# Keras backends

## What is a "backend"?

Keras is a model-level library, providing high-level building blocks for developing deep learning models. It does not handle itself low-level operations such as tensor products, convolutions and so on. Instead, it relies on a specialized, well-optimized tensor manipulation library to do so, serving as the "backend engine" of Keras. Rather than picking one single tensor library and making the implementation of Keras tied to that library, Keras handles the problem in a modular way, and several different backend engines can be plugged seamlessly into Keras.

At this time, Keras has two backend implementations available: the **TensorFlow** backend and the **Theano** backend.

- TensorFlow is an open-source symbolic tensor manipulation framework developed by Google, Inc.
- Theano is an open-source symbolic tensor manipulation framework developed by LISA/MILA Lab at UniversitÃ© de MontrÃ©al.

In the future, we are likely to add more backend options. If you are interested in developing a new backend, get in touch!

## Switching from one backend to another

If you have run Keras at least once, you will find the Keras configuration file at:

`~/.keras/keras.json`

If it isn't there, you can create it.

The default configuration file looks like this:

```
{
"image_dim_ordering": "tf",
"epsilon": 1e-07,
"floatx": "float32",
"backend": "tensorflow"
}
```

Simply change the field `backend`

to either `"theano"`

or `"tensorflow"`

, and Keras will use the new configuration next time you run any Keras code.

You can also define the environment variable `KERAS_BACKEND`

and this will
override what is defined in your config file :

```
KERAS_BACKEND=tensorflow python -c "from keras import backend"
Using TensorFlow backend.
```

## keras.json details

```
{
"image_dim_ordering": "tf",
"epsilon": 1e-07,
"floatx": "float32",
"backend": "tensorflow"
}
```

You can change these settings by editing `~/.keras/keras.json`

.

`image_dim_ordering`

: string, either`"tf"`

or`"th"`

. It specifies which dimension ordering convention Keras will follow. (`keras.backend.image_dim_ordering()`

returns it.)- For 2D data (e.g. image),
`"tf"`

assumes`(rows, cols, channels)`

while`"th"`

assumes`(channels, rows, cols)`

. - For 3D data,
`"tf"`

assumes`(conv_dim1, conv_dim2, conv_dim3, channels)`

while`"th"`

assumes`(channels, conv_dim1, conv_dim2, conv_dim3)`

. `epsilon`

: float, a numeric fuzzing constant used to avoid dividing by zero in some operations.`floatx`

: string,`"float16"`

,`"float32"`

, or`"float64"`

. Default float precision.`backend`

: string,`"tensorflow"`

or`"theano"`

.

## Using the abstract Keras backend to write new code

If you want the Keras modules you write to be compatible with both Theano and TensorFlow, you have to write them via the abstract Keras backend API. Here's an intro.

You can import the backend module via:

```
from keras import backend as K
```

The code below instantiates an input placeholder. It's equivalent to `tf.placeholder()`

or `T.matrix()`

, `T.tensor3()`

, etc.

```
input = K.placeholder(shape=(2, 4, 5))
# also works:
input = K.placeholder(shape=(None, 4, 5))
# also works:
input = K.placeholder(ndim=3)
```

The code below instantiates a shared variable. It's equivalent to `tf.variable()`

or `theano.shared()`

.

```
val = np.random.random((3, 4, 5))
var = K.variable(value=val)
# all-zeros variable:
var = K.zeros(shape=(3, 4, 5))
# all-ones:
var = K.ones(shape=(3, 4, 5))
```

Most tensor operations you will need can be done as you would in TensorFlow or Theano:

```
a = b + c * K.abs(d)
c = K.dot(a, K.transpose(b))
a = K.sum(b, axis=2)
a = K.softmax(b)
a = concatenate([b, c], axis=-1)
# etc...
```

## Backend functions

### set_epsilon

```
set_epsilon(e)
```

Sets the value of the fuzz factor used in numeric expressions.

**Arguments**

**e**: float. New value of epsilon.

**Example**

```
>>> from keras import backend as K
>>> K.epsilon()
1e-08
>>> K.set_epsilon(1e-05)
>>> K.epsilon()
1e-05
```

### floatx

```
floatx()
```

Returns the default float type, as a string (e.g. 'float16', 'float32', 'float64').

