mindchemistry.e3.o3.LinearBias
- class mindchemistry.e3.o3.LinearBias(irreps_in, irreps_out, has_bias, ncon_dtype=float32, **kwargs)[source]
Linear operation equivariant with option to add bias.
Equivalent to TensorProduct with instructions='linear' with option to add bias. For details, see
mindchemistry.e3.o3.TensorProduct
.- Parameters
irreps_in (Union[str, Irrep, Irreps]) – Irreps for the input.
irreps_out (Union[str, Irrep, Irreps]) – Irreps for the output.
irrep_norm (str) – {'component', 'norm'}, the assumed normalization of the input and output representations. Default:
'component'
.path_norm (str) – {'element', 'path'}, the normalization method of path weights. Default:
'element'
.weight_init (str) – {'zeros', 'ones', 'truncatedNormal', 'normal', 'uniform', 'he_uniform', 'he_normal', 'xavier_uniform'}, the initial method of weights. Default:
'normal'
.has_bias (bool) – whether add bias to calculation
ncon_dtype (mindspore.dtype) – The type of input tensors of ncon computation module. Default:
mindspore.float32
.
- Supported Platforms:
Ascend
Examples
>>> from mindchemistry.e3.o3 import LinearBias >>> LinearBias('2x2e+3x1o+3x0e', '3x2e+5x1o+2x0e') TensorProduct [linear] (2x2e+3x1o+3x0e x 1x0e -> 3x2e+5x1o+2x0e)