data_parallel(
-                                   loss_name=avg_cost.name,
-                                   build_strategy=build_strategy,
-                                   exec_strategy=exec_strategy)
+            program).with_data_parallel(
+                loss_name=avg_cost.name,
+                build_strategy=build_strategy,
+                exec_strategy=exec_strategy)
 
         batch_id = 0
         for data in train_reader():
             start_time = time.time()
-            loss_n, acc_top1_n, acc_top5_n,lr_n = exe.run(train_program,
-                                               feed=train_feeder.feed(data),
-                                               fetch_list=[avg_cost.name, acc_top1.name, acc_top5.name,"learning_rate"])
+            loss_n, acc_top1_n, acc_top5_n, lr_n = exe.run(
+                train_program,
+                feed=train_feeder.feed(data),
+                fetch_list=[
+                    avg_cost.name, acc_top1.name, acc_top5.name,
+                    "learning_rate"
+                ])
             end_time = time.time()
             loss_n = np.mean(loss_n)
             acc_top1_n = np.mean(acc_top1_n)
             acc_top5_n = np.mean(acc_top5_n)
             lr_n = np.mean(lr_n)
-            print("epoch[{}]-batch[{}] - loss: {}; acc_top1: {}; acc_top5: {};lrn: {}; time: {}".format(epoch, batch_id, loss_n, acc_top1_n, acc_top5_n, lr_n,end_time-start_time))
+            print(
+                "epoch[{}]-batch[{}] - loss: {}; acc_top1: {}; acc_top5: {};lrn: {}; time: {}".
+                format(epoch, batch_id, loss_n, acc_top1_n, acc_top5_n, lr_n,
+                       end_time - start_time))
             batch_id += 1
 
     params = []
     for param in fluid.default_main_program().global_block().all_parameters():
         #if "_weights" in  param.name and "conv1_weights" not in param.name:
-        if "_sep_weights" in  param.name:
+        if "_sep_weights" in param.name:
             params.append(param.name)
-    print("fops before pruning: {}".format(flops(fluid.default_main_program())))
+    print("fops before pruning: {}".format(
+        flops(fluid.default_main_program())))
     pruned_program_iter = fluid.default_main_program()
     pruned_val_program_iter = val_program
     for ratios in ratiolist:
         pruner = Pruner()
-        pruned_val_program_iter = pruner.prune(pruned_val_program_iter,
-                                  fluid.global_scope(),
-                                  params=params,
-                                  ratios=ratios,
-                                  place=place,
-                                  only_graph=True)
-
-
-        pruned_program_iter = pruner.prune(pruned_program_iter,
-                                  fluid.global_scope(),
-                                  params=params,
-                                  ratios=ratios,
-                                  place=place)
+        pruned_val_program_iter = pruner.prune(
+            pruned_val_program_iter,
+            fluid.global_scope(),
+            params=params,
+            ratios=ratios,
+            place=place,
+            only_graph=True)
+
+        pruned_program_iter = pruner.prune(
+            pruned_program_iter,
+            fluid.global_scope(),
+            params=params,
+            ratios=ratios,
+            place=place)
         print("fops after pruning: {}".format(flops(pruned_program_iter)))
-
     """ do not inherit learning rate """
-    if(os.path.exists(args.pretrained_model + "/learning_rate")):
-      os.remove( args.pretrained_model + "/learning_rate")
-    if(os.path.exists(args.pretrained_model + "/@LR_DECAY_COUNTER@")):
-      os.remove( args.pretrained_model + "/@LR_DECAY_COUNTER@")
-    fluid.io.load_vars(exe, args.pretrained_model , main_program = pruned_program_iter,  predicate=if_exist)
+    if (os.path.exists(args.pretrained_model + "/learning_rate")):
+        os.remove(args.pretrained_model + "/learning_rate")
+    if (os.path.exists(args.pretrained_model + "/@LR_DECAY_COUNTER@")):
+        os.remove(args.pretrained_model + "/@LR_DECAY_COUNTER@")
+    fluid.io.load_vars(
+        exe,
+        args.pretrained_model,
+        main_program=pruned_program_iter,
+        predicate=if_exist)
 
     pruned_program = pruned_program_iter
     pruned_val_program = pruned_val_program_iter
     for i in range(args.num_epochs):
         train(i, pruned_program)
         test(i, pruned_val_program)
-        save_model(args,exe,pruned_program,pruned_val_program,i)
+        save_model(args, exe, pruned_program, pruned_val_program, i)
+
 
 def main():
     args = parser.parse_args()
diff --git a/demo/auto_prune/train_iterator.py b/demo/auto_prune/train_iterator.py
index b30531ea9b7e7247fe44db958f1dd08759580cfb..8b7ca07f768e661476a5943dbc623291a37f939a 100644
--- a/demo/auto_prune/train_iterator.py
+++ b/demo/auto_prune/train_iterator.py
@@ -41,9 +41,10 @@ add_arg('test_period',      int, 10,                 "Test period in epoches.")
 
 model_list = [m for m in dir(models) if "__" not in m]
 ratiolist = [
-#    [0.06, 0.0, 0.09, 0.03, 0.09, 0.02, 0.05, 0.03, 0.0, 0.07, 0.07, 0.05, 0.08],
-#    [0.08, 0.02, 0.03, 0.13, 0.1, 0.06, 0.03, 0.04, 0.14, 0.02, 0.03, 0.02, 0.01],
-        ]
+    #    [0.06, 0.0, 0.09, 0.03, 0.09, 0.02, 0.05, 0.03, 0.0, 0.07, 0.07, 0.05, 0.08],
+    #    [0.08, 0.02, 0.03, 0.13, 0.1, 0.06, 0.03, 0.04, 0.14, 0.02, 0.03, 0.02, 0.01],
+]
+
 
 def piecewise_decay(args):
     step = int(math.ceil(float(args.total_images) / args.batch_size))
@@ -121,8 +122,8 @@ def compress(args):
 
 #        fluid.io.load_vars(exe, args.pretrained_model, predicate=if_exist)
 
-    val_reader = paddle.batch(val_reader, batch_size=args.batch_size)
-    train_reader = paddle.batch(
+    val_reader = paddle.fluid.io.batch(val_reader, batch_size=args.batch_size)
+    train_reader = paddle.fluid.io.batch(
         train_reader, batch_size=args.batch_size, drop_last=True)
 
     train_feeder = feeder = fluid.DataFeeder([image, label], place)
@@ -194,21 +195,26 @@ def compress(args):
 
     for ratios in ratiolist:
         pruner = Pruner()
-        pruned_val_program_iter = pruner.prune(pruned_val_program_iter,
-                                  fluid.global_scope(),
-                                  params=params,
-                                  ratios=ratios,
-                                  place=place,
-                                  only_graph=True)
-
-
-        pruned_program_iter = pruner.prune(pruned_program_iter,
-                                  fluid.global_scope(),
-                                  params=params,
-                                  ratios=ratios,
-                                  place=place)
+        pruned_val_program_iter = pruner.prune(
+            pruned_val_program_iter,
+            fluid.global_scope(),
+            params=params,
+            ratios=ratios,
+            place=place,
+            only_graph=True)
+
+        pruned_program_iter = pruner.prune(
+            pruned_program_iter,
+            fluid.global_scope(),
+            params=params,
+            ratios=ratios,
+            place=place)
         print("fops after pruning: {}".format(flops(pruned_program_iter)))
-    fluid.io.load_vars(exe, args.pretrained_model , main_program = pruned_program_iter,  predicate=if_exist)
+    fluid.io.load_vars(
+        exe,
+        args.pretrained_model,
+        main_program=pruned_program_iter,
+        predicate=if_exist)
 
     pruner = AutoPruner(
         pruned_val_program_iter,
@@ -238,8 +244,6 @@ def compress(args):
         pruner.reward(score)
 
