diff --git a/example/tutorial_bipedalwalker_a3c_continuous_action.py b/example/tutorial_bipedalwalker_a3c_continuous_action.py
index ae3f66736..e861f5124 100644
--- a/example/tutorial_bipedalwalker_a3c_continuous_action.py
+++ b/example/tutorial_bipedalwalker_a3c_continuous_action.py
@@ -32,8 +32,6 @@
 """
 
 import multiprocessing
-import os
-import shutil
 import threading
 
 import gym
@@ -257,8 +255,7 @@ def work(self):
     # start TF threading
     worker_threads = []
     for worker in workers:
-        job = lambda: worker.work()
-        t = threading.Thread(target=job)
+        t = threading.Thread(target=worker.work)
         t.start()
         worker_threads.append(t)
     COORD.join(worker_threads)
diff --git a/example/tutorial_cifar10_tfrecord.py b/example/tutorial_cifar10_tfrecord.py
index 6df316217..65d32c7ef 100644
--- a/example/tutorial_cifar10_tfrecord.py
+++ b/example/tutorial_cifar10_tfrecord.py
@@ -42,7 +42,7 @@
 import io
 import os
 import time
-import numpy as np
+# import numpy as np
 import tensorflow as tf
 import tensorlayer as tl
 from PIL import Image
diff --git a/example/tutorial_imdb_fasttext.py b/example/tutorial_imdb_fasttext.py
index a5c542dc0..437e62b76 100644
--- a/example/tutorial_imdb_fasttext.py
+++ b/example/tutorial_imdb_fasttext.py
@@ -1,10 +1,9 @@
 #!/usr/bin/env python
+"""
+This demo implements FastText[1] for sentence classification.
 
-__doc__ = """
-
-This demo implements FastText[1] for sentence classification. FastText is a
-simple model for text classification with performance often close to
-state-of-the-art, and is useful as a solid baseline.
+FastText is a simple model for text classification with performance often close
+to state-of-the-art, and is useful as a solid baseline.
 
 There are some important differences between this implementation and what
 is described in the paper. Instead of Hogwild! SGD[2], we use Adam optimizer
diff --git a/example/tutorial_inceptionV3_tfslim.py b/example/tutorial_inceptionV3_tfslim.py
index dd5e58901..08b98dc85 100644
--- a/example/tutorial_inceptionV3_tfslim.py
+++ b/example/tutorial_inceptionV3_tfslim.py
@@ -46,7 +46,8 @@ def load_image(path):
     # load image
     img = skimage.io.imread(path)
     img = img / 255.0
-    assert (0 <= img).all() and (img <= 1.0).all()
+    if ((0 <= img).all() and (img <= 1.0).all()) is False:
+        raise Exception("image value should be [0, 1]")
     # print "Original Image Shape: ", img.shape
     # we crop image from center
     short_edge = min(img.shape[:2])
diff --git a/example/tutorial_matrix.py b/example/tutorial_matrix.py
index 50e329140..9c1478bd2 100644
--- a/example/tutorial_matrix.py
+++ b/example/tutorial_matrix.py
@@ -1,5 +1,4 @@
 import tensorflow as tf
-import tensorlayer as tl
 
 sess = tf.InteractiveSession()
 
diff --git a/example/tutorial_ptb_lstm.py b/example/tutorial_ptb_lstm.py
index d75f97940..ea1a18fff 100644
--- a/example/tutorial_ptb_lstm.py
+++ b/example/tutorial_ptb_lstm.py
@@ -104,7 +104,6 @@
 import numpy as np
 import tensorflow as tf
 import tensorlayer as tl
-from tensorlayer.layers import set_keep
 
 flags = tf.flags
 flags.DEFINE_string("model", "small", "A type of model. Possible options are: small, medium, large.")
diff --git a/example/tutorial_vgg16.py b/example/tutorial_vgg16.py
index 9a33aa693..1f376fd30 100644
--- a/example/tutorial_vgg16.py
+++ b/example/tutorial_vgg16.py
@@ -166,7 +166,7 @@ def conv_layers(net_in):
 
 
 def conv_layers_simple_api(net_in):
-    with tf.name_scope('preprocess') as scope:
+    with tf.name_scope('preprocess'):
         """
         Notice that we include a preprocessing layer that takes the RGB image
         with pixels values in the range of 0-255 and subtracts the mean image
diff --git a/tensorlayer/db.py b/tensorlayer/db.py
index 6b0b6c3fe..d4782c7b0 100644
--- a/tensorlayer/db.py
+++ b/tensorlayer/db.py
@@ -85,13 +85,16 @@ def __init__(self, ip='localhost', port=27017, db_name='db_name', user_name=None
         self.db_name = db_name
         self.user_name = user_name
 
+    @classmethod
     def __autofill(self, args):
         return args.update({'studyID': self.studyID})
 
-    def __serialization(self, ps):
+    @staticmethod
+    def __serialization(ps):
         return pickle.dumps(ps, protocol=2)
 
-    def __deserialization(self, ps):
+    @staticmethod
+    def __deserialization(ps):
         return pickle.loads(ps)
 
     def save_params(self, params=None, args=None):  #, file_name='parameters'):
@@ -298,20 +301,25 @@ def test_log(self, args=None):
         return _result
 
     @AutoFill
-    def del_test_log(self, args={}):
+    def del_test_log(self, args=None):
         """ Delete test log.
 
