diff --git a/python/paddle/hapi/callbacks.py b/python/paddle/hapi/callbacks.py
index 61ae8b42d63a909cc4dc88d4b16f0b0e8ed83c71..2bdde3879a2db2bc2487cbf27811c1fda442ced4 100644
--- a/python/paddle/hapi/callbacks.py
+++ b/python/paddle/hapi/callbacks.py
@@ -324,7 +324,7 @@ class ProgBarLogger(Callback):
             ])
             train_dataset = MNIST(mode='train', transform=transform)
 
-            lenet = paddle.vision.LeNet()
+            lenet = paddle.vision.models.LeNet()
             model = paddle.Model(lenet,
                 inputs, labels)
 
@@ -554,7 +554,7 @@ class ModelCheckpoint(Callback):
             ])
             train_dataset = MNIST(mode='train', transform=transform)
 
-            lenet = paddle.vision.LeNet()
+            lenet = paddle.vision.models.LeNet()
             model = paddle.Model(lenet,
                 inputs, labels)
 
@@ -614,7 +614,7 @@ class LRScheduler(Callback):
             ])
             train_dataset = paddle.vision.datasets.MNIST(mode='train', transform=transform)
 
-            lenet = paddle.vision.LeNet()
+            lenet = paddle.vision.models.LeNet()
             model = paddle.Model(lenet,
                 inputs, labels)
 
@@ -630,7 +630,7 @@ class LRScheduler(Callback):
                     boundaries=boundaries, values=values)
                 learning_rate = paddle.optimizer.lr.LinearWarmup(
                     learning_rate=learning_rate,
-                    warmup_steps=wamup_epochs,
+                    warmup_steps=wamup_steps,
                     start_lr=base_lr / 5.,
                     end_lr=base_lr,
                     verbose=True)
@@ -856,7 +856,7 @@ class VisualDL(Callback):
             train_dataset = paddle.vision.datasets.MNIST(mode='train', transform=transform)
             eval_dataset = paddle.vision.datasets.MNIST(mode='test', transform=transform)
 
-            net = paddle.vision.LeNet()
+            net = paddle.vision.models.LeNet()
             model = paddle.Model(net, inputs, labels)
 
             optim = paddle.optimizer.Adam(0.001, parameters=net.parameters())
diff --git a/python/paddle/hapi/model.py b/python/paddle/hapi/model.py
index 160d6c54759d901e2529221c99dce63b29f06810..1c76c9174fd6989d34619c51d366c709efc67835 100644
--- a/python/paddle/hapi/model.py
+++ b/python/paddle/hapi/model.py
@@ -30,20 +30,28 @@ from collections import Iterable
 import paddle
 from paddle import fluid
 from paddle.fluid import core
-from paddle.fluid.framework import in_dygraph_mode, Variable, ParamBase, _current_expected_place
-from paddle.fluid.framework import in_dygraph_mode, Variable, _get_paddle_place
+from paddle.fluid.framework import in_dygraph_mode
+from paddle.fluid.framework import Variable
+from paddle.fluid.framework import ParamBase
+from paddle.fluid.framework import _current_expected_place
+from paddle.fluid.framework import _get_paddle_place
 from paddle.fluid.framework import _current_expected_place as _get_device
 from paddle.fluid.executor import global_scope
 from paddle.fluid.io import is_belong_to_optimizer
 from paddle.fluid.dygraph.base import to_variable
 from paddle.fluid.dygraph.parallel import ParallelEnv
-from paddle.fluid.dygraph.dygraph_to_static.program_translator import ProgramTranslator, FunctionSpec
-from paddle.fluid.dygraph.io import INFER_MODEL_SUFFIX, INFER_PARAMS_SUFFIX
+from paddle.fluid.dygraph.dygraph_to_static.program_translator import ProgramTranslator
+from paddle.fluid.dygraph.dygraph_to_static.program_translator import FunctionSpec
+from paddle.fluid.dygraph.io import INFER_MODEL_SUFFIX
+from paddle.fluid.dygraph.io import INFER_PARAMS_SUFFIX
 from paddle.fluid.layers.utils import flatten
 from paddle.fluid.layers import collective
 