 
-
-
 def main():
     args = parser.parse_args()
     print_arguments(args)
diff --git a/demo/distillation/distill.py b/demo/distillation/distill.py
index 3bafa159ea95690198f34e62707caf53f64d0bf6..f1b2be691ff34f4765568de342d008e7d2657ff6 100644
--- a/demo/distillation/distill.py
+++ b/demo/distillation/distill.py
@@ -133,9 +133,9 @@ def compress(args):
     place = fluid.CUDAPlace(0) if args.use_gpu else fluid.CPUPlace()
     exe = fluid.Executor(place)
 
-    train_reader = paddle.batch(
+    train_reader = paddle.fluid.io.batch(
         train_reader, batch_size=args.batch_size, drop_last=True)
-    val_reader = paddle.batch(
+    val_reader = paddle.fluid.io.batch(
         val_reader, batch_size=args.batch_size, drop_last=True)
     val_program = student_program.clone(for_test=True)
 
diff --git a/demo/distillation/image_classification_distillation_tutorial.ipynb b/demo/distillation/image_classification_distillation_tutorial.ipynb
index 28c1de23050fd1944401c095304dba4674aa965b..e1d679cdabaafc3eb71a5382dff1da0946b0b799 100644
--- a/demo/distillation/image_classification_distillation_tutorial.ipynb
+++ b/demo/distillation/image_classification_distillation_tutorial.ipynb
@@ -165,7 +165,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "train_reader = paddle.batch(\n",
+    "train_reader = paddle.fluid.io.batch(\n",
     "    paddle.dataset.mnist.train(), batch_size=128, drop_last=True)\n",
     "train_feeder = fluid.DataFeeder(['image', 'label'], fluid.CPUPlace(), student_program)"
    ]
diff --git a/demo/nas/block_sa_nas_mobilenetv2.py b/demo/nas/block_sa_nas_mobilenetv2.py
index e4572583736e650235a1832faed82f01ba72b754..a32f97b0b8bb5b7bbe20fa0842e94ad58ff9751d 100644
--- a/demo/nas/block_sa_nas_mobilenetv2.py
+++ b/demo/nas/block_sa_nas_mobilenetv2.py
@@ -137,22 +137,22 @@ def search_mobilenetv2_block(config, args, image_size):
         exe.run(startup_program)
 
         if args.data == 'cifar10':
-            train_reader = paddle.batch(
+            train_reader = paddle.fluid.io.batch(
                 paddle.reader.shuffle(
                     paddle.dataset.cifar.train10(cycle=False), buf_size=1024),
                 batch_size=args.batch_size,
                 drop_last=True)
 
-            test_reader = paddle.batch(
+            test_reader = paddle.fluid.io.batch(
                 paddle.dataset.cifar.test10(cycle=False),
                 batch_size=args.batch_size,
                 drop_last=False)
         elif args.data == 'imagenet':
-            train_reader = paddle.batch(
+            train_reader = paddle.fluid.io.batch(
                 imagenet_reader.train(),
                 batch_size=args.batch_size,
                 drop_last=True)
-            test_reader = paddle.batch(
+            test_reader = paddle.fluid.io.batch(
                 imagenet_reader.val(),
                 batch_size=args.batch_size,
                 drop_last=False)
diff --git a/demo/nas/image_classification_nas_quick_start.ipynb b/demo/nas/image_classification_nas_quick_start.ipynb
index 78d07117b6fd37111d8697195b010da0d485bf69..72f04cf848b8caec65b65b177c99d15ebfa05cc6 100644
--- a/demo/nas/image_classification_nas_quick_start.ipynb
+++ b/demo/nas/image_classification_nas_quick_start.ipynb
@@ -114,9 +114,9 @@
     "    if current_flops > 321208544:\n",
     "        continue\n",
     "    \n",
-    "    train_reader = paddle.batch(paddle.reader.shuffle(paddle.dataset.cifar.train10(cycle=False),                          buf_size=1024),batch_size=256)\n",
+    "    train_reader = paddle.fluid.io.batch(paddle.reader.shuffle(paddle.dataset.cifar.train10(cycle=False),                          buf_size=1024),batch_size=256)\n",
     "    train_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())\n",
-    "    test_reader = paddle.batch(paddle.dataset.cifar.test10(cycle=False),\n",
+    "    test_reader = paddle.fluid.io.batch(paddle.dataset.cifar.test10(cycle=False),\n",
     "               batch_size=256)\n",
     "    test_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())\n",
     "\n",
@@ -160,4 +160,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 2
-}
\ No newline at end of file
+}
diff --git a/demo/nas/parl_nas_mobilenetv2.py b/demo/nas/parl_nas_mobilenetv2.py
index 1d698742cde532c8c3b2b1fb03183a783e2b15da..ef9195fb2dbb8ddf34ce574e4e6c823d1e0b790e 100644
--- a/demo/nas/parl_nas_mobilenetv2.py
+++ b/demo/nas/parl_nas_mobilenetv2.py
@@ -105,22 +105,22 @@ def search_mobilenetv2(config, args, image_size, is_server=True):
         exe.run(startup_program)
 
         if args.data == 'cifar10':
-            train_reader = paddle.batch(
+            train_reader = paddle.fluid.io.batch(
                 paddle.reader.shuffle(
                     paddle.dataset.cifar.train10(cycle=False), buf_size=1024),
                 batch_size=args.batch_size,
                 drop_last=True)
 