         Parameters
         -----------
         args : dictionary, find items to delete, leave it empty to delete all log.
         """
+        if args is None:
+            args = {}
 
         self.db.TestLog.delete_many(args)
         print("[TensorDB] Delete TestLog SUCCESS")
 
-    ## =========================== Network Architecture ================== ##
+    # =========================== Network Architecture ================== ##
     @AutoFill
-    def save_model_architecture(self, s, args={}):
+    def save_model_architecture(self, s, args=None):
+        if args is None:
+            args = {}
+
         self.__autofill(args)
         fid = self.archfs.put(s, filename="modelarchitecture")
         args.update({"fid": fid})
diff --git a/tensorlayer/files.py b/tensorlayer/files.py
index b866f0dbc..e8fa7ff2b 100644
--- a/tensorlayer/files.py
+++ b/tensorlayer/files.py
@@ -594,7 +594,7 @@ def load_flickr25k_dataset(tag='sky', path="data", n_threads=50, printable=False
     else:
         logging.info("[Flickr25k] reading images with tag: {}".format(tag))
     images_list = []
-    for idx in range(0, len(path_tags)):
+    for idx, _v in enumerate(path_tags):
         tags = read_file(folder_tags + '/' + path_tags[idx]).split('\n')
         # logging.info(idx+1, tags)
         if tag is None or tag in tags:
@@ -1459,6 +1459,13 @@ def load_ckpt(sess=None, mode_name='model.ckpt', save_dir='checkpoint', var_list
 def save_any_to_npy(save_dict={}, name='file.npy'):
     """Save variables to `.npy` file.
 
+    Parameters
+    ------------
+    save_dict : directory
+        The variables to be saved.
+    name : str
+        File name.
+
     Examples
     ---------
     >>> tl.files.save_any_to_npy(save_dict={'data': ['a','b']}, name='test.npy')
@@ -1467,12 +1474,21 @@ def save_any_to_npy(save_dict={}, name='file.npy'):
     ... {'data': ['a','b']}
 
     """
+    if save_dict is None:
+        save_dict = {}
     np.save(name, save_dict)
 
 
 def load_npy_to_any(path='', name='file.npy'):
     """Load `.npy` file.
 
+    Parameters
+    ------------
+    path : str
+        Path to the file (optional).
+    name : str
+        File name.
+
     Examples
     ---------
     - see tl.files.save_any_to_npy()
diff --git a/tensorlayer/layers/convolution.py b/tensorlayer/layers/convolution.py
index 748939716..25dae143f 100644
--- a/tensorlayer/layers/convolution.py
+++ b/tensorlayer/layers/convolution.py
@@ -302,7 +302,7 @@ def __init__(
         logging.info("DeConv2dLayer %s: shape:%s out_shape:%s strides:%s pad:%s act:%s" % (self.name, str(shape), str(output_shape), str(strides), padding,
                                                                                            act.__name__))
         # logging.info("  DeConv2dLayer: Untested")
-        with tf.variable_scope(name) as vs:
+        with tf.variable_scope(name):
             W = tf.get_variable(name='W_deconv2d', shape=shape, initializer=W_init, dtype=D_TYPE, **W_init_args)
             if b_init:
                 b = tf.get_variable(name='b_deconv2d', shape=(shape[-2]), initializer=b_init, dtype=D_TYPE, **b_init_args)
diff --git a/tensorlayer/layers/core.py b/tensorlayer/layers/core.py
index e251bf7a1..c0d153823 100644
--- a/tensorlayer/layers/core.py
+++ b/tensorlayer/layers/core.py
@@ -6,7 +6,7 @@
 import tensorflow as tf
 
 from .. import _logging as logging
-from .. import cost, files, iterate, utils, visualize
+from .. import files, iterate, utils, visualize
 
 # __all__ = [
 #     "Layer",
@@ -289,11 +289,13 @@ def list_remove_repeat(x):
 
     """
     y = []
-    [y.append(i) for i in x if not i in y]
+    for i in x:
+        if not i in y:
+            y.append(i)
     return y
 
 
-def merge_networks(layers=[]):
+def merge_networks(layers=None):
     """Merge all parameters, layers and dropout probabilities to a :class:`Layer`.
     The output of return network is the first network in the list.
 
