keras.backend

Keras backend API.

一、Functions

abs(...): Element-wise absolute value.
all(...): Bitwise reduction (logical AND).
any(...): Bitwise reduction (logical OR).
arange(...): Creates a 1D tensor containing a sequence of integers.
argmax(...): Returns the index of the maximum value along an axis.
argmin(...): Returns the index of the minimum value along an axis.
backend(...): Publicly accessible method for determining the current backend.
batch_dot(...): Batchwise dot product.
batch_flatten(...): Turn a nD tensor into a 2D tensor with same 0th dimension.
batch_get_value(...): Returns the value of more than one tensor variable.
batch_normalization(...): Applies batch normalization on x given mean, var, beta and gamma.
batch_set_value(...): Sets the values of many tensor variables at once.
bias_add(...): Adds a bias vector to a tensor.
binary_crossentropy(...): Binary crossentropy between an output tensor and a target tensor.
cast(...): Casts a tensor to a different dtype and returns it.
cast_to_floatx(...): Cast a Numpy array to the default Keras float type.
categorical_crossentropy(...): Categorical crossentropy between an output tensor and a target tensor.
clear_session(...): Destroys the current TF graph and creates a new one.
clip(...): Element-wise value clipping.
concatenate(...): Concatenates a list of tensors alongside the specified axis.
constant(...): Creates a constant tensor.
conv1d(...): 1D convolution.
conv2d(...): 2D convolution.
conv2d_transpose(...): 2D deconvolution (i.e.
conv3d(...): 3D convolution.
cos(...): Computes cos of x element-wise.
count_params(...): Returns the static number of elements in a variable or tensor.
ctc_batch_cost(...): Runs CTC loss algorithm on each batch element.
ctc_decode(...): Decodes the output of a softmax.
ctc_label_dense_to_sparse(...): Converts CTC labels from dense to sparse.
cumprod(...): Cumulative product of the values in a tensor, alongside the specified axis.
cumsum(...): Cumulative sum of the values in a tensor, alongside the specified axis.
dot(...): Multiplies 2 tensors (and/or variables) and returns a tensor.
dropout(...): Sets entries in x to zero at random, while scaling the entire tensor.
dtype(...): Returns the dtype of a Keras tensor or variable, as a string.
elu(...): Exponential linear unit.
epsilon(...): Returns the value of the fuzz factor used in numeric expressions.
equal(...): Element-wise equality between two tensors.
eval(...): Evaluates the value of a variable.
exp(...): Element-wise exponential.
expand_dims(...): Adds a 1-sized dimension at index "axis".
eye(...): Instantiate an identity matrix and returns it.
flatten(...): Flatten a tensor.
floatx(...): Returns the default float type, as a string.
foldl(...): Reduce elems using fn to combine them from left to right.
foldr(...): Reduce elems using fn to combine them from right to left.
function(...): Instantiates a Keras function.
gather(...): Retrieves the elements of indices indices in the tensor reference.
get_uid(...): Associates a string prefix with an integer counter in a TensorFlow graph.
get_value(...): Returns the value of a variable.
gradients(...): Returns the gradients of loss w.r.t. variables.
greater(...): Element-wise truth value of (x > y).
greater_equal(...): Element-wise truth value of (x >= y).
hard_sigmoid(...): Segment-wise linear approximation of sigmoid.
image_data_format(...): Returns the default image data format convention.
in_test_phase(...): Selects x in test phase, and alt otherwise.
in_top_k(...): Returns whether the targets are in the top k predictions.
in_train_phase(...): Selects x in train phase, and alt otherwise.
int_shape(...): Returns the shape of tensor or variable as a tuple of int or None entries.
is_keras_tensor(...): Returns whether x is a Keras tensor.
is_sparse(...): Returns whether a tensor is a sparse tensor.
l2_normalize(...): Normalizes a tensor wrt the L2 norm alongside the specified axis.
learning_phase(...): Returns the learning phase flag.
learning_phase_scope(...): Provides a scope within which the learning phase is equal to value.
less(...): Element-wise truth value of (x < y).
less_equal(...): Element-wise truth value of (x <= y).
local_conv1d(...): Apply 1D conv with un-shared weights.
local_conv2d(...): Apply 2D conv with un-shared weights.
log(...): Element-wise log.
manual_variable_initialization(...): Sets the manual variable initialization flag.