-from paddle.io import DataLoader, Dataset, DistributedBatchSampler
-from paddle.fluid.executor import scope_guard, Executor
+from paddle.io import DataLoader
+from paddle.io import Dataset
+from paddle.io import DistributedBatchSampler
+from paddle.fluid.executor import scope_guard
+from paddle.fluid.executor import Executor
 from paddle.fluid.dygraph.layers import Layer
 from paddle.metric import Metric
 from paddle.static import InputSpec as Input
@@ -166,7 +174,6 @@ def init_communicator(program, rank, nranks, wait_port, current_endpoint,
             name=unique_name.generate('hccl_id'),
             persistable=True,
             type=core.VarDesc.VarType.RAW)
-        endpoint_to_index_map = {e: idx for idx, e in enumerate(endpoints)}
         block.append_op(
             type='c_gen_hccl_id',
             inputs={},
@@ -710,10 +717,10 @@ class DynamicGraphAdapter(object):
                 enable=self._amp_level != 'O0', **self._amp_custom_lists):
             if self._nranks > 1:
                 outputs = self.ddp_model.forward(
-                    * [to_variable(x) for x in inputs])
+                    *[to_variable(x) for x in inputs])
             else:
                 outputs = self.model.network.forward(
-                    * [to_variable(x) for x in inputs])
+                    *[to_variable(x) for x in inputs])
 
             losses = self.model._loss(*(to_list(outputs) + labels))
             losses = to_list(losses)
@@ -732,7 +739,7 @@ class DynamicGraphAdapter(object):
         metrics = []
         for metric in self.model._metrics:
             metric_outs = metric.compute(*(to_list(outputs) + labels))
-            m = metric.update(* [to_numpy(m) for m in to_list(metric_outs)])
+            m = metric.update(*[to_numpy(m) for m in to_list(metric_outs)])
             metrics.append(m)
 
         return ([to_numpy(l) for l in losses], metrics) \
@@ -746,7 +753,7 @@ class DynamicGraphAdapter(object):
         labels = labels or []
         labels = [to_variable(l) for l in to_list(labels)]
 
-        outputs = self.model.network.forward(* [to_variable(x) for x in inputs])
+        outputs = self.model.network.forward(*[to_variable(x) for x in inputs])
         if self.model._loss:
             losses = self.model._loss(*(to_list(outputs) + labels))
             losses = to_list(losses)
@@ -777,7 +784,7 @@ class DynamicGraphAdapter(object):
                     self._merge_count[self.mode + '_batch'] = samples
 
             metric_outs = metric.compute(*(to_list(outputs) + labels))
-            m = metric.update(* [to_numpy(m) for m in to_list(metric_outs)])
+            m = metric.update(*[to_numpy(m) for m in to_list(metric_outs)])
             metrics.append(m)
 
         if self.model._loss and len(metrics):
@@ -1363,8 +1370,9 @@ class Model(object):
             # pure float16 training has some restricts now
             if self._adapter._amp_level == "O2":
                 if in_dygraph_mode():
-                    warnings.warn("Pure float16 training is not supported in dygraph mode now, "\
-                        "and it will be supported in future version.")
+                    warnings.warn(
+                        "Pure float16 training is not supported in dygraph mode now, and it will be supported in future version."
+                    )
                 else:
                     # grad clip is not supported in pure fp16 training now
                     assert self._optimizer._grad_clip is None, \
@@ -1398,8 +1406,7 @@ class Model(object):
 
         if 'use_pure_fp16' in amp_configs:
             raise ValueError(
-                "''use_pure_fp16' is an invalid parameter, "
-                "the level of mixed precision training only depends on 'O1' or 'O2'."
+                "'use_pure_fp16' is an invalid parameter, the level of mixed precision training only depends on 'O1' or 'O2'."
             )
 