**Returns**

String, the current default float type.

**Example**

```
>>> keras.backend.floatx()
'float32'
```

### set_floatx

```
set_floatx(floatx)
```

Sets the default float type.

**Arguments**

**String**: 'float16', 'float32', or 'float64'.

**Example**

```
>>> from keras import backend as K
>>> K.floatx()
'float32'
>>> K.set_floatx('float16')
>>> K.floatx()
'float16'
```

### cast_to_floatx

```
cast_to_floatx(x)
```

Cast a Numpy array to the default Keras float type.

**Arguments**

**x**: Numpy array.

**Returns**

The same Numpy array, cast to its new type.

**Example**

```
>>> from keras import backend as K
>>> K.floatx()
'float32'
>>> arr = numpy.array([1.0, 2.0], dtype='float64')
>>> arr.dtype
dtype('float64')
>>> new_arr = K.cast_to_floatx(arr)
>>> new_arr
array([ 1., 2.], dtype=float32)
>>> new_arr.dtype
dtype('float32')
```

### image_dim_ordering

```
image_dim_ordering()
```

Returns the default image dimension ordering convention ('th' or 'tf').

**Returns**

A string, either `'th'`

or `'tf'`

**Example**

```
>>> keras.backend.image_dim_ordering()
'th'
```

### set_image_dim_ordering

```
set_image_dim_ordering(dim_ordering)
```

Sets the value of the image dimension ordering convention ('th' or 'tf').

**Arguments**

**dim_ordering**: string.`'th'`

or`'tf'`

.

**Example**

```
>>> from keras import backend as K
>>> K.image_dim_ordering()
'th'
>>> K.set_image_dim_ordering('tf')
>>> K.image_dim_ordering()
'tf'
```

### get_uid

```
get_uid(prefix='')
```

Provides a unique UID given a string prefix.

**Arguments**

**prefix**: string.

**Returns**

An integer.

**Example**

```
>>> keras.backend.get_uid('dense')
>>> 1
>>> keras.backend.get_uid('dense')
>>> 2
```

### is_keras_tensor

```
is_keras_tensor(x)
```

Returns whether `x`

is a Keras tensor.

**Arguments**

**x**: a potential tensor.

**Returns**

A boolean: whether the argument is a Keras tensor.

**Examples**

```
>>> from keras import backend as K
>>> np_var = numpy.array([1, 2])
>>> K.is_keras_tensor(np_var)
False
>>> keras_var = K.variable(np_var)
>>> K.is_keras_tensor(keras_var) # A variable is not a Tensor.
False
>>> keras_placeholder = K.placeholder(shape=(2, 4, 5))
>>> K.is_keras_tensor(keras_placeholder) # A placeholder is a Tensor.
True
```

### epsilon

```
epsilon()
```

Returns the value of the fuzz factor used in numeric expressions.

**Returns**

A float.

**Example**

```
>>> keras.backend.epsilon()
1e-08
```

### variable

```
variable(value, dtype=None, name=None)
```

Instantiates a variable and returns it.

**Arguments**

**value**: Numpy array, initial value of the tensor.**dtype**: Tensor type.**name**: Optional name string for the tensor.

**Returns**

A variable instance (with Keras metadata included).

### placeholder

```
placeholder(shape=None, ndim=None, dtype=None, sparse=False, name=None)
```

Instantiate an input data placeholder variable.

### shape

```
shape(x)
```

Returns the shape of a tensor.

**Warning**: type returned will be different for Theano backend (Theano tensor type) and TF backend (TF TensorShape).

### int_shape

```
int_shape(x)
```

Returns the shape of a Keras tensor or a Keras variable as a tuple of integers or None entries.

**Arguments**

**x**: Tensor or variable.

**Returns**

A tuple of integers (or None entries).

### eval

```
eval(x)
```

Returns the value of a tensor.

### zeros

```
zeros(shape, dtype=None, name=None)
```

Instantiates an all-zeros variable.

### ones

```
ones(shape, dtype=None, name=None)
```

Instantiates an all-ones variable.

### eye

```
eye(size, dtype=None, name=None)
```

Instantiates an identity matrix.

