braincore.math module

get_dtype(a)	Get the dtype of a.
is_float(array)	Check if the array is a floating point array.
is_int(array)	Check if the array is an integer array.
exprel(x)	Relative error exponential, (exp(x) - 1)/x.
flatten(input[, start_dim, end_dim])	Flattens input by reshaping it into a one-dimensional tensor.
unflatten(x, dim, sizes)	Expands a dimension of the input tensor over multiple dimensions.
remove_diag(arr)	Remove the diagonal of the matrix.
clip_by_norm(t, clip_norm[, axis])	Clip the tensor by the norm of the tensor.
from_numpy(x)	Convert the numpy array to jax array.
as_numpy(x)	Convert the array to numpy array.
tree_zeros_like(tree)	Create a tree with the same structure as the input tree, but with zeros in each leaf.
tree_ones_like(tree)	Create a tree with the same structure as the input tree, but with ones in each leaf.
ein_reduce(tensor, pattern, reduction, ...)	ein_reduce provides combination of reordering and reduction using reader-friendly notation.
ein_rearrange(tensor, pattern, **axes_lengths)	ein_rearrange is a reader-friendly smart element reordering for multidimensional tensors.
ein_repeat(tensor, pattern, **axes_lengths)	ein_repeat allows reordering elements and repeating them in arbitrary combinations.
ein_shape(x, pattern)	Parse a tensor shape to dictionary mapping axes names to their lengths.