         _check_pure_fp16_configs()
@@ -1427,9 +1434,8 @@ class Model(object):
             }
             if amp_config_key_set - accepted_param_set:
                 raise ValueError(
-                    "Except for 'level', the keys of 'amp_configs' must be accepted by mixed precision APIs, "
-                    "but {} could not be recognized.".format(
-                        tuple(amp_config_key_set - accepted_param_set)))
+                    "Except for 'level', the keys of 'amp_configs' must be accepted by mixed precision APIs, but {} could not be recognized.".
+                    format(tuple(amp_config_key_set - accepted_param_set)))
 
             if 'use_fp16_guard' in amp_config_key_set:
                 if in_dygraph_mode():
@@ -1501,8 +1507,9 @@ class Model(object):
         self._optimizer = optimizer
         if loss is not None:
             if not isinstance(loss, paddle.nn.Layer) and not callable(loss):
-                raise TypeError("'loss' must be sub classes of " \
-                    "`paddle.nn.Layer` or any callable function.")
+                raise TypeError(
+                    "'loss' must be sub classes of `paddle.nn.Layer` or any callable function."
+                )
         self._loss = loss
 
         metrics = metrics or []
@@ -2080,7 +2087,7 @@ class Model(object):
               input = InputSpec([None, 1, 28, 28], 'float32', 'image')
               label = InputSpec([None, 1], 'int64', 'label')
            
-              model = paddle.Model(paddle.vision.LeNet(),
+              model = paddle.Model(paddle.vision.models.LeNet(),
                   input, label)
               optim = paddle.optimizer.Adam(
                   learning_rate=0.001, parameters=model.parameters())
@@ -2122,9 +2129,11 @@ class Model(object):
             else:
                 out_specs = to_list(specs)
         elif isinstance(specs, dict):
-            assert is_input == False
-            out_specs = [specs[n] \
-                for n in extract_args(self.network.forward) if n != 'self']
+            assert is_input is False
+            out_specs = [
+                specs[n] for n in extract_args(self.network.forward)
+                if n != 'self'
+            ]
         else:
             out_specs = to_list(specs)
         # Note: checks each element has specificed `name`.
diff --git a/python/paddle/metric/metrics.py b/python/paddle/metric/metrics.py
index 61d1eb0e373341374199b811f198f7e295026ecc..d8e400b08bd474a1a59399e413a59e9a7d77f8b7 100644
--- a/python/paddle/metric/metrics.py
+++ b/python/paddle/metric/metrics.py
@@ -222,7 +222,7 @@ class Accuracy(Metric):
           transform = T.Compose([T.Transpose(), T.Normalize([127.5], [127.5])])
           train_dataset = MNIST(mode='train', transform=transform)
 
-          model = paddle.Model(paddle.vision.LeNet(), input, label)
+          model = paddle.Model(paddle.vision.models.LeNet(), input, label)
           optim = paddle.optimizer.Adam(
               learning_rate=0.001, parameters=model.parameters())
           model.prepare(
diff --git a/python/paddle/tests/test_callback_visualdl.py b/python/paddle/tests/test_callback_visualdl.py
index 36316183104fe3a19bfa5e9868e26e54f5405dd1..db3b83f2b141417b363d5dbe2d4fedd2542d31ad 100644
--- a/python/paddle/tests/test_callback_visualdl.py
+++ b/python/paddle/tests/test_callback_visualdl.py
@@ -55,7 +55,7 @@ class TestCallbacks(unittest.TestCase):
         train_dataset = MnistDataset(mode='train', transform=transform)
         eval_dataset = MnistDataset(mode='test', transform=transform)
 
-        net = paddle.vision.LeNet()
+        net = paddle.vision.models.LeNet()
         model = paddle.Model(net, inputs, labels)
 
         optim = paddle.optimizer.Adam(0.001, parameters=net.parameters())
diff --git a/python/paddle/vision/__init__.py b/python/paddle/vision/__init__.py
index aeb07bf281fb0a0289640e0591af4d864ca10b39..79fb7844dd58c664ce5c391788aacc384e49432c 100644
--- a/python/paddle/vision/__init__.py
+++ b/python/paddle/vision/__init__.py
@@ -11,22 +11,59 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+import paddle
+import paddle.nn as nn
+from . import models  # noqa: F401
+from . import transforms  # noqa: F401
+from . import datasets  # noqa: F401
+from . import ops  # noqa: F401
+from .image import set_image_backend  # noqa: F401
+from .image import get_image_backend  # noqa: F401
+from .image import image_load  # noqa: F401
+from .models import LeNet as models_LeNet
+import paddle.utils.deprecated as deprecated
 
-from . import models
-from .models import *
+__all__ = [  #noqa
+    'set_image_backend', 'get_image_backend', 'image_load'
+]
 
-from . import transforms
-from .transforms import *
 
-from . import datasets
-from .datasets import *
+class LeNet(models_LeNet):
+    """LeNet model from
+    `"LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.`_
 
-from . import image
-from .image import *
+    Args:
+        num_classes (int): output dim of last fc layer. If num_classes <=0, last fc layer 
+                            will not be defined. Default: 10.
 