### count_params

```
count_params(x)
```

Returns the number of scalars in a tensor.

**Return**: numpy integer.

### batch_dot

```
batch_dot(x, y, axes=None)
```

Batchwise dot product.

batch_dot results in a tensor with less dimensions than the input.
If the number of dimensions is reduced to 1, we use `expand_dims`

to
make sure that ndim is at least 2.

**Arguments**

x, y: tensors with ndim >= 2
- **axes**: list (or single) int with target dimensions

**Returns**

A tensor with shape equal to the concatenation of x's shape (less the dimension that was summed over) and y's shape (less the batch dimension and the dimension that was summed over). If the final rank is 1, we reshape it to (batch_size, 1).

**Examples**

Assume x = [[1, 2], [3, 4]] and y = [[5, 6], [7, 8]] batch_dot(x, y, axes=1) = [[17, 53]] which is the main diagonal of x.dot(y.T), although we never have to calculate the off-diagonal elements.

Shape inference: Let x's shape be (100, 20) and y's shape be (100, 30, 20). If dot_axes is (1, 2), to find the output shape of resultant tensor, loop through each dimension in x's shape and y's shape: x.shape[0] : 100 : append to output shape x.shape[1] : 20 : do not append to output shape, dimension 1 of x has been summed over. (dot_axes[0] = 1) y.shape[0] : 100 : do not append to output shape, always ignore first dimension of y y.shape[1] : 30 : append to output shape y.shape[2] : 20 : do not append to output shape, dimension 2 of y has been summed over. (dot_axes[1] = 2)

output_shape = (100, 30)

### gather

```
gather(reference, indices)
```

reference: a tensor.
- **indices**: an int tensor of indices.

**Return**: a tensor of same type as reference.

### sum

```
sum(x, axis=None, keepdims=False)
```

Sum of the values in a tensor, alongside the specified axis.

### prod

```
prod(x, axis=None, keepdims=False)
```

Multiply the values in a tensor, alongside the specified axis.

### mean

```
mean(x, axis=None, keepdims=False)
```

Mean of a tensor, alongside the specified axis.

### any

```
any(x, axis=None, keepdims=False)
```

Bitwise reduction (logical OR).

### all

```
all(x, axis=None, keepdims=False)
```

Bitwise reduction (logical AND).

### normalize_batch_in_training

```
normalize_batch_in_training(x, gamma, beta, reduction_axes, epsilon=0.001)
```

Computes mean and std for batch then apply batch_normalization on batch.

### batch_normalization

```
batch_normalization(x, mean, var, beta, gamma, epsilon=0.001)
```

Apply batch normalization on x given mean, var, beta and gamma.

### permute_dimensions

```
permute_dimensions(x, pattern)
```

Transpose dimensions.

pattern should be a tuple or list of dimension indices, e.g. [0, 2, 1].

### repeat_elements

```
repeat_elements(x, rep, axis)
```

Repeat the elements of a tensor along an axis, like np.repeat.

If x has shape (s1, s2, s3) and axis=1, the output will have shape (s1, s2 * rep, s3).

### resize_images

```
resize_images(X, height_factor, width_factor, dim_ordering)
```

Resize the images contained in a 4D tensor of shape - [batch, channels, height, width] (for 'th' dim_ordering) - [batch, height, width, channels] (for 'tf' dim_ordering) by a factor of (height_factor, width_factor). Both factors should be positive integers.

### resize_volumes

```
resize_volumes(X, depth_factor, height_factor, width_factor, dim_ordering)
```

Resize the volume contained in a 5D tensor of shape - [batch, channels, depth, height, width] (for 'th' dim_ordering) - [batch, depth, height, width, channels] (for 'tf' dim_ordering) by a factor of (depth_factor, height_factor, width_factor). Both factors should be positive integers.

### repeat

```
repeat(x, n)
```

Repeat a 2D tensor.

If x has shape (samples, dim) and n=2, the output will have shape (samples, 2, dim).

### arange

```
arange(start, stop=None, step=1, dtype='int32')
```

Creates a 1-D tensor containing a sequence of integers.

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

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

### batch_flatten

```
batch_flatten(x)
```

Turn a n-D tensor into a 2D tensor where the first dimension is conserved.