-            test_reader = paddle.batch(
+            test_reader = paddle.fluid.io.batch(
                 paddle.dataset.cifar.test10(cycle=False),
                 batch_size=args.batch_size,
                 drop_last=False)
         elif args.data == 'imagenet':
-            train_reader = paddle.batch(
+            train_reader = paddle.fluid.io.batch(
                 imagenet_reader.train(),
                 batch_size=args.batch_size,
                 drop_last=True)
-            test_reader = paddle.batch(
+            test_reader = paddle.fluid.io.batch(
                 imagenet_reader.val(),
                 batch_size=args.batch_size,
                 drop_last=False)
diff --git a/demo/nas/rl_nas_mobilenetv2.py b/demo/nas/rl_nas_mobilenetv2.py
index 3eb562334120b5baaa118a6baa1718767eb91015..4997a530ea1549f4afb4fb7d7fa51ab7115f2b65 100644
--- a/demo/nas/rl_nas_mobilenetv2.py
+++ b/demo/nas/rl_nas_mobilenetv2.py
@@ -109,22 +109,22 @@ def search_mobilenetv2(config, args, image_size, is_server=True):
         exe.run(startup_program)
 
         if args.data == 'cifar10':
-            train_reader = paddle.batch(
+            train_reader = paddle.fluid.io.batch(
                 paddle.reader.shuffle(
                     paddle.dataset.cifar.train10(cycle=False), buf_size=1024),
                 batch_size=args.batch_size,
                 drop_last=True)
 
-            test_reader = paddle.batch(
+            test_reader = paddle.fluid.io.batch(
                 paddle.dataset.cifar.test10(cycle=False),
                 batch_size=args.batch_size,
                 drop_last=False)
         elif args.data == 'imagenet':
-            train_reader = paddle.batch(
+            train_reader = paddle.fluid.io.batch(
                 imagenet_reader.train(),
                 batch_size=args.batch_size,
                 drop_last=True)
-            test_reader = paddle.batch(
+            test_reader = paddle.fluid.io.batch(
                 imagenet_reader.val(),
                 batch_size=args.batch_size,
                 drop_last=False)
diff --git a/demo/nas/sa_nas_mobilenetv2.py b/demo/nas/sa_nas_mobilenetv2.py
index 9ef26bc5d1d75a10cd8ebf7183bb70b8dbd2b354..da6f17548a0881aa325524c513c048324641210d 100644
--- a/demo/nas/sa_nas_mobilenetv2.py
+++ b/demo/nas/sa_nas_mobilenetv2.py
@@ -102,22 +102,22 @@ def search_mobilenetv2(config, args, image_size, is_server=True):
         exe.run(startup_program)
 
         if args.data == 'cifar10':
-            train_reader = paddle.batch(
+            train_reader = paddle.fluid.io.batch(
                 paddle.reader.shuffle(
                     paddle.dataset.cifar.train10(cycle=False), buf_size=1024),
                 batch_size=args.batch_size,
                 drop_last=True)
 
-            test_reader = paddle.batch(
+            test_reader = paddle.fluid.io.batch(
                 paddle.dataset.cifar.test10(cycle=False),
                 batch_size=args.batch_size,
                 drop_last=False)
         elif args.data == 'imagenet':
-            train_reader = paddle.batch(
+            train_reader = paddle.fluid.io.batch(
                 imagenet_reader.train(),
                 batch_size=args.batch_size,
                 drop_last=True)
-            test_reader = paddle.batch(
+            test_reader = paddle.fluid.io.batch(
                 imagenet_reader.val(),
                 batch_size=args.batch_size,
                 drop_last=False)
@@ -197,22 +197,22 @@ def test_search_result(tokens, image_size, args, config):
     exe.run(startup_program)
 
     if args.data == 'cifar10':
-        train_reader = paddle.batch(
+        train_reader = paddle.fluid.io.batch(
             paddle.reader.shuffle(
                 paddle.dataset.cifar.train10(cycle=False), buf_size=1024),
             batch_size=args.batch_size,
             drop_last=True)
 
-        test_reader = paddle.batch(
+        test_reader = paddle.fluid.io.batch(
             paddle.dataset.cifar.test10(cycle=False),
             batch_size=args.batch_size,
             drop_last=False)
     elif args.data == 'imagenet':
-        train_reader = paddle.batch(
+        train_reader = paddle.fluid.io.batch(
             imagenet_reader.train(),
             batch_size=args.batch_size,
             drop_last=True)
-        test_reader = paddle.batch(
+        test_reader = paddle.fluid.io.batch(
             imagenet_reader.val(), batch_size=args.batch_size, drop_last=False)
 
     train_loader.set_sample_list_generator(
diff --git a/demo/one_shot/train.py b/demo/one_shot/train.py
index e9904e45143f879bd6d1019dc6402898780173b1..5e8267ff66f37f5b24807eb86c3bdad7182de2b7 100644
--- a/demo/one_shot/train.py
+++ b/demo/one_shot/train.py
@@ -113,7 +113,7 @@ def test_mnist(model, tokens=None):
     acc_set = []
     avg_loss_set = []
     batch_size = 64
-    test_reader = paddle.batch(
+    test_reader = paddle.fluid.io.batch(
         paddle.dataset.mnist.test(), batch_size=batch_size, drop_last=True)
     for batch_id, data in enumerate(test_reader()):
         dy_x_data = np.array([x[0].reshape(1, 28, 28)
@@ -145,7 +145,7 @@ def train_mnist(args, model, tokens=None):
     adam = AdamOptimizer(
         learning_rate=0.001, parameter_list=model.parameters())
 
-    train_reader = paddle.batch(
+    train_reader = paddle.fluid.io.batch(
         paddle.dataset.mnist.train(), batch_size=BATCH_SIZE, drop_last=True)
     if args.use_data_parallel:
         train_reader = fluid.contrib.reader.distributed_batch_reader(
diff --git a/demo/prune/eval.py b/demo/prune/eval.py
index 0cd2a9dc6049233104c412a532335e5dd6bf5c7f..b2c9ea26cbb2223c9cb0ee4bac0962680637f2db 100644
--- a/demo/prune/eval.py
+++ b/demo/prune/eval.py
@@ -63,7 +63,7 @@ def eval(args):
     exe = fluid.Executor(place)
     exe.run(fluid.default_startup_program())
 
-    val_reader = paddle.batch(val_reader, batch_size=args.batch_size)
+    val_reader = paddle.fluid.io.batch(val_reader, batch_size=args.batch_size)
 
     val_feeder = feeder = fluid.DataFeeder(
         [image, label], place, program=val_program)
diff --git a/demo/prune/image_classification_pruning_quick_start.ipynb b/demo/prune/image_classification_pruning_quick_start.ipynb
index 849fd8a67fa8478b28c9cea53017fddeec826b0f..670a2edf611629a9f33b694b59b24138b0bfdc56 100644
--- a/demo/prune/image_classification_pruning_quick_start.ipynb
+++ b/demo/prune/image_classification_pruning_quick_start.ipynb
@@ -161,7 +161,7 @@
    "outputs": [],
    "source": [
     "import paddle.dataset.mnist as reader\n",
-    "train_reader = paddle.batch(\n",
+    "train_reader = paddle.fluid.io.batch(\n",
     "        reader.train(), batch_size=128, drop_last=True)\n",
     "train_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())"
    ]
diff --git a/demo/prune/train.py b/demo/prune/train.py
index 231cda9cc183ede5f83bf4f51033d8d321fd1e1a..73e08756f34bd212db3b2239351cf9f8ce6962d9 100644
--- a/demo/prune/train.py
+++ b/demo/prune/train.py
@@ -142,8 +142,8 @@ def compress(args):
             args.pretrained_model))
         fluid.io.load_vars(exe, args.pretrained_model, predicate=if_exist)
 
