Documentation update.

docs/sources/backend.md

@@ -32,7 +32,7 @@ You can import the backend module via:
 from keras import backend as K
 ```
 
-This instantiates an input placeholder. It's equivalent to `tf.placeholder()` or `T.matrix()`, `T.tensor3()`, etc.
+The code below instantiates an input placeholder. It's equivalent to `tf.placeholder()` or `T.matrix()`, `T.tensor3()`, etc.
 
 ```python
 input = K.placeholder(shape=(2, 4, 5))
@@ -42,7 +42,7 @@ input = K.placeholder(shape=(None, 4, 5))
 input = K.placeholder(ndim=3)
 ```
 
-This instantiates a shared variable. It's equivalent to `tf.variable()` or `theano.shared()`.
+The code below instantiates a shared variable. It's equivalent to `tf.variable()` or `theano.shared()`.
 
 ```python
 val = np.random.random((3, 4, 5))

docs/sources/layers/core.md

@@ -188,7 +188,7 @@ keras.layers.core.Activation(activation)
 Apply an activation function to the input. 
 
 
-- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model.
+- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model. To specify the number of samples per batch, you can use the keyword argument `batch_input_shape` (tuple of integers, including the samples axis).
 
 - __Output shape__: Same as input.
 
@@ -206,7 +206,7 @@ keras.layers.core.Dropout(p)
 Apply dropout to the input. Dropout consists in randomly setting a fraction `p` of input units to 0 at each update during training time, which helps prevent overfitting. Reference: [Dropout: A Simple Way to Prevent Neural Networks from Overfitting](http://www.cs.toronto.edu/~rsalakhu/papers/srivastava14a.pdf)
 
 
-- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model.
+- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model. To specify the number of samples per batch, you can use the keyword argument `batch_input_shape` (tuple of integers, including the samples axis).
 
 - __Output shape__: Same as input.
 
@@ -225,7 +225,7 @@ keras.layers.core.Reshape(dims)
 Reshape the input to a new shape containing the same number of units. 
 
 
-- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model.
+- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model. To specify the number of samples per batch, you can use the keyword argument `batch_input_shape` (tuple of integers, including the samples axis).
 
 - __Output shape__: `(nb_samples, dims)`.
 
@@ -249,7 +249,7 @@ keras.layers.core.Flatten()
 
 Convert a nD input to 1D. 
 
-- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model.
+- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model. To specify the number of samples per batch, you can use the keyword argument `batch_input_shape` (tuple of integers, including the samples axis).
 
 - __Output shape__: `(nb_samples, nb_input_units)`.
 
@@ -264,7 +264,7 @@ Repeat the 1D input n times. Dimensions of input are assumed to be `(nb_samples,
 
 Note that the output is still a single tensor; `RepeatVector` does not split the data flow.
 
-- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model.
+- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model. To specify the number of samples per batch, you can use the keyword argument `batch_input_shape` (tuple of integers, including the samples axis).
 
 - __Output shape__: `(nb_samples, n, input_dims)`.
 
@@ -279,7 +279,7 @@ keras.layers.core.Permute(dims)
 ```
 Permute the dimensions of the input data according to the given tuple. Sometimes useful for connecting RNNs and convnets together.
 
-- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model.
+- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model. To specify the number of samples per batch, you can use the keyword argument `batch_input_shape` (tuple of integers, including the samples axis).
 
 - __Output shape__: Same as the input shape, but with the dimensions re-ordered according to the ordering specified by the tuple.
 

docs/sources/layers/noise.md

@@ -8,7 +8,7 @@ Apply to the input an additive zero-centred gaussian noise with standard deviati
 
 Only active at training time.
 
-- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model.
+- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model. To specify the number of samples per batch, you can use the keyword argument `batch_input_shape` (tuple of integers, including the samples axis).
 
 - __Output shape__: Same as input.
 
@@ -26,7 +26,7 @@ Apply to the input an multiplicative one-centred gaussian noise with standard de
 
 Only active at training time.
 
-- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model.
+- __Input shape__: Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model. To specify the number of samples per batch, you can use the keyword argument `batch_input_shape` (tuple of integers, including the samples axis).
 
 - __Output shape__: Same as input.
 

docs/sources/models.md

@@ -127,6 +127,7 @@ model = keras.models.Graph()
     - __add_input__(name, input_shape, dtype='float'): Add an input with shape dimensionality `ndim`. 
         - __Arguments__:
             - __input_shape__: Integer tuple, shape of the expected input (not including the samples axis). E.g. (10,) for 10-dimensional vectors, (None, 128) for sequences (of variable length) of 128-dimensional vectors, (3, 32, 32) for 32x32 images with RGB channels.
+            - __batch_input_shape: Integer tuple, shape of the expected batch input (including the samples axis).
             - __dtype__: `float` or `int`. Type of the expected input data.
     - __add_output__(name, input=None, inputs=[], merge_mode='concat'): Add an output connect to `input` or `inputs`.
         - __Arguments__: