Test init args in documentation (keras-team#12192)

* Test init args in documentation

* Impact associated docstrings

keras/callbacks.py

@@ -648,6 +648,9 @@ class ModelCheckpoint(Callback):
         save_best_only: if `save_best_only=True`,
             the latest best model according to
             the quantity monitored will not be overwritten.
+        save_weights_only: if True, then only the model's weights will be
+            saved (`model.save_weights(filepath)`), else the full model
+            is saved (`model.save(filepath)`).
         mode: one of {auto, min, max}.
             If `save_best_only=True`, the decision
             to overwrite the current save file is made
@@ -656,9 +659,6 @@ class ModelCheckpoint(Callback):
             this should be `max`, for `val_loss` this should
             be `min`, etc. In `auto` mode, the direction is
             automatically inferred from the name of the monitored quantity.
-        save_weights_only: if True, then only the model's weights will be
-            saved (`model.save_weights(filepath)`), else the full model
-            is saved (`model.save(filepath)`).
         period: Interval (number of epochs) between checkpoints.
     """
 
@@ -967,13 +967,13 @@ class TensorBoard(Callback):
             and weight histograms for the layers of the model. If set to 0,
             histograms won't be computed. Validation data (or split) must be
             specified for histogram visualizations.
+        batch_size: size of batch of inputs to feed to the network
+            for histograms computation.
         write_graph: whether to visualize the graph in TensorBoard.
             The log file can become quite large when
             write_graph is set to True.
         write_grads: whether to visualize gradient histograms in TensorBoard.
             `histogram_freq` must be greater than 0.
-        batch_size: size of batch of inputs to feed to the network
-            for histograms computation.
         write_images: whether to write model weights to visualize as
             image in TensorBoard.
         embeddings_freq: frequency (in epochs) at which selected embedding

keras/engine/sequential.py

@@ -26,6 +26,7 @@ class Sequential(Model):
 
     # Arguments
         layers: list of layers to add to the model.
+        name: Name given to the model
 
     # Example
 

keras/layers/core.py

@@ -50,6 +50,9 @@ class Masking(Layer):
         model.add(Masking(mask_value=0., input_shape=(timesteps, features)))
         model.add(LSTM(32))
     ```
+
+    # Arguments
+        mask_value: Either None or mask value to skip
     """
 
     def __init__(self, mask_value=0., **kwargs):
@@ -625,6 +628,8 @@ def hadamard_product_sum_output_shape(input_shapes):
                  `output_shape = (None, ) + output_shape`
             If a function, it specifies the entire shape as a function of the
             input shape: `output_shape = f(input_shape)`
+        mask: Either None (indicating no masking) or a Tensor indicating the
+          input mask for Embedding.
         arguments: optional dictionary of keyword arguments to be passed
             to the function.
 

keras/layers/cudnn_recurrent.py

@@ -335,17 +335,17 @@ class CuDNNLSTM(_CuDNNRNN):
         kernel_initializer: Initializer for the `kernel` weights matrix,
             used for the linear transformation of the inputs.
             (see [initializers](../initializers.md)).
-        unit_forget_bias: Boolean.
-            If True, add 1 to the bias of the forget gate at initialization.
-            Setting it to true will also force `bias_initializer="zeros"`.
-            This is recommended in [Jozefowicz et al. (2015)](
-            http://www.jmlr.org/proceedings/papers/v37/jozefowicz15.pdf).
         recurrent_initializer: Initializer for the `recurrent_kernel`
             weights matrix,
             used for the linear transformation of the recurrent state.
             (see [initializers](../initializers.md)).
         bias_initializer: Initializer for the bias vector
             (see [initializers](../initializers.md)).
+        unit_forget_bias: Boolean.
+            If True, add 1 to the bias of the forget gate at initialization.
+            Setting it to true will also force `bias_initializer="zeros"`.
+            This is recommended in [Jozefowicz et al. (2015)](
+            http://www.jmlr.org/proceedings/papers/v37/jozefowicz15.pdf).
         kernel_regularizer: Regularizer function applied to
             the `kernel` weights matrix
             (see [regularizer](../regularizers.md)).