### expand_dims

```
expand_dims(x, dim=-1)
```

Add a 1-sized dimension at index "dim".

### squeeze

```
squeeze(x, axis)
```

Remove a 1-dimension from the tensor at index "axis".

### temporal_padding

```
temporal_padding(x, padding=1)
```

Pad the middle dimension of a 3D tensor with "padding" zeros left and right.

Apologies for the inane API, but Theano makes this really hard.

### asymmetric_temporal_padding

```
asymmetric_temporal_padding(x, left_pad=1, right_pad=1)
```

Pad the middle dimension of a 3D tensor with "left_pad" zeros left and "right_pad" right.

Apologies for the inane API, but Theano makes this really hard.

### spatial_2d_padding

```
spatial_2d_padding(x, padding=(1, 1), dim_ordering='default')
```

Pad the 2nd and 3rd dimensions of a 4D tensor with "padding[0]" and "padding[1]" (resp.) zeros left and right.

### asymmetric_spatial_2d_padding

```
asymmetric_spatial_2d_padding(x, top_pad=1, bottom_pad=1, left_pad=1, right_pad=1, dim_ordering='default')
```

Pad the rows and columns of a 4D tensor with "top_pad", "bottom_pad", "left_pad", "right_pad" (resp.) zeros rows on top, bottom; cols on left, right.

### spatial_3d_padding

```
spatial_3d_padding(x, padding=(1, 1, 1), dim_ordering='default')
```

Pad the 2nd, 3rd and 4th dimensions of a 5D tensor with "padding[0]", "padding[1]" and "padding[2]" (resp.) zeros left and right.

### one_hot

```
one_hot(indices, nb_classes)
```

Input: nD integer tensor of shape (batch_size, dim1, dim2, ... dim(n-1))
- **Output**: (n + 1)D one hot representation of the input
with shape (batch_size, dim1, dim2, ... dim(n-1), nb_classes)

### reverse

```
reverse(x, axes)
```

Reverse a tensor along the the specified axes

### batch_get_value

```
batch_get_value(xs)
```

Returns the value of more than one tensor variable, as a list of Numpy arrays.

### print_tensor

```
print_tensor(x, message='')
```

Print the message and the tensor when evaluated and return the same tensor.

### stop_gradient

```
stop_gradient(variables)
```

Returns `variables`

but with zero gradient with respect to every other
variables.

### rnn

```
rnn(step_function, inputs, initial_states, go_backwards=False, mask=None, constants=None, unroll=False, input_length=None)
```

Iterates over the time dimension of a tensor.

**Arguments**

**inputs**: tensor of temporal data of shape (samples, time, ...) (at least 3D).**step_function**:**Parameters**:**input**: tensor with shape (samples, ...) (no time dimension), representing input for the batch of samples at a certain time step.**states**: list of tensors.

**Returns**:**output**: tensor with shape (samples, ...) (no time dimension),**new_states**: list of tensors, same length and shapes as 'states'.

**initial_states**: tensor with shape (samples, ...) (no time dimension), containing the initial values for the states used in the step function.**go_backwards**: boolean. If True, do the iteration over the time dimension in reverse order.**mask**: binary tensor with shape (samples, time), with a zero for every element that is masked.**constants**: a list of constant values passed at each step.**unroll**: whether to unroll the RNN or to use a symbolic loop (`scan`

).**input_length**: must be specified if using`unroll`

.

**Returns**

A tuple (last_output, outputs, new_states).
- **last_output**: the latest output of the rnn, of shape (samples, ...)
- **outputs**: tensor with shape (samples, time, ...) where each
entry outputs[s, t] is the output of the step function
at time t for sample s.
- **new_states**: list of tensors, latest states returned by
the step function, of shape (samples, ...).

### switch

```
switch(condition, then_expression, else_expression)
```

condition: scalar tensor.

### elu

```
elu(x, alpha=1.0)
```

Exponential linear unit

**Arguments**

**x**: Tensor to compute the activation function for.**alpha**: scalar

### dropout

```
dropout(x, level, noise_shape=None, seed=None)
```

Sets entries in `x`

to zero at random,
while scaling the entire tensor.