@@ -314,6 +316,8 @@ def merge_networks(layers=[]):
     >>> n1 = tl.layers.merge_networks([n1, n2])
 
     """
+    if layers is None:
+        raise Exception("layers should be a list of TensorLayer's Layers.")
     layer = layers[0]
 
     all_params = []
@@ -702,7 +706,7 @@ def __init__(
         self.inputs = inputs
         logging.info("EmbeddingInputlayer %s: (%d, %d)" % (self.name, vocabulary_size, embedding_size))
 
-        with tf.variable_scope(name) as vs:
+        with tf.variable_scope(name):
             embeddings = tf.get_variable(name='embeddings', shape=(vocabulary_size, embedding_size), initializer=E_init, dtype=D_TYPE, **E_init_args)
             embed = tf.nn.embedding_lookup(embeddings, self.inputs)
 
diff --git a/tensorlayer/layers/extend.py b/tensorlayer/layers/extend.py
index e9a96fee9..bcf749d83 100644
--- a/tensorlayer/layers/extend.py
+++ b/tensorlayer/layers/extend.py
@@ -68,7 +68,7 @@ def __init__(
         self.inputs = layer.outputs
 
         logging.info("TileLayer  %s: multiples:%s" % (self.name, multiples))
-        with tf.variable_scope(name) as vs:
+        with tf.variable_scope(name):
             self.outputs = tf.tile(self.inputs, multiples=multiples)
         self.all_layers = list(layer.all_layers)
         self.all_params = list(layer.all_params)
diff --git a/tensorlayer/layers/importer.py b/tensorlayer/layers/importer.py
index 87711aef9..1dd02eb30 100644
--- a/tensorlayer/layers/importer.py
+++ b/tensorlayer/layers/importer.py
@@ -13,7 +13,7 @@ class LambdaLayer(Layer):
         Previous layer.
     fn : function
         The function that applies to the outputs of previous layer.
-    fn_args : dictionary
+    fn_args : dictionary or None
         The arguments for the function (option).
     name : str
         A unique layer name.
@@ -47,9 +47,11 @@ def __init__(
             self,
             layer,
             fn,
-            fn_args={},
+            fn_args=None,
             name='lambda_layer',
     ):
+        if fn_args is None:
+            fn_args = {}
         Layer.__init__(self, name=name)
         assert layer is not None
         assert fn is not None
diff --git a/tensorlayer/layers/merge.py b/tensorlayer/layers/merge.py
index 40a9c113f..1f4775c83 100644
--- a/tensorlayer/layers/merge.py
+++ b/tensorlayer/layers/merge.py
@@ -68,7 +68,6 @@ def __init__(
 
         self.all_layers = list_remove_repeat(self.all_layers)
         self.all_params = list_remove_repeat(self.all_params)
-        #self.all_drop = list_remove_repeat(self.all_drop) # it is a dict
 
 
 class ElementwiseLayer(Layer):
@@ -112,8 +111,8 @@ def __init__(
         self.outputs = layers[0].outputs
         # logging.info(self.outputs._shape, type(self.outputs._shape))
         for l in layers[1:]:
-            assert str(self.outputs.get_shape()) == str(
-                l.outputs.get_shape()), "Hint: the input shapes should be the same. %s != %s" % (self.outputs.get_shape(), str(l.outputs.get_shape()))
+            if str(self.outputs.get_shape()) != str(l.outputs.get_shape()):
+                raise Exception("Hint: the input shapes should be the same. %s != %s" % (self.outputs.get_shape(), str(l.outputs.get_shape())))
             self.outputs = combine_fn(self.outputs, l.outputs, name=name)
 
         self.all_layers = list(layers[0].all_layers)
diff --git a/tensorlayer/layers/recurrent.py b/tensorlayer/layers/recurrent.py
index e16dc0985..1bb79720c 100644
--- a/tensorlayer/layers/recurrent.py
+++ b/tensorlayer/layers/recurrent.py
@@ -256,7 +256,7 @@ class BiRNNLayer(Layer):
         A TensorFlow core RNN cell.
             - See `RNN Cells in TensorFlow <https://www.tensorflow.org/api_docs/python/>`__.
             - Note TF1.0+ and TF1.0- are different.
-    cell_init_args : dictionary
+    cell_init_args : dictionary or None
         The arguments for the cell function.
     n_hidden : int
         The number of hidden units in the layer.
@@ -316,10 +316,7 @@ def __init__(
             self,
             layer,
             cell_fn,
-            cell_init_args={
-                'use_peepholes': True,
-                'state_is_tuple': True
-            },
+            cell_init_args=None,
             n_hidden=100,
             initializer=tf.random_uniform_initializer(-0.1, 0.1),
             n_steps=5,
@@ -331,6 +328,9 @@ def __init__(
             return_seq_2d=False,
             name='birnn_layer',
     ):
+        if cell_init_args is None:
+            cell_init_args = {'use_peepholes': True, 'state_is_tuple': True}
+
         Layer.__init__(self, name=name)
         if cell_fn is None:
             raise Exception("Please put in cell_fn")
@@ -427,7 +427,7 @@ def __init__(
 
             if return_last:
                 raise Exception("Do not support return_last at the moment.")
-                self.outputs = outputs[-1]
+                # self.outputs = outputs[-1]
             else:
                 self.outputs = outputs
                 if return_seq_2d:
@@ -752,13 +752,13 @@ def __init__(
 
 
 # Advanced Ops for Dynamic RNN
-def advanced_indexing_op(input, index):
+def advanced_indexing_op(inputs, index):
     """Advanced Indexing for Sequences, returns the outputs by given sequence lengths.
     When return the last output :class:`DynamicRNNLayer` uses it to get the last outputs with the sequence lengths.
 