-    val_reader = paddle.batch(val_reader, batch_size=args.batch_size)
-    train_reader = paddle.batch(
+    val_reader = paddle.fluid.io.batch(val_reader, batch_size=args.batch_size)
+    train_reader = paddle.fluid.io.batch(
         train_reader, batch_size=args.batch_size, drop_last=True)
 
     train_feeder = feeder = fluid.DataFeeder([image, label], place)
diff --git a/demo/quant/quant_aware/image_classification_training_aware_quantization_quick_start.ipynb b/demo/quant/quant_aware/image_classification_training_aware_quantization_quick_start.ipynb
index 495e3e1655074cffbb5a390c335ed47399d0968b..0c771cc096b26d79cc7d0b0b2aa87ff29bbce27f 100755
--- a/demo/quant/quant_aware/image_classification_training_aware_quantization_quick_start.ipynb
+++ b/demo/quant/quant_aware/image_classification_training_aware_quantization_quick_start.ipynb
@@ -81,9 +81,9 @@
    "outputs": [],
    "source": [
     "import paddle.dataset.mnist as reader\n",
-    "train_reader = paddle.batch(\n",
+    "train_reader = paddle.fluid.io.batch(\n",
     "        reader.train(), batch_size=128, drop_last=True)\n",
-    "test_reader = paddle.batch(\n",
+    "test_reader = paddle.fluid.io.batch(\n",
     "        reader.train(), batch_size=128, drop_last=True)\n",
     "train_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())"
    ]
diff --git a/demo/quant/quant_aware/train.py b/demo/quant/quant_aware/train.py
index 81016e2931a3bf66455e0528b99a573885549215..f8040a5917aa054fe248f69d83c1bc65fed64ed3 100644
--- a/demo/quant/quant_aware/train.py
+++ b/demo/quant/quant_aware/train.py
@@ -159,8 +159,8 @@ def compress(args):
 
         fluid.io.load_vars(exe, args.pretrained_model, predicate=if_exist)
 
-    val_reader = paddle.batch(val_reader, batch_size=args.batch_size)
-    train_reader = paddle.batch(
+    val_reader = paddle.fluid.io.batch(val_reader, batch_size=args.batch_size)
+    train_reader = paddle.fluid.io.batch(
         train_reader, batch_size=args.batch_size, drop_last=True)
 
     train_feeder = feeder = fluid.DataFeeder([image, label], place)
diff --git a/demo/quant/quant_post/eval.py b/demo/quant/quant_post/eval.py
index d7414b0973226425e9627137c185a39f26603fb9..c144fd1690ed55304cc722472cb155814bd26f64 100755
--- a/demo/quant/quant_post/eval.py
+++ b/demo/quant/quant_post/eval.py
@@ -46,7 +46,7 @@ def eval(args):
         exe,
         model_filename=args.model_name,
         params_filename=args.params_name)
-    val_reader = paddle.batch(reader.val(), batch_size=128)
+    val_reader = paddle.fluid.io.batch(reader.val(), batch_size=128)
     feeder = fluid.DataFeeder(
         place=place, feed_list=feed_target_names, program=val_program)
 
diff --git a/demo/quant/quant_post/image_classification_post_training_quantization_quick_start.ipynb b/demo/quant/quant_post/image_classification_post_training_quantization_quick_start.ipynb
index 23b813e6c2525341579d26c13908a89ed96c1017..bdc0bc32e7c389bebd765c9f3726e4acb84f2e0e 100755
--- a/demo/quant/quant_post/image_classification_post_training_quantization_quick_start.ipynb
+++ b/demo/quant/quant_post/image_classification_post_training_quantization_quick_start.ipynb
@@ -79,9 +79,9 @@
    "outputs": [],
    "source": [
     "import paddle.dataset.mnist as reader\n",
-    "train_reader = paddle.batch(\n",
+    "train_reader = paddle.fluid.io.batch(\n",
     "        reader.train(), batch_size=128, drop_last=True)\n",
-    "test_reader = paddle.batch(\n",
+    "test_reader = paddle.fluid.io.batch(\n",
     "        reader.train(), batch_size=128, drop_last=True)\n",
     "train_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())"
    ]
diff --git a/demo/sensitive/image_classification_sensitivity_analysis.ipynb b/demo/sensitive/image_classification_sensitivity_analysis.ipynb
index 002bc8ee07b40069fef9f09fd7940d2a45e94ebb..19234337f744ac01aceaaf92b7443b5e97e40923 100644
--- a/demo/sensitive/image_classification_sensitivity_analysis.ipynb
+++ b/demo/sensitive/image_classification_sensitivity_analysis.ipynb
@@ -73,9 +73,9 @@
    "outputs": [],
    "source": [
     "import paddle.dataset.mnist as reader\n",
-    "train_reader = paddle.batch(\n",
+    "train_reader = paddle.fluid.io.batch(\n",
     "        reader.train(), batch_size=128, drop_last=True)\n",
-    "test_reader = paddle.batch(\n",
+    "test_reader = paddle.fluid.io.batch(\n",
     "        reader.test(), batch_size=128, drop_last=True)\n",
     "data_feeder = fluid.DataFeeder(inputs, place)"
    ]
diff --git a/demo/sensitive/train.py b/demo/sensitive/train.py
index 7137b95368aba9b2b46b734b0151a1fa18ad0dc7..693d6bf4e167d68b04c255485a3b64282cbebdc1 100644
--- a/demo/sensitive/train.py
+++ b/demo/sensitive/train.py
@@ -68,7 +68,7 @@ def compress(args):
 
         fluid.io.load_vars(exe, args.pretrained_model, predicate=if_exist)
 
-    val_reader = paddle.batch(val_reader, batch_size=args.batch_size)
+    val_reader = paddle.fluid.io.batch(val_reader, batch_size=args.batch_size)
 
     val_feeder = feeder = fluid.DataFeeder(
         [image, label], place, program=val_program)
diff --git a/demo/sensitive_prune/greedy_prune.py b/demo/sensitive_prune/greedy_prune.py
index e3f8bb57eb3eb0e5c515376970d9484eeca78764..f59b7eaa6e5b02fb977be730ab6f72a2a2518fb8 100644
--- a/demo/sensitive_prune/greedy_prune.py
+++ b/demo/sensitive_prune/greedy_prune.py
@@ -119,8 +119,8 @@ def compress(args):
 
         fluid.io.load_vars(exe, args.pretrained_model, predicate=if_exist)
 