keras/layers/embeddings.py

@@ -45,6 +45,9 @@ class Embedding(Layer):
         embeddings_regularizer: Regularizer function applied to
             the `embeddings` matrix
             (see [regularizer](../regularizers.md)).
+        activity_regularizer: Regularizer function applied to
+            the output of the layer (its "activation").
+            (see [regularizer](../regularizers.md)).
         embeddings_constraint: Constraint function applied to
             the `embeddings` matrix
             (see [constraints](../constraints.md)).

keras/layers/local.py

@@ -47,6 +47,7 @@ class LocallyConnected1D(Layer):
             any `dilation_rate` value != 1.
         padding: Currently only supports `"valid"` (case-insensitive).
             `"same"` may be supported in the future.
+        data_format: String, one of `channels_first`, `channels_last`.
         activation: Activation function to use
             (see [activations](../activations.md)).
             If you don't specify anything, no activation is applied

keras/layers/noise.py

@@ -116,6 +116,8 @@ class AlphaDropout(Layer):
         rate: float, drop probability (as with `Dropout`).
             The multiplicative noise will have
             standard deviation `sqrt(rate / (1 - rate))`.
+        noise_shape: A 1-D `Tensor` of type `int32`, representing the
+            shape for randomly generated keep/drop flags.
         seed: A Python integer to use as random seed.
 
     # Input shape

keras/layers/wrappers.py

@@ -340,6 +340,7 @@ class Bidirectional(Wrapper):
             One of {'sum', 'mul', 'concat', 'ave', None}.
             If None, the outputs will not be combined,
             they will be returned as a list.
+        weights: Initial weights to load in the Bidirectional model
 
     # Raises
         ValueError: In case of invalid `merge_mode` argument.

keras/optimizers.py

@@ -532,7 +532,8 @@ class Adamax(Optimizer):
 
     # Arguments
         lr: float >= 0. Learning rate.
-        beta_1/beta_2: floats, 0 < beta < 1. Generally close to 1.
+        beta_1: floats, 0 < beta < 1. Generally close to 1.
+        beta_2: floats, 0 < beta < 1. Generally close to 1.
         epsilon: float >= 0. Fuzz factor. If `None`, defaults to `K.epsilon()`.
         decay: float >= 0. Learning rate decay over each update.
 
@@ -614,8 +615,10 @@ class Nadam(Optimizer):
 
     # Arguments
         lr: float >= 0. Learning rate.
-        beta_1/beta_2: floats, 0 < beta < 1. Generally close to 1.
+        beta_1: floats, 0 < beta < 1. Generally close to 1.
+        beta_2: floats, 0 < beta < 1. Generally close to 1.
         epsilon: float >= 0. Fuzz factor. If `None`, defaults to `K.epsilon()`.
+        schedule_decay: floats, 0 < schedule_decay < 1.
 
     # References
         - [Nadam report](http://cs229.stanford.edu/proj2015/054_report.pdf)
@@ -694,6 +697,9 @@ def get_config(self):
 
 class TFOptimizer(Optimizer):
     """Wrapper class for native TensorFlow optimizers.
+
+    # Arguments
+        optimizer: Selected optimizer
     """
 
     def __init__(self, optimizer):

keras/utils/data_utils.py

@@ -650,7 +650,7 @@ class GeneratorEnqueuer(SequenceEnqueuer):
     Used in `fit_generator`, `evaluate_generator`, `predict_generator`.
 
     # Arguments
-        generator: a generator function which yields data
+        sequence: a sequence function which yields data
         use_multiprocessing: use multiprocessing if True, otherwise threading
         wait_time: time to sleep in-between calls to `put()`
         random_seed: Initial seed for workers,

tests/test_documentation.py

@@ -18,13 +18,24 @@
 MIN_CODE_SIZE = 10
 
 
+def handle_class_init(name, member):
+    init_args = [
+        arg for arg in list(inspect.signature(member.__init__).parameters.keys())
+        if arg not in ['self', 'args', 'kwargs']
+    ]
+    assert_args_presence(init_args, member.__doc__, member, name)
+
+
 def handle_class(name, member):
     if is_accepted(name, member):
         return
 
     if member.__doc__ is None and not member_too_small(member):
         raise ValueError("{} class doesn't have any documentation".format(name),
                          member.__module__, inspect.getmodule(member).__file__)
+
+    handle_class_init(name, member)
+
     for n, met in inspect.getmembers(member):
         if inspect.ismethod(met):
             handle_method(n, met)