**Arguments**

**x**: tensor**level**: fraction of the entries in the tensor that will be set to 0.**noise_shape**: shape for randomly generated keep/drop flags, must be broadcastable to the shape of`x`

**seed**: random seed to ensure determinism.

### in_top_k

```
in_top_k(predictions, targets, k)
```

Returns whether the `targets`

are in the top `k`

`predictions`

**Arguments**

**predictions**: A tensor of shape batch_size x classess and type float32.**targets**: A tensor of shape batch_size and type int32 or int64.**k**: An int, number of top elements to consider.

**Returns**

A tensor of shape batch_size and type int. output_i is 1 if targets_i is within top-k values of predictions_i

### conv1d

```
conv1d(x, kernel, stride=1, border_mode='valid', image_shape=None, filter_shape=None)
```

1D convolution.

**Arguments**

**kernel**: kernel tensor.**strides**: stride integer.**border_mode**: string, "same" or "valid".

### conv2d

```
conv2d(x, kernel, strides=(1, 1), border_mode='valid', dim_ordering='default', image_shape=None, filter_shape=None, filter_dilation=(1, 1))
```

2D convolution.

**Arguments**

**kernel**: kernel tensor.**strides**: strides tuple.**border_mode**: string, "same" or "valid".**dim_ordering**: "tf" or "th". Whether to use Theano or TensorFlow dimension ordering in inputs/kernels/ouputs.

### deconv2d

```
deconv2d(x, kernel, output_shape, strides=(1, 1), border_mode='valid', dim_ordering='default', image_shape=None, filter_shape=None)
```

2D deconvolution (transposed convolution).

**Arguments**

**kernel**: kernel tensor.**output_shape**: desired dimensions of output.**strides**: strides tuple.**border_mode**: string, "same" or "valid".**dim_ordering**: "tf" or "th". Whether to use Theano or TensorFlow dimension ordering in inputs/kernels/ouputs.

### conv3d

```
conv3d(x, kernel, strides=(1, 1, 1), border_mode='valid', dim_ordering='default', volume_shape=None, filter_shape=None, filter_dilation=(1, 1, 1))
```

3D convolution.

**Arguments**

**kernel**: kernel tensor.**strides**: strides tuple.**border_mode**: string, "same" or "valid".**dim_ordering**: "tf" or "th". Whether to use Theano or TensorFlow dimension ordering in inputs/kernels/ouputs.

### ctc_batch_cost

```
ctc_batch_cost(y_true, y_pred, input_length, label_length)
```

Runs CTC loss algorithm on each batch element.

**Arguments**

**y_true**: tensor (samples, max_string_length) containing the truth labels**y_pred**: tensor (samples, time_steps, num_categories) containing the prediction, or output of the softmax**input_length**: tensor (samples,1) containing the sequence length for each batch item in y_pred**label_length**: tensor (samples,1) containing the sequence length for each batch item in y_true

**Returns**

Tensor with shape (samples,1) containing the CTC loss of each element

### map_fn

```
map_fn(fn, elems, name=None)
```

Map the function fn over the elements elems and return the outputs.

**Arguments**

**fn**: Callable that will be called upon each element in elems**elems**: tensor, at least 2 dimensional**name**: A string name for the map node in the graph

**Returns**

Tensor with first dimension equal to the elems and second depending on fn

### foldl

```
foldl(fn, elems, initializer=None, name=None)
```

Reduce elems using fn to combine them from left to right.

**Arguments**

**fn**: Callable that will be called upon each element in elems and an accumulator, for instance lambda acc, x: acc + x**elems**: tensor**initializer**: The first value used (elems[0] in case of None)**name**: A string name for the foldl node in the graph

**Returns**

Same type and shape as initializer

### foldr

```
foldr(fn, elems, initializer=None, name=None)
```

Reduce elems using fn to combine them from right to left.

**Arguments**

**fn**: Callable that will be called upon each element in elems and an accumulator, for instance lambda acc, x: acc + x**elems**: tensor**initializer**: The first value used (elems[-1] in case of None)**name**: A string name for the foldr node in the graph

**Returns**

Same type and shape as initializer

### backend

```
backend()
```

Publicly accessible method for determining the current backend.