batch_dot

batch_dot(lhs=None, rhs=None, transpose_a=_Null, transpose_b=_Null, forward_stype=_Null, out=None, name=None, **kwargs)

Batchwise dot product.

batch_dot is used to compute dot product of x and y when x and y are data in batch, namely N-D (N >= 3) arrays in shape of (B0, …, B_i, :, :).

For example, given x with shape (B_0, …, B_i, N, M) and y with shape (B_0, …, B_i, M, K), the result array will have shape (B_0, …, B_i, N, K), which is computed by:

batch_dot(x,y)[b_0, ..., b_i, :, :] = dot(x[b_0, ..., b_i, :, :], y[b_0, ..., b_i, :, :])

Defined in src/operator/tensor/dot.cc:L127

Parameters:

lhs : ndarray

The first input

rhs : ndarray

The second input

transpose_a : boolean, optional, default=0

If true then transpose the first input before dot.

transpose_b : boolean, optional, default=0

If true then transpose the second input before dot.

forward_stype : {None, ‘csr’, ‘default’, ‘row_sparse’},optional, default=’None’

The desired storage type of the forward output given by user, if thecombination of input storage types and this hint does not matchany implemented ones, the dot operator will perform fallback operationand still produce an output of the desired storage type.

out : ndarray, optional

The output ndarray to hold the result.

Returns:

out : ndarray or list of ndarrays

The output of this function.