-from . import ops
+    Examples:
+        .. code-block:: python
 
-__all__ = models.__all__ \
-        + transforms.__all__ \
-        + datasets.__all__ \
-        + image.__all__
+            from paddle.vision.models import LeNet
+
+            model = LeNet()
+    """
+
+    @deprecated(
+        since="2.0.0",
+        update_to="paddle.vision.models.LeNet",
+        level=1,
+        reason="Please use new API in models, paddle.vision.LeNet will be removed in future"
+    )
+    def __init__(self, num_classes=10):
+        super(LeNet, self).__init__(num_classes=10)
+        self.num_classes = num_classes
+        self.features = nn.Sequential(
+            nn.Conv2D(
+                1, 6, 3, stride=1, padding=1),
+            nn.ReLU(),
+            nn.MaxPool2D(2, 2),
+            nn.Conv2D(
+                6, 16, 5, stride=1, padding=0),
+            nn.ReLU(),
+            nn.MaxPool2D(2, 2))
+
+        if num_classes > 0:
+            self.fc = nn.Sequential(
+                nn.Linear(400, 120),
+                nn.Linear(120, 84), nn.Linear(84, num_classes))
diff --git a/python/paddle/vision/datasets/__init__.py b/python/paddle/vision/datasets/__init__.py
index 6703aa4197603be2d82d930e3cd2622ff6b4cd77..3ee7503e27979753ba97241256f769841b40b0c8 100644
--- a/python/paddle/vision/datasets/__init__.py
+++ b/python/paddle/vision/datasets/__init__.py
@@ -12,20 +12,22 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from . import folder
-from . import mnist
-from . import flowers
-from . import cifar
-from . import voc2012
+from .folder import DatasetFolder  # noqa: F401
+from .folder import ImageFolder  # noqa: F401
+from .mnist import MNIST  # noqa: F401
+from .mnist import FashionMNIST  # noqa: F401
+from .flowers import Flowers  # noqa: F401
+from .cifar import Cifar10  # noqa: F401
+from .cifar import Cifar100  # noqa: F401
+from .voc2012 import VOC2012  # noqa: F401
 
-from .folder import *
-from .mnist import *
-from .flowers import *
-from .cifar import *
-from .voc2012 import *
-
-__all__ = folder.__all__ \
-          + mnist.__all__ \
-          + flowers.__all__ \
-          + cifar.__all__ \
-          + voc2012.__all__
+__all__ = [ #noqa
+    'DatasetFolder'
+    'ImageFolder',
+    'MNIST',
+    'FashionMNIST',
+    'Flowers',
+    'Cifar10',
+    'Cifar100',
+    'VOC2012'
+]
diff --git a/python/paddle/vision/datasets/cifar.py b/python/paddle/vision/datasets/cifar.py
index 0a0a48026af80eccc891df9202ab3a42f37ba06d..2a582d7d0a8e5c09830162b37c2b0aa0a493b13e 100644
--- a/python/paddle/vision/datasets/cifar.py
+++ b/python/paddle/vision/datasets/cifar.py
@@ -24,7 +24,7 @@ import paddle
 from paddle.io import Dataset
 from paddle.dataset.common import _check_exists_and_download
 
-__all__ = ['Cifar10', 'Cifar100']
+__all__ = []
 
 URL_PREFIX = 'https://dataset.bj.bcebos.com/cifar/'
 CIFAR10_URL = URL_PREFIX + 'cifar-10-python.tar.gz'
diff --git a/python/paddle/vision/datasets/flowers.py b/python/paddle/vision/datasets/flowers.py
index 448d6efb52beca953de7981312e8f9131e6fb05d..11b781b7a6dc7bc131d7a7ddf230785f86fcf417 100644
--- a/python/paddle/vision/datasets/flowers.py
+++ b/python/paddle/vision/datasets/flowers.py
@@ -25,7 +25,7 @@ from paddle.io import Dataset
 from paddle.utils import try_import
 from paddle.dataset.common import _check_exists_and_download
 