-    val_reader = paddle.batch(val_reader, batch_size=args.batch_size)
-    train_reader = paddle.batch(
+    val_reader = paddle.fluid.io.batch(val_reader, batch_size=args.batch_size)
+    train_reader = paddle.fluid.io.batch(
         train_reader, batch_size=args.batch_size, drop_last=True)
 
     train_feeder = feeder = fluid.DataFeeder([image, label], place)
diff --git a/demo/sensitive_prune/prune.py b/demo/sensitive_prune/prune.py
index e6c1ba7ccd09f41c8d0652075036a1c279251517..a4cb8ac242558c6daa6b92c51bcea534b406098f 100644
--- a/demo/sensitive_prune/prune.py
+++ b/demo/sensitive_prune/prune.py
@@ -117,8 +117,8 @@ def compress(args):
 
         fluid.io.load_vars(exe, args.pretrained_model, predicate=if_exist)
 
-    val_reader = paddle.batch(val_reader, batch_size=args.batch_size)
-    train_reader = paddle.batch(
+    val_reader = paddle.fluid.io.batch(val_reader, batch_size=args.batch_size)
+    train_reader = paddle.fluid.io.batch(
         train_reader, batch_size=args.batch_size, drop_last=True)
 
     train_feeder = feeder = fluid.DataFeeder([image, label], place)
diff --git a/demo/slimfacenet/dataloader/casia.py b/demo/slimfacenet/dataloader/casia.py
index 7faec56cfd94ec1b234d928d8698e4b118ef0a11..4162ef46b5aebdaa6cb6bb4b70a817cb5948df15 100644
--- a/demo/slimfacenet/dataloader/casia.py
+++ b/demo/slimfacenet/dataloader/casia.py
@@ -79,7 +79,7 @@ if __name__ == '__main__':
         dataset = CASIA_Face(root=data_dir)
         print(len(dataset))
         print(dataset.class_nums)
-        trainloader = paddle.batch(
+        trainloader = paddle.fluid.io.batch(
             dataset.reader, batch_size=1, drop_last=False)
         for i in range(10):
             for data in trainloader():
diff --git a/demo/slimfacenet/lfw_eval.py b/demo/slimfacenet/lfw_eval.py
index 44bf0d33bcaa59096cb64d90e59fdc150a5e5160..974fe0783ca4a7f040153514feb7c10851865bf1 100644
--- a/demo/slimfacenet/lfw_eval.py
+++ b/demo/slimfacenet/lfw_eval.py
@@ -159,7 +159,7 @@ if __name__ == "__main__":
         train_dataset = CASIA_Face(root=args.train_data_dir)
         nl, nr, flods, flags = parse_filelist(args.test_data_dir)
         test_dataset = LFW(nl, nr)
-        test_reader = paddle.batch(
+        test_reader = paddle.fluid.io.batch(
             test_dataset.reader,
             batch_size=args.test_batchsize,
             drop_last=False)
diff --git a/demo/slimfacenet/train_eval.py b/demo/slimfacenet/train_eval.py
index 421496f0463ce99a48b19f483f970f44ceb022dd..901384a7bd2123684db1373b6a2712c7c67b2aa7 100644
--- a/demo/slimfacenet/train_eval.py
+++ b/demo/slimfacenet/train_eval.py
@@ -166,7 +166,7 @@ def build_program(program, startup, args, is_train=True):
                 image = fluid.data(
                     name='image', shape=[-1, 3, 112, 96], dtype='float32')
                 label = fluid.data(name='label', shape=[-1, 1], dtype='int64')
-                train_reader = paddle.batch(
+                train_reader = paddle.fluid.io.batch(
                     train_dataset.reader,
                     batch_size=args.train_batchsize // num_trainers,
                     drop_last=False)
@@ -187,7 +187,7 @@ def build_program(program, startup, args, is_train=True):
             else:
                 nl, nr, flods, flags = parse_filelist(args.test_data_dir)
                 test_dataset = LFW(nl, nr)
-                test_reader = paddle.batch(
+                test_reader = paddle.fluid.io.batch(
                     test_dataset.reader,
                     batch_size=args.test_batchsize,
                     drop_last=False)
@@ -231,7 +231,7 @@ def build_program(program, startup, args, is_train=True):
 def quant_val_reader_batch():
     nl, nr, flods, flags = parse_filelist(args.test_data_dir)
     test_dataset = LFW(nl, nr)
-    test_reader = paddle.batch(
+    test_reader = paddle.fluid.io.batch(
         test_dataset.reader, batch_size=1, drop_last=False)
     shuffle_index = args.seed if args.seed else np.random.randint(1000)
     print('shuffle_index: {}'.format(shuffle_index))
@@ -347,7 +347,7 @@ def main():
              executor=exe)
         nl, nr, flods, flags = parse_filelist(args.test_data_dir)
         test_dataset = LFW(nl, nr)
-        test_reader = paddle.batch(
+        test_reader = paddle.fluid.io.batch(
             test_dataset.reader,
             batch_size=args.test_batchsize,
             drop_last=False)
diff --git a/docs/en/quick_start/distillation_tutorial_en.md b/docs/en/quick_start/distillation_tutorial_en.md
index 23ed8d2db98239b8d8d527bdcdca335ba14da759..d948f117b9fb188571b0fc07b677824ab237156e 100755
--- a/docs/en/quick_start/distillation_tutorial_en.md
+++ b/docs/en/quick_start/distillation_tutorial_en.md
@@ -100,7 +100,7 @@ The package `paddle.dataset.mnist` of Paddle define the downloading and reading
 Define training data reader and test data reader as below：
 
 ```python
-train_reader = paddle.batch(
+train_reader = paddle.fluid.io.batch(
     paddle.dataset.mnist.train(), batch_size=128, drop_last=True)
 train_feeder = fluid.DataFeeder(['image', 'label'], fluid.CPUPlace(), student_program)
 ```
diff --git a/docs/en/quick_start/nas_tutorial_en.md b/docs/en/quick_start/nas_tutorial_en.md
index 63d695b0b611728ba932c236f7b07cd6f419b1a9..040f46530cd61c815f633fdf478b368c0d88e07e 100644
--- a/docs/en/quick_start/nas_tutorial_en.md
+++ b/docs/en/quick_start/nas_tutorial_en.md
@@ -1,11 +1,11 @@
-# Nerual Architecture Search for Image Classification 
+# Nerual Architecture Search for Image Classification
 
 This tutorial shows how to use [API](../api/nas_api.md) about SANAS in PaddleSlim. We start experiment based on MobileNetV2 as example. The tutorial contains follow section.
 