     Parameters
     -----------
-    input : tensor for data
+    inputs : tensor for data
         With shape of [batch_size, n_step(max), n_features]
     index : tensor for indexing
         Sequence length in Dynamic RNN. [batch_size]
@@ -790,12 +790,12 @@ def advanced_indexing_op(input, index):
     - Modified from TFlearn (the original code is used for fixed length rnn), `references <https://github.com/tflearn/tflearn/blob/master/tflearn/layers/recurrent.py>`__.
 
     """
-    batch_size = tf.shape(input)[0]
-    # max_length = int(input.get_shape()[1])    # for fixed length rnn, length is given
-    max_length = tf.shape(input)[1]  # for dynamic_rnn, length is unknown
-    dim_size = int(input.get_shape()[2])
+    batch_size = tf.shape(inputs)[0]
+    # max_length = int(inputs.get_shape()[1])    # for fixed length rnn, length is given
+    max_length = tf.shape(inputs)[1]  # for dynamic_rnn, length is unknown
+    dim_size = int(inputs.get_shape()[2])
     index = tf.range(0, batch_size) * max_length + (index - 1)
-    flat = tf.reshape(input, [-1, dim_size])
+    flat = tf.reshape(inputs, [-1, dim_size])
     relevant = tf.gather(flat, index)
     return relevant
 
@@ -1076,7 +1076,7 @@ def __init__(
             #                     cell_instance_fn1(),
             #                     input_keep_prob=in_keep_prob,
             #                     output_keep_prob=out_keep_prob)
-            cell_creator = lambda: DropoutWrapper_fn(rnn_creator(), input_keep_prob=in_keep_prob, output_keep_prob=1.0)  #out_keep_prob)
+            cell_creator = lambda: DropoutWrapper_fn(rnn_creator(), input_keep_prob=in_keep_prob, output_keep_prob=1.0)
         else:
             cell_creator = rnn_creator
         self.cell = cell_creator()
@@ -1323,9 +1323,9 @@ def __init__(
                 cell_creator = lambda is_last=True: \
                     DropoutWrapper_fn(rnn_creator(),
                                       input_keep_prob=in_keep_prob,
-                                      output_keep_prob=out_keep_prob if is_last else 1.0)  # out_keep_prob)
+                                      output_keep_prob=out_keep_prob if is_last else 1.0)
             else:
-                cell_creator = lambda: rnn_creator()
+                cell_creator = rnn_creator
 
             # if dropout:
             #     self.fw_cell = DropoutWrapper_fn(self.fw_cell, input_keep_prob=1.0, output_keep_prob=out_keep_prob)
@@ -1374,15 +1374,17 @@ def __init__(
             rnn_variables = tf.get_collection(TF_GRAPHKEYS_VARIABLES, scope=vs.name)
 
             logging.info("     n_params : %d" % (len(rnn_variables)))
+
             # Manage the outputs
             try:  # TF1.0
                 outputs = tf.concat(outputs, 2)
             except Exception:  # TF0.12
                 outputs = tf.concat(2, outputs)
+
             if return_last:
                 # [batch_size, 2 * n_hidden]
-                raise Exception("Do not support return_last at the moment")
-                self.outputs = advanced_indexing_op(outputs, sequence_length)
+                raise NotImplementedError("Return last is not implemented yet.")
+                # self.outputs = advanced_indexing_op(outputs, sequence_length)
             else:
                 # [batch_size, n_step(max), 2 * n_hidden]
                 if return_seq_2d:
@@ -1401,7 +1403,6 @@ def __init__(
                         self.outputs = tf.reshape(tf.concat(outputs, 1), [batch_size, max_length, 2 * n_hidden])
                     except Exception:  # TF0.12
                         self.outputs = tf.reshape(tf.concat(1, outputs), [batch_size, max_length, 2 * n_hidden])
-                    # self.outputs = tf.reshape(tf.concat(1, outputs), [-1, max_length, 2 * n_hidden])
 
         # Final state
         self.fw_final_states = states_fw
@@ -1417,7 +1418,6 @@ def __init__(
         self.all_params.extend(rnn_variables)
 