-__all__ = ["Flowers"]
+__all__ = []
 
 DATA_URL = 'http://paddlemodels.bj.bcebos.com/flowers/102flowers.tgz'
 LABEL_URL = 'http://paddlemodels.bj.bcebos.com/flowers/imagelabels.mat'
diff --git a/python/paddle/vision/datasets/folder.py b/python/paddle/vision/datasets/folder.py
index 718af041307a15e5c44ece79b478d7a47bf8729c..220b3d8ecb4b412a83e452381ef021afdf0e4940 100644
--- a/python/paddle/vision/datasets/folder.py
+++ b/python/paddle/vision/datasets/folder.py
@@ -20,7 +20,7 @@ import paddle
 from paddle.io import Dataset
 from paddle.utils import try_import
 
-__all__ = ["DatasetFolder", "ImageFolder"]
+__all__ = []
 
 
 def has_valid_extension(filename, extensions):
diff --git a/python/paddle/vision/datasets/mnist.py b/python/paddle/vision/datasets/mnist.py
index 1b998fd71a62e5bd21545e1548e628042fca833a..84760f9598b6adc60eb3873633db0bc87bf64785 100644
--- a/python/paddle/vision/datasets/mnist.py
+++ b/python/paddle/vision/datasets/mnist.py
@@ -24,7 +24,7 @@ import paddle
 from paddle.io import Dataset
 from paddle.dataset.common import _check_exists_and_download
 
-__all__ = ["MNIST", "FashionMNIST"]
+__all__ = []
 
 
 class MNIST(Dataset):
diff --git a/python/paddle/vision/datasets/voc2012.py b/python/paddle/vision/datasets/voc2012.py
index 1a42d143f0f72b21b6f431400713500f395b03f9..5a82d7864cb009da066929c830f6213818b7c203 100644
--- a/python/paddle/vision/datasets/voc2012.py
+++ b/python/paddle/vision/datasets/voc2012.py
@@ -23,7 +23,7 @@ import paddle
 from paddle.io import Dataset
 from paddle.dataset.common import _check_exists_and_download
 
-__all__ = ["VOC2012"]
+__all__ = []
 
 VOC_URL = 'https://dataset.bj.bcebos.com/voc/VOCtrainval_11-May-2012.tar'
 
diff --git a/python/paddle/vision/image.py b/python/paddle/vision/image.py
index 19986816b7cc42282050057b5cc791faa8fd1c1f..5c260b1d90a891134d344bb364d065bca2518c5b 100644
--- a/python/paddle/vision/image.py
+++ b/python/paddle/vision/image.py
@@ -15,7 +15,7 @@
 from PIL import Image
 from paddle.utils import try_import
 
-__all__ = ['set_image_backend', 'get_image_backend', 'image_load']
+__all__ = []
 
 _image_backend = 'pil'
 
diff --git a/python/paddle/vision/models/__init__.py b/python/paddle/vision/models/__init__.py
index 60d8c246ae10e2bcb2a6576ce13a99e5e984c5bc..d38f3b1722ee8c2f31d53a26b96d3320abd2e350 100644
--- a/python/paddle/vision/models/__init__.py
+++ b/python/paddle/vision/models/__init__.py
@@ -12,20 +12,38 @@
 #See the License for the specific language governing permissions and
 #limitations under the License.
 
-from . import resnet
-from . import vgg
-from . import mobilenetv1
-from . import mobilenetv2
-from . import lenet
+from .resnet import ResNet  # noqa: F401
+from .resnet import resnet18  # noqa: F401
+from .resnet import resnet34  # noqa: F401
+from .resnet import resnet50  # noqa: F401
+from .resnet import resnet101  # noqa: F401
+from .resnet import resnet152  # noqa: F401
+from .mobilenetv1 import MobileNetV1  # noqa: F401
+from .mobilenetv1 import mobilenet_v1  # noqa: F401
+from .mobilenetv2 import MobileNetV2  # noqa: F401
+from .mobilenetv2 import mobilenet_v2  # noqa: F401
+from .vgg import VGG  # noqa: F401
+from .vgg import vgg11  # noqa: F401
+from .vgg import vgg13  # noqa: F401
+from .vgg import vgg16  # noqa: F401
+from .vgg import vgg19  # noqa: F401
+from .lenet import LeNet  # noqa: F401
 