 1. necessary imports
 2. initial SANAS instance
 3. define function about building program
-4. define function about input data 
+4. define function about input data
 5. define function about training
 6. define funciton about evaluation
 7. start search
@@ -52,7 +52,7 @@ def build_program(archs):
         acc_top1 = fluid.layers.accuracy(input=softmax_out, label=label, k=1)
         acc_top5 = fluid.layers.accuracy(input=softmax_out, label=label, k=5)
         test_program = fluid.default_main_program().clone(for_test=True)
-            
+
         optimizer = fluid.optimizer.Adam(learning_rate=0.1)
         optimizer.minimize(avg_cost)
 
@@ -62,13 +62,13 @@ def build_program(archs):
     return exe, train_program, test_program, (data, label), avg_cost, acc_top1, acc_top5
 ```
 
-## 4. define function about input data 
-The dataset we used is cifar10, and `paddle.dataset.cifar` in Paddle including the download and pre-read about cifar. 
+## 4. define function about input data
+The dataset we used is cifar10, and `paddle.dataset.cifar` in Paddle including the download and pre-read about cifar.
 ```python
 def input_data(inputs):
-    train_reader = paddle.batch(paddle.reader.shuffle(paddle.dataset.cifar.train10(cycle=False), buf_size=1024),batch_size=256)
+    train_reader = paddle.fluid.io.batch(paddle.reader.shuffle(paddle.dataset.cifar.train10(cycle=False), buf_size=1024),batch_size=256)
     train_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())
-    eval_reader = paddle.batch(paddle.dataset.cifar.test10(cycle=False), batch_size=256)
+    eval_reader = paddle.fluid.io.batch(paddle.dataset.cifar.test10(cycle=False), batch_size=256)
     eval_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())
     return train_reader, train_feeder, eval_reader, eval_feeder
 ```
@@ -76,7 +76,7 @@ def input_data(inputs):
 ## 5. define function about training
 Start training.
 ```python
-def start_train(program, data_reader, data_feeder): 
+def start_train(program, data_reader, data_feeder):
     outputs = [avg_cost.name, acc_top1.name, acc_top5.name]
     for data in data_reader():
         batch_reward = exe.run(program, feed=data_feeder.feed(data), fetch_list = outputs)
@@ -145,7 +145,7 @@ for step in range(3):
     current_flops = slim.analysis.flops(train_program)
     if current_flops > 321208544:
         continue
-    
+
     for epoch in range(7):
         start_train(train_program, train_reader, train_feeder)
 
diff --git a/docs/en/quick_start/pruning_tutorial_en.md b/docs/en/quick_start/pruning_tutorial_en.md
index e80729455af02b635445e7a8d9d33efe79793e91..9107a38b58255f08ce3da78fa18274c05d844604 100755
--- a/docs/en/quick_start/pruning_tutorial_en.md
+++ b/docs/en/quick_start/pruning_tutorial_en.md
@@ -74,7 +74,7 @@ Define training data reader and test data reader as below：
 
 ```
 import paddle.dataset.mnist as reader
-train_reader = paddle.batch(
+train_reader = paddle.fluid.io.batch(
         reader.train(), batch_size=128, drop_last=True)
 train_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())
 ```
diff --git a/docs/en/quick_start/quant_aware_tutorial_en.md b/docs/en/quick_start/quant_aware_tutorial_en.md
index 938e85f50df7c9b78ea1d90e8b1cfe93c917b5d5..8b169294ce1ae7bde64ed59035b40f7b2f588d0b 100644
--- a/docs/en/quick_start/quant_aware_tutorial_en.md
+++ b/docs/en/quick_start/quant_aware_tutorial_en.md
@@ -41,9 +41,9 @@ To speed up training process, we select MNIST dataset to train image classificat
 
 ```python
 import paddle.dataset.mnist as reader
-train_reader = paddle.batch(
+train_reader = paddle.fluid.io.batch(
         reader.train(), batch_size=128, drop_last=True)
-test_reader = paddle.batch(
+test_reader = paddle.fluid.io.batch(
         reader.train(), batch_size=128, drop_last=True)
 train_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())
 ```
diff --git a/docs/en/quick_start/quant_post_tutorial_en.md b/docs/en/quick_start/quant_post_tutorial_en.md
index a46329f365a7043661c85b42bb45904b9f74ea3f..e1e3ba4a4e08bdfbd6b79a568f3b7fb1d7fbd050 100644
--- a/docs/en/quick_start/quant_post_tutorial_en.md
+++ b/docs/en/quick_start/quant_post_tutorial_en.md
@@ -39,9 +39,10 @@ To speed up training process, we select MNIST dataset to train image classificat
 
 ```python
 import paddle.dataset.mnist as reader
-train_reader = paddle.batch(
+train_reader = paddle.fluid.io.batch(
         reader.train(), batch_size=128, drop_last=True)
-test_reader = paddle.batch(
+test_reader = paddle.fluid.io.batch(
+cs/en/quick_start/quant_aware_tutorial_en.md
         reader.train(), batch_size=128, drop_last=True)
 train_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())
 ```
diff --git a/docs/en/tutorials/image_classification_sensitivity_analysis_tutorial_en.md b/docs/en/tutorials/image_classification_sensitivity_analysis_tutorial_en.md
index 2b084074d9c9f79cbe013252457f01f448968f5e..043e144a1f122fd9abd1598f35c688f5bc7b6f71 100644
--- a/docs/en/tutorials/image_classification_sensitivity_analysis_tutorial_en.md
+++ b/docs/en/tutorials/image_classification_sensitivity_analysis_tutorial_en.md
@@ -45,9 +45,9 @@ Show as below：
 
 ```python
 import paddle.dataset.mnist as reader
-train_reader = paddle.batch(
+train_reader = paddle.fluid.io.batch(
         reader.train(), batch_size=128, drop_last=True)
-test_reader = paddle.batch(
+test_reader = paddle.fluid.io.batch(
         reader.test(), batch_size=128, drop_last=True)
 data_feeder = fluid.DataFeeder(inputs, place)
 ```
diff --git a/docs/zh_cn/api_cn/pantheon_api.md b/docs/zh_cn/api_cn/pantheon_api.md
index 1de04a6451396149f09c198c206d47181d74546e..87fc67249c5dd91368e0c256cf552fb09aa48685 100644
--- a/docs/zh_cn/api_cn/pantheon_api.md
+++ b/docs/zh_cn/api_cn/pantheon_api.md
@@ -125,7 +125,7 @@ place = fluid.CPUPlace()
 exe = fluid.Executor(place)
 exe.run(startup)
 
-train_reader = paddle.batch(
+train_reader = paddle.fluid.io.batch(
         paddle.dataset.cifar.train10(), batch_size=32)
 
 teacher = Teacher(out_path="example_knowledge.dat", # offline mode
diff --git a/docs/zh_cn/api_cn/prune_api.rst b/docs/zh_cn/api_cn/prune_api.rst
index 1da4c72dfa1242dd8a7873a7a8a4309d772b74c4..540dae043d9c81dd3d9f5146cbaf318bbd4e091c 100644
--- a/docs/zh_cn/api_cn/prune_api.rst
+++ b/docs/zh_cn/api_cn/prune_api.rst
@@ -270,7 +270,7 @@ sensitivity
    exe = fluid.Executor(place)
    exe.run(startup_program)
    