 
-# Seq2seq
 class Seq2Seq(Layer):
     """
     The :class:`Seq2Seq` class is a simple :class:`DynamicRNNLayer` based Seq2seq layer without using `tl.contrib.seq2seq <https://www.tensorflow.org/api_guides/python/contrib.seq2seq>`__.
diff --git a/tensorlayer/layers/special_activation.py b/tensorlayer/layers/special_activation.py
index 576f353e1..1cf80acc9 100644
--- a/tensorlayer/layers/special_activation.py
+++ b/tensorlayer/layers/special_activation.py
@@ -50,7 +50,7 @@ def __init__(
             alphas = tf.get_variable(name='alphas', shape=w_shape, initializer=a_init, dtype=D_TYPE, **a_init_args)
             try:  # TF 1.0
                 self.outputs = tf.nn.relu(self.inputs) + tf.multiply(alphas, (self.inputs - tf.abs(self.inputs))) * 0.5
-            except:  # TF 0.12
+            except Exception:  # TF 0.12
                 self.outputs = tf.nn.relu(self.inputs) + tf.mul(alphas, (self.inputs - tf.abs(self.inputs))) * 0.5
 
         self.all_layers = list(layer.all_layers)
diff --git a/tensorlayer/layers/stack.py b/tensorlayer/layers/stack.py
index 1ec94ddfb..d5ba3928d 100644
--- a/tensorlayer/layers/stack.py
+++ b/tensorlayer/layers/stack.py
@@ -68,7 +68,7 @@ def unstack_layer(layer, num=None, axis=0, name='unstack'):
 
     """
     inputs = layer.outputs
-    with tf.variable_scope(name) as vs:
+    with tf.variable_scope(name):
         outputs = tf.unstack(inputs, num=num, axis=axis)
 
     logging.info("UnStackLayer %s: num: %s axis: %d, n_outputs: %d" % (name, num, axis, len(outputs)))
diff --git a/tensorlayer/layers/super_resolution.py b/tensorlayer/layers/super_resolution.py
index 2ce06ef47..02e41655e 100644
--- a/tensorlayer/layers/super_resolution.py
+++ b/tensorlayer/layers/super_resolution.py
@@ -94,7 +94,7 @@ def _PS(X, r, n_out_channels):
 
     net_new = Layer(inputs, name=whole_name)
     # with tf.name_scope(name):
-    with tf.variable_scope(name) as vs:
+    with tf.variable_scope(name):
         net_new.outputs = act(_PS(inputs, r=scale, n_out_channels=n_out_channel))
 
     net_new.all_layers = list(net.all_layers)
diff --git a/tensorlayer/nlp.py b/tensorlayer/nlp.py
index 6d9efe0fb..b82f604a0 100755
--- a/tensorlayer/nlp.py
+++ b/tensorlayer/nlp.py
@@ -67,8 +67,11 @@ def generate_skip_gram_batch(data, batch_size, num_skips, skip_window, data_inde
     # global data_index   # you can put data_index outside the function, then
     #       modify the global data_index in the function without return it.
     # note: without using yield, this code use data_index to instead.
-    assert batch_size % num_skips == 0
-    assert num_skips <= 2 * skip_window
+
+    if batch_size % num_skips != 0:
+        raise Exception("batch_size should be able to be divided by num_skips.")
+    if num_skips > 2 * skip_window:
+        raise Exception("num_skips <= 2 * skip_window")
     batch = np.ndarray(shape=(batch_size), dtype=np.int32)
     labels = np.ndarray(shape=(batch_size, 1), dtype=np.int32)
     span = 2 * skip_window + 1  # [ skip_window target skip_window ]
@@ -90,7 +93,7 @@ def generate_skip_gram_batch(data, batch_size, num_skips, skip_window, data_inde
     return batch, labels, data_index
 
 
-def sample(a=[], temperature=1.0):
+def sample(a=None, temperature=1.0):
     """Sample an index from a probability array.
 
     Parameters
@@ -110,6 +113,8 @@ def sample(a=[], temperature=1.0):
     - For large vocabulary size, choice a higher temperature or ``tl.nlp.sample_top`` to avoid error.
 
     """
+    if a is None:
+        raise Exception("a : list of float")
     b = np.copy(a)
     try:
         if temperature == 1:
@@ -120,7 +125,7 @@ def sample(a=[], temperature=1.0):
             a = np.log(a) / temperature
             a = np.exp(a) / np.sum(np.exp(a))
             return np.argmax(np.random.multinomial(1, a, 1))
-    except:
+    except Exception:
         # np.set_printoptions(threshold=np.nan)
         # logging.info(a)
         # logging.info(np.sum(a))
@@ -472,7 +477,7 @@ def read_words(filename="nietzsche.txt", replace=None):
     with tf.gfile.GFile(filename, "r") as f:
         try:  # python 3.4 or older
             context_list = f.read().replace(*replace).split()
-        except:  # python 3.5
+        except Exception:  # python 3.5
             f.seek(0)
             replace = [x.encode('utf-8') for x in replace]
             context_list = f.read().replace(*replace).split()
@@ -605,7 +610,7 @@ def build_reverse_dictionary(word_to_id):
     return reverse_dictionary
 
 
-def build_words_dataset(words=[], vocabulary_size=50000, printable=True, unk_key='UNK'):
+def build_words_dataset(words=None, vocabulary_size=50000, printable=True, unk_key='UNK'):
     """Build the words dictionary and replace rare words with 'UNK' token.
     The most common word has the smallest integer id.
 