-from .resnet import *
-from .mobilenetv1 import *
-from .mobilenetv2 import *
-from .vgg import *
-from .lenet import *
-
-__all__ = resnet.__all__ \
-        + vgg.__all__ \
-        + mobilenetv1.__all__ \
-        + mobilenetv2.__all__ \
-        + lenet.__all__
+__all__ = [ #noqa
+    'ResNet',
+    'resnet18',
+    'resnet34',
+    'resnet50',
+    'resnet101',
+    'resnet152',
+    'VGG',
+    'vgg11',
+    'vgg13',
+    'vgg16',
+    'vgg19',
+    'MobileNetV1',
+    'mobilenet_v1',
+    'MobileNetV2',
+    'mobilenet_v2',
+    'LeNet'
+]
diff --git a/python/paddle/vision/models/lenet.py b/python/paddle/vision/models/lenet.py
index 2fb50fc17b9e9f1f9c8af3d5c22d8f0e35c3958a..46212f46f3a487c4ea567d049d7bc200331d34b4 100644
--- a/python/paddle/vision/models/lenet.py
+++ b/python/paddle/vision/models/lenet.py
@@ -15,7 +15,7 @@
 import paddle
 import paddle.nn as nn
 
-__all__ = ['LeNet']
+__all__ = []
 
 
 class LeNet(nn.Layer):
diff --git a/python/paddle/vision/models/mobilenetv1.py b/python/paddle/vision/models/mobilenetv1.py
index 22d177248e8b3708a37eb04b1b0eeeece8d154cf..671a2cd8dfd5f4cebf756edb397ad1f182b895ad 100644
--- a/python/paddle/vision/models/mobilenetv1.py
+++ b/python/paddle/vision/models/mobilenetv1.py
@@ -17,7 +17,7 @@ import paddle.nn as nn
 
 from paddle.utils.download import get_weights_path_from_url
 
-__all__ = ['MobileNetV1', 'mobilenet_v1']
+__all__ = []
 
 model_urls = {
     'mobilenetv1_1.0':
diff --git a/python/paddle/vision/models/mobilenetv2.py b/python/paddle/vision/models/mobilenetv2.py
index f1cbaab1f90accc616f5a93bba8d3fd6126770fb..74071fc121688eafbf17833a6410b94d34191ec4 100644
--- a/python/paddle/vision/models/mobilenetv2.py
+++ b/python/paddle/vision/models/mobilenetv2.py
@@ -20,7 +20,7 @@ import paddle.nn.functional as F
 
 from paddle.utils.download import get_weights_path_from_url
 
-__all__ = ['MobileNetV2', 'mobilenet_v2']
+__all__ = []
 
 model_urls = {
     'mobilenetv2_1.0':
diff --git a/python/paddle/vision/models/resnet.py b/python/paddle/vision/models/resnet.py
index 1f44e0bc6dfeb18cd1eb99489860500a390c33de..5be69c93e8b5f05f17f7d8c4503a794682a12d15 100644
--- a/python/paddle/vision/models/resnet.py
+++ b/python/paddle/vision/models/resnet.py
@@ -20,9 +20,7 @@ import paddle.nn as nn
 
 from paddle.utils.download import get_weights_path_from_url
 
-__all__ = [
-    'ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101', 'resnet152'
-]
+__all__ = []
 
 model_urls = {
     'resnet18': ('https://paddle-hapi.bj.bcebos.com/models/resnet18.pdparams',
diff --git a/python/paddle/vision/models/vgg.py b/python/paddle/vision/models/vgg.py
index f6b4c75e84f01379264fb2066b218747204fd6da..d526de8208329fb23ff4fad219db5dd706958ad8 100644
--- a/python/paddle/vision/models/vgg.py
+++ b/python/paddle/vision/models/vgg.py
@@ -17,13 +17,7 @@ import paddle.nn as nn
 
 from paddle.utils.download import get_weights_path_from_url
 
-__all__ = [
-    'VGG',
-    'vgg11',
-    'vgg13',
-    'vgg16',
-    'vgg19',
-]
+__all__ = []
 