-   val_reader = paddle.batch(reader.test(), batch_size=128)
+   val_reader = paddle.fluid.io.batch(reader.test(), batch_size=128)
    val_feeder = feeder = fluid.DataFeeder(
            [image, label], place, program=main_program)
    
diff --git a/docs/zh_cn/quick_start/distillation_tutorial.md b/docs/zh_cn/quick_start/distillation_tutorial.md
index d998e338afda7a9d607e88ef75c670d273e4cf72..a9b989760c1609cea40faad6482ef2056218db02 100755
--- a/docs/zh_cn/quick_start/distillation_tutorial.md
+++ b/docs/zh_cn/quick_start/distillation_tutorial.md
@@ -101,7 +101,7 @@ exe.run(student_startup)
 为了快速执行该示例，我们选取简单的MNIST数据，Paddle框架的`paddle.dataset.mnist`包定义了MNIST数据的下载和读取。 代码如下：
 
 ```python
-train_reader = paddle.batch(
+train_reader = paddle.fluid.io.batch(
     paddle.dataset.mnist.train(), batch_size=128, drop_last=True)
 train_feeder = fluid.DataFeeder(['image', 'label'], fluid.CPUPlace(), student_program)
 ```
diff --git a/docs/zh_cn/quick_start/nas_tutorial.md b/docs/zh_cn/quick_start/nas_tutorial.md
index e68cb7fe1b973cad2ecfd3ea2cec36bf8468fd3e..1dea7c9daa2a09b854de1a308ee8bb6fc7a7f976 100644
--- a/docs/zh_cn/quick_start/nas_tutorial.md
+++ b/docs/zh_cn/quick_start/nas_tutorial.md
@@ -67,9 +67,9 @@ def build_program(archs):
 使用的数据集为cifar10，paddle框架中`paddle.dataset.cifar`包括了cifar数据集的下载和读取，代码如下：
 ```python
 def input_data(inputs):
-    train_reader = paddle.batch(paddle.reader.shuffle(paddle.dataset.cifar.train10(cycle=False), buf_size=1024),batch_size=256)
+    train_reader = paddle.fluid.io.batch(paddle.reader.shuffle(paddle.dataset.cifar.train10(cycle=False), buf_size=1024),batch_size=256)
     train_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())
-    eval_reader = paddle.batch(paddle.dataset.cifar.test10(cycle=False), batch_size=256)
+    eval_reader = paddle.fluid.io.batch(paddle.dataset.cifar.test10(cycle=False), batch_size=256)
     eval_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())
     return train_reader, train_feeder, eval_reader, eval_feeder
 ```
diff --git a/docs/zh_cn/quick_start/pruning_tutorial.md b/docs/zh_cn/quick_start/pruning_tutorial.md
index 7545fad64552d79879435ff44f8654c8064fca0c..051a740f4602f2175537efe5eaf22b62a06c10e7 100755
--- a/docs/zh_cn/quick_start/pruning_tutorial.md
+++ b/docs/zh_cn/quick_start/pruning_tutorial.md
@@ -74,7 +74,7 @@ print("FLOPs: {}".format(FLOPs))
 
 ```
 import paddle.dataset.mnist as reader
-train_reader = paddle.batch(
+train_reader = paddle.fluid.io.batch(
         reader.train(), batch_size=128, drop_last=True)
 train_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())
 ```
diff --git a/docs/zh_cn/quick_start/quant_aware_tutorial.md b/docs/zh_cn/quick_start/quant_aware_tutorial.md
index 5dfc3837aed641accf75c334aa962ae9efb75b66..5ed1e59ffd623d1877f4d65a8f3f6cc10fd7a8f1 100644
--- a/docs/zh_cn/quick_start/quant_aware_tutorial.md
+++ b/docs/zh_cn/quick_start/quant_aware_tutorial.md
@@ -42,9 +42,9 @@ exe, train_program, val_program, inputs, outputs = \
 
 ```python
 import paddle.dataset.mnist as reader
-train_reader = paddle.batch(
+train_reader = paddle.fluid.io.batch(
         reader.train(), batch_size=128, drop_last=True)
-test_reader = paddle.batch(
+test_reader = paddle.fluid.io.batch(
         reader.train(), batch_size=128, drop_last=True)
 train_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())
 ```
diff --git a/docs/zh_cn/quick_start/quant_post_tutorial.md b/docs/zh_cn/quick_start/quant_post_tutorial.md
index 5904b872bd4e5f9782ab4b8affd1fdf7ac587fd9..b29a4f4054fe7a1113488aaa3cb8903bc2df946c 100755
--- a/docs/zh_cn/quick_start/quant_post_tutorial.md
+++ b/docs/zh_cn/quick_start/quant_post_tutorial.md
@@ -40,9 +40,9 @@ exe, train_program, val_program, inputs, outputs = \
 
 ```python
 import paddle.dataset.mnist as reader
-train_reader = paddle.batch(
+train_reader = paddle.fluid.io.batch(
         reader.train(), batch_size=128, drop_last=True)
-test_reader = paddle.batch(
+test_reader = paddle.fluid.io.batch(
         reader.train(), batch_size=128, drop_last=True)
 train_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())
 ```
diff --git a/docs/zh_cn/tutorials/image_classification_nas_quick_start.ipynb b/docs/zh_cn/tutorials/image_classification_nas_quick_start.ipynb
index c176c262a0f1809bea56ddd4436f182c0935d056..fceccb98fbb201bd873cf34478a7f396110e427a 100644
--- a/docs/zh_cn/tutorials/image_classification_nas_quick_start.ipynb
+++ b/docs/zh_cn/tutorials/image_classification_nas_quick_start.ipynb
@@ -128,9 +128,9 @@
    "outputs": [],
    "source": [
     "def input_data(inputs):\n",
-    "    train_reader = paddle.batch(paddle.reader.shuffle(paddle.dataset.cifar.train10(cycle=False), buf_size=1024),batch_size=256)\n",
+    "    train_reader = paddle.fluid.io.batch(paddle.reader.shuffle(paddle.dataset.cifar.train10(cycle=False), buf_size=1024),batch_size=256)\n",
     "    train_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())\n",
-    "    eval_reader = paddle.batch(paddle.dataset.cifar.test10(cycle=False), batch_size=256)\n",
+    "    eval_reader = paddle.fluid.io.batch(paddle.dataset.cifar.test10(cycle=False), batch_size=256)\n",
     "    eval_feeder = fluid.DataFeeder(inputs, fluid.CPUPlace())\n",
     "    return train_reader, train_feeder, eval_reader, eval_feeder"
    ]
diff --git a/docs/zh_cn/tutorials/image_classification_sensitivity_analysis_tutorial.md b/docs/zh_cn/tutorials/image_classification_sensitivity_analysis_tutorial.md
index bfa35d389e714a39e3c9574b4c94c5cd5eb32913..6bde2f8ca4615554152aacf2983c8c5d6f369ff0 100644
--- a/docs/zh_cn/tutorials/image_classification_sensitivity_analysis_tutorial.md
+++ b/docs/zh_cn/tutorials/image_classification_sensitivity_analysis_tutorial.md
@@ -44,9 +44,9 @@ place = fluid.CUDAPlace(0)
 
 ```python
 import paddle.dataset.mnist as reader
-train_reader = paddle.batch(
+train_reader = paddle.fluid.io.batch(
         reader.train(), batch_size=128, drop_last=True)
-test_reader = paddle.batch(
+test_reader = paddle.fluid.io.batch(
         reader.test(), batch_size=128, drop_last=True)
 data_feeder = fluid.DataFeeder(inputs, place)
 ```
diff --git a/docs/zh_cn/tutorials/sanas_darts_space.ipynb b/docs/zh_cn/tutorials/sanas_darts_space.ipynb
index 8cc43df5ca55543d58d49d04e21313045f4c75ec..658124b5ceea1b0e48fe488faffd2fbfa9b6584e 100644
--- a/docs/zh_cn/tutorials/sanas_darts_space.ipynb
+++ b/docs/zh_cn/tutorials/sanas_darts_space.ipynb
@@ -264,8 +264,8 @@
     }
    ],
    "source": [
-    "train_reader = paddle.batch(paddle.reader.shuffle(paddle.dataset.cifar.train10(cycle=False), buf_size=1024), batch_size=BATCH_SIZE, drop_last=True)\n",
-    "test_reader = paddle.batch(paddle.dataset.cifar.test10(cycle=False), batch_size=BATCH_SIZE, drop_last=False)\n",
+    "train_reader = paddle.fluid.io.batch(paddle.reader.shuffle(paddle.dataset.cifar.train10(cycle=False), buf_size=1024), batch_size=BATCH_SIZE, drop_last=True)\n",
+    "test_reader = paddle.fluid.io.batch(paddle.dataset.cifar.test10(cycle=False), batch_size=BATCH_SIZE, drop_last=False)\n",
     "train_loader.set_sample_list_generator(train_reader, places=place)\n",
     "test_loader.set_sample_list_generator(test_reader, places=place)"
    ]
diff --git a/docs/zh_cn/tutorials/sanas_darts_space.md b/docs/zh_cn/tutorials/sanas_darts_space.md
index 939ded2bfba743e265259a79b7bb1dfb079e70c7..b280db4ef88c5e2e63e398379f771976c03a3d7b 100644
--- a/docs/zh_cn/tutorials/sanas_darts_space.md
+++ b/docs/zh_cn/tutorials/sanas_darts_space.md
@@ -236,8 +236,8 @@ exe.run(startup_program)
 
