NdArray

class nnabla.NdArray(*args, **kwargs)

nnabla.NdArray is a device-agnostic data container for multi-dimensional arrays (tensors). nnabla.NdArray can also implicitly handle data transfers across different devices (e.g. CPU to CUDA GPU, CUDA GPU to CPU). See Python API Tutorial for more details.

NdArray overrides some arithmetic operators (+, -, *, /, **). Operands can be either a scalar number, NdArray or Variable. An arithmetic operation containing NdArray returns NdArray which stores the output of the computation immediately invoked. Also, inplace arithmetic operations (+=, -=, *=, /=, **=) are implemented. Note that = doesn’t perform inplace substitution but just replaces the object reference. Instead, you can use copy_from() for inplace substitution.

Parameters:

shape (tuple or int) – Shape of tuple.

bool_fill(self, mask, value)

Return a new but inplaced nnabla.NdArray filled with value where mask is non-zero.

Parameters:

  • mask (nnabla.NdArray) – Mask with which to fill. Non-zero/zero elements are supposed to be a binary mask as 1/0. No gradients are computed with respect to mask.

  • value (float) – The value to fill.

cast(self, dtype, ctx=None)

In-place cast of data type of the NdArray. It returns the reference values as a numpy.ndarray only if optional parameter ctx is not given, None otherwise.

Parameters:
Returns:

numpy.array if ctx is None, otherwise nothing.

clear(self)

Clear memories which this NdArray has and return them to allocator.

clear_called

Checking if the array is not modified after cleared. This returns False until clear is called at the first time.

copy_from(self, NdArray arr, use_current_context=True)

Copy values from another NdArray object.

It returns the caller object itself.

Parameters:

  • arr (NdArray) – Values will be copied to the caller object. The shape of arr` must be same as the caller object.

  • use_current_context (bool) – If True, a copy is happening in a device and dtype specified in the current context (equivalent to call F.identity(src, output=[self])). Otherwise, a device and dtype in the source array is used. The default is True.

Returns:

nnabla.NdArray

data

Returns the values held by this array as a numpy.ndarray. Note that only the references are returned, and the values are not copied. Therefore, modifying the returned nnabla.NdArray will affect the data contained inside the NNabla array. This method can also be called as a setter where an array is created as the same type as rhs. There is an exception where zero() or fill(rhs) is invoked if a scalar with a float or an integer <= 2^53 (as filling value is maintained as float64) is given.

Note that this may implicitly invoke a data transfer from device arrays to the CPU.

Parameters:

value (numpy.ndarray) –

Returns:

numpy.ndarray

data_ptr(self, dtype, ctx=None, bool write_only=False)

Get array’s pointer.

The behavior is similar to cast method but returns the data pointer based on the ctx. If the ctx is not specified, the default context obtained by nn.get_current_context is used.

Parameters:

  • dtype (numpy.dtype) – Numpy Data type.

  • ctx (nnabla.Context, optional) – Context descriptor.

  • write_only (bool, optional) – No synchronization happens.

Returns:

The data pointer.

Return type:

int

dtype

Get dtype.

Returns:

numpy.dtype

fill(self, value)

Fill all of the elements with the provided scalar value.

Note

This doesn’t not fill values in an internal array with 0 immediately. An array is created as a requested data type when this array is used (in forward or backward computation for exampe), and is filled with the value.

Parameters:

value (float) – The value filled with.

static from_numpy_array(nparr)

Create a NdArray object from Numpy array data.

The data is initialized with the given Numpy array.

Parameters:

nparr (ndarray) – Numpy multi-dimensional array.

Returns:

nnabla.NdArray

get_data(self, str mode='rw', dtype=None)

Returns the values held by this array as a numpy.ndarray with a specified mode.

Parameters:

  • mode (str) – Computation becomes more efficient if right one is chosen. * ‘r’: Read-only access. * ‘w’: Write-only access. * ‘rw’: You can both read and write.

  • dtype (numpy.dtype, optional) – Force dtype of a returned array.

See :function:`nnabla.NdArray.data` for more details.

masked_fill(mask, value)

NdArray.bool_fill(self, mask, value) Return a new but inplaced nnabla.NdArray filled with value where mask is non-zero.

Args:

mask (nnabla.NdArray): Mask with which to fill. Non-zero/zero elements are supposed to be a binary mask as 1/0. No gradients are computed with respect to mask. value (float): The value to fill.

modification_count

Returns how many times modified after memory allocation or clearing buffer.

narrow(self, dim, start, length)

Returns a new array that is a narrowed part of this array. The narrowed part is specified by the slice of this array from start to start + length along the dimension dim. The returned array and this array share the same underlying allocated memory.

Parameters:

  • dim (int) – Dimension along which to narrow. Currently, only 0 can be specified.

  • start (int) – Starting index in specified dimension.

  • length (int) – Distance to the ending index from start.

See :function:`nnabla.NdArray.narrow` for more details.

ndim

Number of dimensions.

Returns:

int

shape

Shape of the N-d array.

Returns:

tuple of int

size

Total size of the N-d array.

Returns:

int

size_from_axis(self, axis=-1)

Gets the size followed by the provided axis.

Example

a = nnabla.NdArray([10,9])
a.size_from_axis()
# ==> 90
a.size_from_axis(0)
# ==> 90
a.size_from_axis(1)
# ==> 9
a.size_from_axis(2)
# ==> 1
Parameters:

axis (int, optional) – -1 as default

Returns:

int

strides

Strides.

Returns:

tuple of int

view(self, shape)

Create viewd NdArray. Create a new NdArray of sharing same data with specified shape. :param shape: Shape of tuple. :type shape: tuple

Returns:

nnabla.NdArray

zero(self)

Fill all of the elements with 0.

Note

This doesn’t not fill values in an internal array with 0 immediately. An array is created as a requested data type when this array is used (in forward or backward computation for exampe), and is filled with 0.

zeroing

Checking if the array is not modified after calling zero().