@@ -645,6 +650,8 @@ def build_words_dataset(words=[], vocabulary_size=50000, printable=True, unk_key
     - `tensorflow/examples/tutorials/word2vec/word2vec_basic.py <https://github.com/tensorflow/tensorflow/blob/r0.7/tensorflow/examples/tutorials/word2vec/word2vec_basic.py>`__
 
     """
+    if words is None:
+        raise Exception("words : list of str or byte")
     import collections
     count = [[unk_key, -1]]
     count.extend(collections.Counter(words).most_common(vocabulary_size - 1))
@@ -665,12 +672,13 @@ def build_words_dataset(words=[], vocabulary_size=50000, printable=True, unk_key
     if printable:
         logging.info('Real vocabulary size    %d' % len(collections.Counter(words).keys()))
         logging.info('Limited vocabulary size {}'.format(vocabulary_size))
-    assert len(collections.Counter(words).keys()) >= vocabulary_size, \
-        "the limited vocabulary_size must be less than or equal to the read vocabulary_size"
+    if len(collections.Counter(words).keys()) < vocabulary_size:
+        raise Exception(
+            "len(collections.Counter(words).keys()) >= vocabulary_size , the limited vocabulary_size must be less than or equal to the read vocabulary_size")
     return data, count, dictionary, reverse_dictionary
 
 
-def words_to_word_ids(data=[], word_to_id={}, unk_key='UNK'):
+def words_to_word_ids(data=None, word_to_id=None, unk_key='UNK'):
     """Convert a list of string (words) to IDs.
 
     Parameters
@@ -705,6 +713,10 @@ def words_to_word_ids(data=[], word_to_id={}, unk_key='UNK'):
     - `tensorflow.models.rnn.ptb.reader <https://github.com/tensorflow/tensorflow/tree/master/tensorflow/models/rnn/ptb>`__
 
     """
+    if data is None:
+        raise Exception("data : list of string or byte")
+    if word_to_id is None:
+        raise Exception("word_to_id : a dictionary")
     # if isinstance(data[0], six.string_types):
     #     logging.info(type(data[0]))
     #     # exit()
@@ -832,13 +844,7 @@ def basic_tokenizer(sentence, _WORD_SPLIT=re.compile(b"([.,!?\"':;)(])")):
     return [w for w in words if w]
 
 
-def create_vocabulary(vocabulary_path,
-                      data_path,
-                      max_vocabulary_size,
-                      tokenizer=None,
-                      normalize_digits=True,
-                      _DIGIT_RE=re.compile(br"\d"),
-                      _START_VOCAB=[b"_PAD", b"_GO", b"_EOS", b"_UNK"]):
+def create_vocabulary(vocabulary_path, data_path, max_vocabulary_size, tokenizer=None, normalize_digits=True, _DIGIT_RE=re.compile(br"\d"), _START_VOCAB=None):
     """Create vocabulary file (if it does not exist yet) from data file.
 
     Data file is assumed to contain one sentence per line. Each sentence is
@@ -859,12 +865,18 @@ def create_vocabulary(vocabulary_path,
         A function to use to tokenize each data sentence. If None, basic_tokenizer will be used.
     normalize_digits : boolean
         If true, all digits are replaced by `0`.
+    _DIGIT_RE : regular expression function
+        Default is ``re.compile(br"\d")``.
+    _START_VOCAB : list of str
+        The pad, go, eos and unk token, default is ``[b"_PAD", b"_GO", b"_EOS", b"_UNK"]``.
 
     References
     ----------
     - Code from ``/tensorflow/models/rnn/translation/data_utils.py``
 
     """
+    if _START_VOCAB is None:
+        _START_VOCAB = [b"_PAD", b"_GO", b"_EOS", b"_UNK"]
     if not gfile.Exists(vocabulary_path):
         logging.info("Creating vocabulary %s from data %s" % (vocabulary_path, data_path))
         vocab = {}
diff --git a/tensorlayer/prepro.py b/tensorlayer/prepro.py
index 68d85b8a5..133ed4a36 100644
--- a/tensorlayer/prepro.py
+++ b/tensorlayer/prepro.py
@@ -794,7 +794,7 @@ def elastic_transform(x, alpha, sigma, mode="constant", cval=0, is_random=False)
         is_3d = True
     elif len(x.shape) == 3 and x.shape[-1] != 1:
         raise Exception("Only support greyscale image")
-    assert len(x.shape) == 2
+    assert len(x.shape) == 2, "input should be grey-scale image"
 