 model_urls = {
     'vgg16': ('https://paddle-hapi.bj.bcebos.com/models/vgg16.pdparams',
diff --git a/python/paddle/vision/ops.py b/python/paddle/vision/ops.py
index 60a7a90c9be89591e681192f5e886f9c5443a8c0..53beedb885a7112bc9d3f3fc33bc1c48928e500d 100644
--- a/python/paddle/vision/ops.py
+++ b/python/paddle/vision/ops.py
@@ -22,8 +22,12 @@ from ..fluid.initializer import Normal
 
 from paddle.common_ops_import import *
 
-__all__ = [
-    'yolo_loss', 'yolo_box', 'deform_conv2d', 'DeformConv2D', 'read_file',
+__all__ = [ #noqa
+    'yolo_loss',
+    'yolo_box',
+    'deform_conv2d',
+    'DeformConv2D',
+    'read_file',
     'decode_jpeg'
 ]
 
diff --git a/python/paddle/vision/transforms/__init__.py b/python/paddle/vision/transforms/__init__.py
index f7c5b63b19ed081ee6887850c1aa3ef918715222..413f09f78699ee995f490e86a94006cd1a48c6a0 100644
--- a/python/paddle/vision/transforms/__init__.py
+++ b/python/paddle/vision/transforms/__init__.py
@@ -12,11 +12,70 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from . import transforms
-from . import functional
+from .transforms import BaseTransform  # noqa: F401
+from .transforms import Compose  # noqa: F401
+from .transforms import Resize  # noqa: F401
+from .transforms import RandomResizedCrop  # noqa: F401
+from .transforms import CenterCrop  # noqa: F401
+from .transforms import RandomHorizontalFlip  # noqa: F401
+from .transforms import RandomVerticalFlip  # noqa: F401
+from .transforms import Transpose  # noqa: F401
+from .transforms import Normalize  # noqa: F401
+from .transforms import BrightnessTransform  # noqa: F401
+from .transforms import SaturationTransform  # noqa: F401
+from .transforms import ContrastTransform  # noqa: F401
+from .transforms import HueTransform  # noqa: F401
+from .transforms import ColorJitter  # noqa: F401
+from .transforms import RandomCrop  # noqa: F401
+from .transforms import Pad  # noqa: F401
+from .transforms import RandomRotation  # noqa: F401
+from .transforms import Grayscale  # noqa: F401
+from .transforms import ToTensor  # noqa: F401
+from .functional import to_tensor  # noqa: F401
+from .functional import hflip  # noqa: F401
+from .functional import vflip  # noqa: F401
+from .functional import resize  # noqa: F401
+from .functional import pad  # noqa: F401
+from .functional import rotate  # noqa: F401
+from .functional import to_grayscale  # noqa: F401
+from .functional import crop  # noqa: F401
+from .functional import center_crop  # noqa: F401
+from .functional import adjust_brightness  # noqa: F401
+from .functional import adjust_contrast  # noqa: F401
+from .functional import adjust_hue  # noqa: F401
+from .functional import normalize  # noqa: F401
 
-from .transforms import *
-from .functional import *
-
-__all__ = transforms.__all__ \
-        + functional.__all__
+__all__ = [ #noqa
+    'BaseTransform',
+    'Compose',
+    'Resize',
+    'RandomResizedCrop',
+    'CenterCrop',
+    'RandomHorizontalFlip',
+    'RandomVerticalFlip',
+    'Transpose',
+    'Normalize',
+    'BrightnessTransform',
+    'SaturationTransform',
+    'ContrastTransform',
+    'HueTransform',
+    'ColorJitter',
+    'RandomCrop',
+    'Pad',
+    'RandomRotation',
+    'Grayscale',
+    'ToTensor',
+    'to_tensor',
+    'hflip',
+    'vflip',
+    'resize',
+    'pad',
+    'rotate',
+    'to_grayscale',
+    'crop',
+    'center_crop',
+    'adjust_brightness',
+    'adjust_contrast',
+    'adjust_hue',
+    'normalize'
+]
diff --git a/python/paddle/vision/transforms/functional.py b/python/paddle/vision/transforms/functional.py
index 18a35915c99da505678a2ab836d21dd0ace56ee6..3087d5c3ed57702e9bd4d8de7a9a2273876101c7 100644
--- a/python/paddle/vision/transforms/functional.py
+++ b/python/paddle/vision/transforms/functional.py
@@ -29,11 +29,7 @@ from . import functional_pil as F_pil
 from . import functional_cv2 as F_cv2
 from . import functional_tensor as F_t
 