map_fn(...): Map the function fn over the elements elems and return the outputs.
max(...): Maximum value in a tensor.
maximum(...): Element-wise maximum of two tensors.
mean(...): Mean of a tensor, alongside the specified axis.
min(...): Minimum value in a tensor.
minimum(...): Element-wise minimum of two tensors.
moving_average_update(...): Compute the moving average of a variable.
name_scope(...): A context manager for use when defining a Python op.
ndim(...): Returns the number of axes in a tensor, as an integer.
normalize_batch_in_training(...): Computes mean and std for batch then apply batch_normalization on batch.
not_equal(...): Element-wise inequality between two tensors.
one_hot(...): Computes the one-hot representation of an integer tensor.
ones(...): Instantiates an all-ones variable and returns it.
ones_like(...): Instantiates an all-ones variable of the same shape as another tensor.
permute_dimensions(...): Permutes axes in a tensor.
placeholder(...): Instantiates a placeholder tensor and returns it.
pool2d(...): 2D Pooling.
pool3d(...): 3D Pooling.
pow(...): Element-wise exponentiation.
print_tensor(...): Prints message and the tensor value when evaluated.
prod(...): Multiplies the values in a tensor, alongside the specified axis.
random_binomial(...): Returns a tensor with random binomial distribution of values.
random_normal(...): Returns a tensor with normal distribution of values.
random_normal_variable(...): Instantiates a variable with values drawn from a normal distribution.
random_uniform(...): Returns a tensor with uniform distribution of values.
random_uniform_variable(...): Instantiates a variable with values drawn from a uniform distribution.
relu(...): Rectified linear unit.
repeat(...): Repeats a 2D tensor.
repeat_elements(...): Repeats the elements of a tensor along an axis, like np.repeat.
reset_uids(...): Resets graph identifiers.
reshape(...): Reshapes a tensor to the specified shape.
resize_images(...): Resizes the images contained in a 4D tensor.
resize_volumes(...): Resizes the volume contained in a 5D tensor.
reverse(...): Reverse a tensor along the specified axes.
rnn(...): Iterates over the time dimension of a tensor.
round(...): Element-wise rounding to the closest integer.
separable_conv2d(...): 2D convolution with separable filters.
set_epsilon(...): Sets the value of the fuzz factor used in numeric expressions.
set_floatx(...): Sets the default float type.
set_image_data_format(...): Sets the value of the image data format convention.
set_learning_phase(...): Sets the learning phase to a fixed value.
set_value(...): Sets the value of a variable, from a Numpy array.
shape(...): Returns the symbolic shape of a tensor or variable.
sigmoid(...): Element-wise sigmoid.
sign(...): Element-wise sign.
sin(...): Computes sin of x element-wise.
softmax(...): Softmax of a tensor.
softplus(...): Softplus of a tensor.
softsign(...): Softsign of a tensor.
sparse_categorical_crossentropy(...): Categorical crossentropy with integer targets.
spatial_2d_padding(...): Pads the 2nd and 3rd dimensions of a 4D tensor.
spatial_3d_padding(...): Pads 5D tensor with zeros along the depth, height, width dimensions.
sqrt(...): Element-wise square root.
square(...): Element-wise square.
squeeze(...): Removes a 1-dimension from the tensor at index "axis".
stack(...): Stacks a list of rank R tensors into a rank R+1 tensor.
std(...): Standard deviation of a tensor, alongside the specified axis.
stop_gradient(...): Returns variables but with zero gradient w.r.t. every other variable.
sum(...): Sum of the values in a tensor, alongside the specified axis.
switch(...): Switches between two operations depending on a scalar value.
tanh(...): Element-wise tanh.
temporal_padding(...): Pads the middle dimension of a 3D tensor.
tile(...): Creates a tensor by tiling x by n.
to_dense(...): Converts a sparse tensor into a dense tensor and returns it.
transpose(...): Transposes a tensor and returns it.
truncated_normal(...): Returns a tensor with truncated random normal distribution of values.
update(...)
update_add(...): Update the value of x by adding increment.
update_sub(...): Update the value of x by subtracting decrement.
var(...): Variance of a tensor, alongside the specified axis.
variable(...): Instantiates a variable and returns it.
zeros(...): Instantiates an all-zeros variable and returns it.
zeros_like(...): Instantiates an all-zeros variable of the same shape as another tensor.

