Update docs for 2.0 release

Author: rundiwu

docs/modules/cost.rst

@@ -1,5 +1,5 @@
 API - Cost
-================
+==================
 
 To make TensorLayer simple, we minimize the number of cost functions as much as
 we can. So we encourage you to use TensorFlow's function, , see `TensorFlow API <https://www.tensorflow.org/versions/r2.0/api_docs/python/tf>`_.
@@ -83,8 +83,7 @@ Regularization functions
 --------------------------
 
 For ``tf.nn.l2_loss``, ``tf.contrib.layers.l1_regularizer``, ``tf.contrib.layers.l2_regularizer`` and
-``tf.contrib.layers.sum_regularizer``, see `TensorFlow API <https://www.tensorflow.org/versions/master/api_docs/index.html>`_.
-
+``tf.contrib.layers.sum_regularizer``, see tensorflow API.
 Maxnorm
 ^^^^^^^^^^
 .. autofunction:: maxnorm_regularizer

docs/modules/layers.rst

@@ -73,21 +73,12 @@ Layer list
    GroupNorm
    SwitchNorm
 
-   ROIPoolingLayer
-
    RNN
    BiRNN
 
-   ConvRNNCell
-   BasicConvLSTMCell
-   ConvLSTM
-
    retrieve_seq_length_op
    retrieve_seq_length_op2
    retrieve_seq_length_op3
-   target_mask_op
-
-   Seq2Seq
 
    Flatten
    Reshape
@@ -106,8 +97,6 @@ Layer list
    Stack
    UnStack
 
-   SlimNets
-
    Sign
    Scale
    BinaryDense
@@ -116,10 +105,6 @@ Layer list
    TernaryConv2d
    DorefaDense
    DorefaConv2d
-   QuantizedDense
-   QuantizedDenseWithBN
-   QuantizedConv2d
-   QuantizedConv2dWithBN
 
    PRelu
    PRelu6
@@ -548,28 +533,6 @@ DorefaConv2d
 """""""""""""""""""""
 .. autoclass:: DorefaConv2d
 
-Quantization Dense Layer
-^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-QuantizedDense
-"""""""""""""""""""""
-.. autoclass:: QuantizedDense
-
-QuantizedDenseWithBN
-""""""""""""""""""""""""""""""""""""
-.. autoclass:: QuantizedDenseWithBN
-
-Quantization Convolutions
-^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-Quantization
-"""""""""""""""""""""
-.. autoclass:: QuantizedConv2d
-
-QuantizedConv2dWithBN
-"""""""""""""""""""""
-.. autoclass:: QuantizedConv2dWithBN
-
 
 .. -----------------------------------------------------------
 ..                  Recurrent Layers
@@ -590,26 +553,6 @@ Bidirectional layer
 """""""""""""""""""""""""""""""""
 .. autoclass:: BiRNN
 
-
-Recurrent Convolution
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-Conv RNN Cell
-"""""""""""""""""""""""""""""""""
-.. autoclass:: ConvRNNCell
-
-Basic Conv LSTM Cell
-"""""""""""""""""""""""""""""""""
-.. autoclass:: BasicConvLSTMCell
-
-Conv LSTM layer
-"""""""""""""""""""""""""""""""""
-.. autoclass:: ConvLSTM
-
-Simple Seq2Seq
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-.. autoclass:: Seq2Seq
-
 Advanced Ops for Dynamic RNN
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 These operations usually be used inside Dynamic RNN layer, they can
@@ -627,9 +570,6 @@ Compute Sequence length 3
 """"""""""""""""""""""""""
 .. autofunction:: retrieve_seq_length_op3
 
-Get Mask
-""""""""""""""""""""""""""
-.. autofunction:: target_mask_op
 
 
 

docs/user/get_start_model.rst

@@ -5,8 +5,7 @@ Define a model
 ===============
 
 TensorLayer provides two ways to define a model.
-Static model
-Dynamic model allows you to control the forward process
+Static model allows you to build model in a fluent way while dynamic model allows you to fully control the forward process.
 
 Static model
 ===============
@@ -37,7 +36,6 @@ Dynamic model
 
 
 In this case, you need to manually input the output shape of the previous layer to the new layer.
-For example,
 
 .. code-block:: python