-__all__ = [
-    'to_tensor', 'hflip', 'vflip', 'resize', 'pad', 'rotate', 'to_grayscale',
-    'crop', 'center_crop', 'adjust_brightness', 'adjust_contrast', 'adjust_hue',
-    'normalize'
-]
+__all__ = []
 
 
 def _is_pil_image(img):
diff --git a/python/paddle/vision/transforms/functional_cv2.py b/python/paddle/vision/transforms/functional_cv2.py
index 99cbfd6dc4f8dd195960b776864bc523bdca2c71..487d79d2765347759660d7d217d608f393ff90e4 100644
--- a/python/paddle/vision/transforms/functional_cv2.py
+++ b/python/paddle/vision/transforms/functional_cv2.py
@@ -33,6 +33,8 @@ else:
     Sequence = collections.abc.Sequence
     Iterable = collections.abc.Iterable
 
+__all__ = []
+
 
 def to_tensor(pic, data_format='CHW'):
     """Converts a ``numpy.ndarray`` to paddle.Tensor.
@@ -49,7 +51,7 @@ def to_tensor(pic, data_format='CHW'):
 
     """
 
-    if not data_format in ['CHW', 'HWC']:
+    if data_format not in ['CHW', 'HWC']:
         raise ValueError('data_format should be CHW or HWC. Got {}'.format(
             data_format))
 
diff --git a/python/paddle/vision/transforms/functional_pil.py b/python/paddle/vision/transforms/functional_pil.py
index eee60c5452b2de1235c577b2eabb8de1cfdc1467..ae6d0cc45a92ae543dc6308bc6ffa2680e0fcc4b 100644
--- a/python/paddle/vision/transforms/functional_pil.py
+++ b/python/paddle/vision/transforms/functional_pil.py
@@ -41,6 +41,8 @@ _pil_interp_from_str = {
     'hamming': Image.HAMMING
 }
 
+__all__ = []
+
 
 def to_tensor(pic, data_format='CHW'):
     """Converts a ``PIL.Image`` to paddle.Tensor.
@@ -57,7 +59,7 @@ def to_tensor(pic, data_format='CHW'):
 
     """
 
-    if not data_format in ['CHW', 'HWC']:
+    if data_format not in ['CHW', 'HWC']:
         raise ValueError('data_format should be CHW or HWC. Got {}'.format(
             data_format))
 
diff --git a/python/paddle/vision/transforms/functional_tensor.py b/python/paddle/vision/transforms/functional_tensor.py
index 7f490d57916fbcb67475cd433b09771d13261128..1ec67416998a3d03e391922ad078b827812661bf 100644
--- a/python/paddle/vision/transforms/functional_tensor.py
+++ b/python/paddle/vision/transforms/functional_tensor.py
@@ -23,6 +23,8 @@ import paddle.nn.functional as F
 import sys
 import collections
 
+__all__ = []
+
 
 def _assert_image_tensor(img, data_format):
     if not isinstance(
diff --git a/python/paddle/vision/transforms/transforms.py b/python/paddle/vision/transforms/transforms.py
index 00e12689c4d9fe41e67798309fee42ce63d0f7a5..8a35e6c3b908ea9fa782c428acc6797c6fb0986c 100644
--- a/python/paddle/vision/transforms/transforms.py
+++ b/python/paddle/vision/transforms/transforms.py
@@ -35,13 +35,7 @@ else:
     Sequence = collections.abc.Sequence
     Iterable = collections.abc.Iterable
 
-__all__ = [
-    "BaseTransform", "Compose", "Resize", "RandomResizedCrop", "CenterCrop",
-    "RandomHorizontalFlip", "RandomVerticalFlip", "Transpose", "Normalize",
-    "BrightnessTransform", "SaturationTransform", "ContrastTransform",
-    "HueTransform", "ColorJitter", "RandomCrop", "Pad", "RandomRotation",
-    "Grayscale", "ToTensor"
-]
+__all__ = []
 
 
 def _get_image_size(img):