二、重要的函数

1、keras.backend.arange

Creates a 1D tensor containing a sequence of integers.

tf.keras.backend.arange(
    start,
    stop=None,
    step=1,
    dtype='int32'
)

The function arguments use the same convention as Theano's arange: if only one argument is provided, it is in fact the "stop" argument and "start" is 0.

The default type of the returned tensor is 'int32' to match TensorFlow's default.

Arguments:

start: Start value.
stop: Stop value.
step: Difference between two successive values.
dtype: Integer dtype to use.

Returns:

An integer tensor.

Example:

Compat aliases

2、keras.backend.reshape

Reshapes a tensor to the specified shape.

tf.keras.backend.reshape(
    x,
    shape
)

Arguments:

x: Tensor or variable.
shape: Target shape tuple.

Returns:

A tensor.

Example:

Compat aliases

3、keras.backend.variable

Instantiates a variable and returns it.

tf.keras.backend.variable(
    value,
    dtype=None,
    name=None,
    constraint=None
)

Arguments:

value: Numpy array, initial value of the tensor.
dtype: Tensor type.
name: Optional name string for the tensor.
constraint: Optional projection function to be applied to the variable after an optimizer update.

Returns:

A variable instance (with Keras metadata included).

Examples:

<pre class="devsite-click-to-copy prettyprint lang-py">
<code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">import numpy as np </code>
<code class="no-select nocode">    &gt;&gt;&gt; from keras import backend as K </code>
<code class="no-select nocode">    &gt;&gt;&gt; val = np.array([[1, 2], [3, 4]]) </code>
<code class="no-select nocode">    &gt;&gt;&gt; kvar = K.variable(value=val, dtype=&#39;float64&#39;, name=&#39;example_var&#39;) </code>
<code class="no-select nocode">    &gt;&gt;&gt; K.dtype(kvar) </code>
<code class="no-select nocode">    &#39;float64&#39; </code>
<code class="no-select nocode">    &gt;&gt;&gt; print(kvar) </code>
<code class="no-select nocode">    example_var </code>
<code class="no-select nocode">    &gt;&gt;&gt; kvar.eval() </code>
<code class="no-select nocode">    array([[ 1.,  2.], </code>
<code class="no-select nocode">           [ 3.,  4.]]) </code>
</pre>

Compat aliases

4、keras.backend.cast

Casts a tensor to a different dtype and returns it.

tf.keras.backend.cast(
    x,
    dtype
)

You can cast a Keras variable but it still returns a Keras tensor.

Arguments:

x: Keras tensor (or variable).
dtype: String, either ('float16', 'float32', or 'float64').

Returns:

Keras tensor with dtype dtype.

Examples:

Cast a float32 variable to a float64 tensor

<pre class="devsite-click-to-copy prettyprint lang-py">
<code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">import tensorflow as tf </code>
<code class="no-select nocode">    &gt;&gt;&gt; from tensorflow.keras import backend as K </code>
<code class="no-select nocode">    &gt;&gt;&gt; input = K.ones(shape=(1,3)) </code>
<code class="no-select nocode">    &gt;&gt;&gt; print(input) </code>
<code class="no-select nocode">    &gt;&gt;&gt; cast_input = K.cast(input, dtype=&#39;float64&#39;) </code>
<code class="no-select nocode">    &gt;&gt;&gt; print(cast_input) </code>
<code class="no-select nocode"> </code>
<code class="no-select nocode">    &lt;tf.Variable &#39;Variable:0&#39; shape=(1, 3) dtype=float32, </code>
<code class="no-select nocode">         numpy=array([[1., 1., 1.]], dtype=float32)&gt; </code>
<code class="no-select nocode">    tf.Tensor([[1. 1. 1.]], shape=(1, 3), dtype=float64) </code>
</pre>

Compat aliases

5、keras.backend.greater

Element-wise truth value of (x > y).

tf.keras.backend.greater(
    x,
    y
)

Arguments:

x: Tensor or variable.
y: Tensor or variable.

Returns:

A bool tensor.

Compat aliases

6、keras.backend.gather

Retrieves the elements of indices indices in the tensor reference.

tf.keras.backend.gather(
    reference,
    indices
)

Arguments:

reference: A tensor.
indices: An integer tensor of indices.

Returns:

A tensor of same type as reference.

Compat aliases

7、keras.backend.stack

Stacks a list of rank R tensors into a rank R+1 tensor.

tf.keras.backend.stack(
    x,
    axis=0
)

Arguments:

x: List of tensors.
axis: Axis along which to perform stacking.

Returns:

A tensor.

Example:

Compat aliases

8、keras.backend.shape

Returns the symbolic shape of a tensor or variable.

tf.keras.backend.shape(x)

Arguments:

x: A tensor or variable.

Returns:

A symbolic shape (which is itself a tensor).

Examples:

    # TensorFlow example
    >>> from keras import backend as K
    >>> tf_session = K.get_session()
    >>> val = np.array([[1, 2], [3, 4]])
    >>> kvar = K.variable(value=val)
    >>> input = keras.backend.placeholder(shape=(2, 4, 5))
    >>> K.shape(kvar)
    <tf.Tensor 'Shape_8:0' shape=(2,) dtype=int32>
    >>> K.shape(input)
    <tf.Tensor 'Shape_9:0' shape=(3,) dtype=int32>
    # To get integer shape (Instead, you can use K.int_shape(x))
    >>> K.shape(kvar).eval(session=tf_session)
    array([2, 2], dtype=int32)
    >>> K.shape(input).eval(session=tf_session)
    array([2, 4, 5], dtype=int32)

Compat aliases

9、keras.backend.concatenate

Concatenates a list of tensors alongside the specified axis.

tf.keras.backend.concatenate(
    tensors,
    axis=-1
)

Arguments:

tensors: list of tensors to concatenate.
axis: concatenation axis.

Returns:

A tensor.

Example:

Compat aliases

10、keras.backend.max

Maximum value in a tensor.

tf.keras.backend.max(
    x,
    axis=None,
    keepdims=False
)

Arguments:

x: A tensor or variable.
axis: An integer, the axis to find maximum values.
keepdims: A boolean, whether to keep the dimensions or not. If keepdims is False, the rank of the tensor is reduced by 1. If keepdims is True, the reduced dimension is retained with length 1.

Returns:

A tensor with maximum values of x.

Compat aliases