 **注意：**本示例为了简化代码直接调用`paddle.dataset.cifar10`定义训练数据和预测数据，实际训练需要使用自定义cifar10文件中的reader。
 ```python
-train_reader = paddle.batch(paddle.reader.shuffle(paddle.dataset.cifar.train10(cycle=False), buf_size=1024), batch_size=BATCH_SIZE, drop_last=True)
-test_reader = paddle.batch(paddle.dataset.cifar.test10(cycle=False), batch_size=BATCH_SIZE, drop_last=False)
+train_reader = paddle.fluid.io.batch(paddle.reader.shuffle(paddle.dataset.cifar.train10(cycle=False), buf_size=1024), batch_size=BATCH_SIZE, drop_last=True)
+test_reader = paddle.fluid.io.batch(paddle.dataset.cifar.test10(cycle=False), batch_size=BATCH_SIZE, drop_last=False)
 train_loader.set_sample_list_generator(train_reader, places=place)
 test_loader.set_sample_list_generator(test_reader, places=place)
 ```
diff --git a/tests/test_quant_aware.py b/tests/test_quant_aware.py
index 16c93fe15eda513d2c98a99243208c89aee3b3b4..f0a8464f7e688625ff87279ce3fb030f7ba9cff3 100644
--- a/tests/test_quant_aware.py
+++ b/tests/test_quant_aware.py
@@ -112,9 +112,10 @@ class TestQuantAwareCase2(unittest.TestCase):
         exe = fluid.Executor(place)
         exe.run(fluid.default_startup_program())
         feeder = fluid.DataFeeder([image, label], place, program=main_prog)
-        train_reader = paddle.batch(
+        train_reader = paddle.fluid.io.batch(
             paddle.dataset.mnist.train(), batch_size=64)
-        eval_reader = paddle.batch(paddle.dataset.mnist.test(), batch_size=64)
+        eval_reader = paddle.fluid.io.batch(
+            paddle.dataset.mnist.test(), batch_size=64)
 
         def train(program):
             iter = 0
diff --git a/tests/test_quant_post.py b/tests/test_quant_post.py
index 17068410109f4651f43382a603b1829eb5769413..2279d5fb7549ea72f41efa6d5662634bcdeafe9b 100644
--- a/tests/test_quant_post.py
+++ b/tests/test_quant_post.py
@@ -50,9 +50,10 @@ class TestQuantAwareCase1(unittest.TestCase):
         exe = fluid.Executor(place)
         exe.run(fluid.default_startup_program())
         feeder = fluid.DataFeeder([image, label], place, program=main_prog)
-        train_reader = paddle.batch(
+        train_reader = paddle.fluid.io.batch(
             paddle.dataset.mnist.train(), batch_size=64)
-        eval_reader = paddle.batch(paddle.dataset.mnist.test(), batch_size=64)
+        eval_reader = paddle.fluid.io.batch(
+            paddle.dataset.mnist.test(), batch_size=64)
 
         def train(program):
             iter = 0
diff --git a/tests/test_quant_post_only_weight.py b/tests/test_quant_post_only_weight.py
index 0a09aa0650756325795ebc522c52e926935bc00e..bbb1a00bd6fd0178142968ce0422161217f827bf 100644
--- a/tests/test_quant_post_only_weight.py
+++ b/tests/test_quant_post_only_weight.py
@@ -50,9 +50,10 @@ class TestQuantPostOnlyWeightCase1(unittest.TestCase):
         exe = fluid.Executor(place)
         exe.run(fluid.default_startup_program())
         feeder = fluid.DataFeeder([image, label], place, program=main_prog)
-        train_reader = paddle.batch(
+        train_reader = paddle.fluid.io.batch(
             paddle.dataset.mnist.train(), batch_size=64)
-        eval_reader = paddle.batch(paddle.dataset.mnist.test(), batch_size=64)
+        eval_reader = paddle.fluid.io.batch(
+            paddle.dataset.mnist.test(), batch_size=64)
 
         def train(program):
             iter = 0
diff --git a/tests/test_sensitivity.py b/tests/test_sensitivity.py
index e2cfa01d889db2891fd7507b2d4d9aec018a1163..648c09f2a96067c89826f462e7fe955eb1b9b7e8 100644
--- a/tests/test_sensitivity.py
+++ b/tests/test_sensitivity.py
@@ -44,7 +44,8 @@ class TestSensitivity(unittest.TestCase):
         exe = fluid.Executor(place)
         exe.run(startup_program)
 
-        val_reader = paddle.batch(paddle.dataset.mnist.test(), batch_size=128)
+        val_reader = paddle.fluid.io.batch(
+            paddle.dataset.mnist.test(), batch_size=128)
 
         def eval_func(program, scope):
             feeder = fluid.DataFeeder(