     shape = x.shape
 
@@ -843,7 +843,7 @@ def elastic_transform_multi(x, alpha, sigma, mode="constant", cval=0, is_random=
             is_3d = True
         elif len(data.shape) == 3 and data.shape[-1] != 1:
             raise Exception("Only support greyscale image")
-        assert len(data.shape) == 2
+        assert len(data.shape) == 2, "input should be grey-scale image"
 
         dx = gaussian_filter((new_shape * 2 - 1), sigma, mode=mode, cval=cval) * alpha
         dy = gaussian_filter((new_shape * 2 - 1), sigma, mode=mode, cval=cval) * alpha
@@ -1270,7 +1270,7 @@ def imresize(x, size=None, interp='bicubic', mode=None):
 
 
 # value scale
-def pixel_value_scale(im, val=0.9, clip=[], is_random=False):
+def pixel_value_scale(im, val=0.9, clip=(-np.inf, np.inf), is_random=False):
     """Scales each value in the pixels of the image.
 
     Parameters
@@ -1281,6 +1281,10 @@ def pixel_value_scale(im, val=0.9, clip=[], is_random=False):
         The scale value for changing pixel value.
             - If is_random=False, multiply this value with all pixels.
             - If is_random=True, multiply a value between [1-val, 1+val] with all pixels.
+    clip : tuple of 2 numbers
+        The minimum and maximum value.
+    is_random : boolean
+        If True, see ``val``.
 
     Returns
     -------
@@ -1306,6 +1310,8 @@ def pixel_value_scale(im, val=0.9, clip=[], is_random=False):
 
     if len(clip) == 2:
         im = np.clip(im, clip[0], clip[1])
+    else:
+        raise Exception("clip : tuple of 2 numbers")
 
     return im
 
@@ -1708,9 +1714,11 @@ def projective_transform_by_points(x, src, dst, map_args=None, output_shape=None
     """
     if map_args is None:
         map_args = {}
-    if type(src) is list:  # convert to numpy
+    # if type(src) is list:
+    if isinstance(src, list):  # convert to numpy
         src = np.array(src)
-    if type(dst) is list:
+    # if type(dst) is list:
+    if isinstance(dst, list):
         dst = np.array(dst)
     if np.max(x) > 1:  # convert to [0, 1]
         x = x / 255
@@ -1792,13 +1800,13 @@ def find_contours(x, level=0.8, fully_connected='low', positive_orientation='low
     return skimage.measure.find_contours(x, level, fully_connected=fully_connected, positive_orientation=positive_orientation)
 
 
-def pt2map(list_points=[], size=(100, 100), val=1):
+def pt2map(list_points=None, size=(100, 100), val=1):
     """Inputs a list of points, return a 2D image.
 
     Parameters
     --------------
     list_points : list of 2 int
-        [x, y] for point coordinates.
+        [[x, y], [x, y]..] for point coordinates.
     size : tuple of 2 int
         (w, h) for output size.
     val : float or int
@@ -1810,6 +1818,8 @@ def pt2map(list_points=[], size=(100, 100), val=1):
         An image.
 
     """
+    if list_points is None:
+        raise Exception("list_points : list of 2 int")
     i_m = np.zeros(size)
     if len(list_points) == 0:
         return i_m
@@ -2195,9 +2205,9 @@ def parse_darknet_ann_list_to_cls_box(annotations):
     """
     class_list = []
     bbox_list = []
-    for i in range(len(annotations)):
-        class_list.append(annotations[i][0])
-        bbox_list.append(annotations[i][1:])
+    for ann in annotations:
+        class_list.append(ann[0])
+        bbox_list.append(ann[1:])
     return class_list, bbox_list
 
 
diff --git a/tensorlayer/rein.py b/tensorlayer/rein.py
index bec9daf38..c5c2d2811 100644
--- a/tensorlayer/rein.py
+++ b/tensorlayer/rein.py
@@ -118,7 +118,7 @@ def log_weight(probs, weights, name='log_weight'):
         return exp_v
 
 
-def choice_action_by_probs(probs=[0.5, 0.5], action_list=None):
+def choice_action_by_probs(probs=(0.5, 0.5), action_list=None):
     """Choice and return an an action by given the action probability distribution.
 
     Parameters
diff --git a/tensorlayer/utils.py b/tensorlayer/utils.py
index a63ff6e57..1f1bb469b 100644
--- a/tensorlayer/utils.py
+++ b/tensorlayer/utils.py
@@ -491,12 +491,23 @@ def class_balancing_oversample(X_train=None, y_train=None, printable=True):
 
 
 ## Random
-def get_random_int(min=0, max=10, number=5, seed=None):
+def get_random_int(min_v=0, max_v=10, number=5, seed=None):
     """Return a list of random integer by the given range and quantity.
 
+    Parameters
+    -----------
+    min_v : number
+        The minimum value.
+    max_v : number
+        The maximum value.
+    number : int
+        Number of value.
+    seed : int or None
+        The seed for random.
+
     Examples
     ---------
-    >>> r = get_random_int(min=0, max=10, number=5)
+    >>> r = get_random_int(min_v=0, max_v=10, number=5)
     ... [10, 2, 3, 3, 7]
 
     """
@@ -504,7 +515,7 @@ def get_random_int(min=0, max=10, number=5, seed=None):
     if seed:
         rnd = random.Random(seed)
     # return [random.randint(min,max) for p in range(0, number)]
-    return [rnd.randint(min, max) for p in range(0, number)]
+    return [rnd.randint(min_v, max_v) for p in range(0, number)]
 
 
 def list_string_to_dict(string):
@@ -528,7 +539,7 @@ def exit_tensorflow(sess=None, port=6006):
     """
     text = "[TL] Close tensorboard and nvidia-process if available"
     text2 = "[TL] Close tensorboard and nvidia-process not yet supported by this function (tl.ops.exit_tf) on "
-    if sess != None:
+    if sess is not None:
         sess.close()
     # import time
     # time.sleep(2)
@@ -542,8 +553,7 @@ def exit_tensorflow(sess=None, port=6006):
         logging.info('OS X: %s' % text)
         subprocess.Popen("lsof -i tcp:" + str(port) + "  | grep -v PID | awk '{print $2}' | xargs kill", shell=True)  # kill tensorboard
     elif _platform == "win32":
-        logging.info(text2 + "Windows")
-        # TODO
+        raise NotImplementedError("this function is not supported on the Windows platform")
     else:
         logging.info(text2 + _platform)
 
@@ -566,16 +576,14 @@ def open_tensorboard(log_dir='/tmp/tensorflow', port=6006):
         logging.info("[TL] Log reportory was created at %s" % log_dir)
 
     if _platform == "linux" or _platform == "linux2":
-        logging.info('linux %s' % text2)
-        # TODO
+        raise NotImplementedError()
     elif _platform == "darwin":
         logging.info('OS X: %s' % text)
         subprocess.Popen(
             sys.prefix + " | python -m tensorflow.tensorboard --logdir=" + log_dir + " --port=" + str(port),
             shell=True)  # open tensorboard in localhost:6006/ or whatever port you chose
     elif _platform == "win32":
-        logging.info('Windows%s' % text2)
-        # TODO
+        raise NotImplementedError("this function is not supported on the Windows platform")
     else:
         logging.info(_platform + text2)
 
diff --git a/tensorlayer/visualize.py b/tensorlayer/visualize.py
index 3cec6225b..f1edbbd65 100644
--- a/tensorlayer/visualize.py
+++ b/tensorlayer/visualize.py
@@ -289,7 +289,7 @@ def CNN2d(CNN=None, second=10, saveable=True, name='cnn', fig_idx=3119362):
         for _ic in range(1, col + 1):
             if count > n_mask:
                 break
-            a = fig.add_subplot(col, row, count)
+            fig.add_subplot(col, row, count)
             # logging.info(CNN[:,:,:,count-1].shape, n_row, n_col)   # (5, 1, 32) 5 5
             # exit()
             # plt.imshow(
@@ -349,8 +349,8 @@ def images2d(images=None, second=10, saveable=True, name='images', dtype=None, f
     plt.ion()  # active mode
     fig = plt.figure(fig_idx)
     count = 1
-    for ir in range(1, row + 1):
-        for ic in range(1, col + 1):
+    for _ir in range(1, row + 1):
+        for _ic in range(1, col + 1):
             if count > n_mask:
                 break
             fig.add_subplot(col, row, count)
@@ -424,7 +424,6 @@ def plot_with_labels(low_dim_embs, labels, figsize=(18, 18), second=5, saveable=
 
     try:
         from sklearn.manifold import TSNE
-        import matplotlib.pyplot as plt
         from six.moves import xrange
 
         tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)
diff --git a/tests/test_pydocstyle.py b/tests/test_pydocstyle.py
index 96bba16c1..3dcb71329 100644
--- a/tests/test_pydocstyle.py
+++ b/tests/test_pydocstyle.py
@@ -1,5 +1,3 @@
-import os
-
 from pydocstyle.checker import check
 from pydocstyle.checker import violations
 
diff --git a/tests/test_yapf_format.py b/tests/test_yapf_format.py
index e98d36d23..e65675cef 100644
--- a/tests/test_yapf_format.py
+++ b/tests/test_yapf_format.py
@@ -1,8 +1,6 @@
-import os
 import sys
-
-from yapf.yapflib.yapf_api import FormatCode
 import testing
+from yapf.yapflib.yapf_api import FormatCode
 
 
 def _read_utf_8_file(filename):