Returns random tuples (s, V) drawn elementwise from a normal distribution. :param n: number of data points :param dims: tuple of dimensions (n_scalar, n_vector) :return: (s, V) with s.shape = (n, n_scalar) and V.shape = (n, n_vector, 3)
(n, dims, device="cpu")
| 39 | |
| 40 | |
| 41 | def randn(n, dims, device="cpu"): |
| 42 | ''' |
| 43 | Returns random tuples (s, V) drawn elementwise from a normal distribution. |
| 44 | |
| 45 | :param n: number of data points |
| 46 | :param dims: tuple of dimensions (n_scalar, n_vector) |
| 47 | |
| 48 | :return: (s, V) with s.shape = (n, n_scalar) and |
| 49 | V.shape = (n, n_vector, 3) |
| 50 | ''' |
| 51 | return torch.randn(n, dims[0], device=device), \ |
| 52 | torch.randn(n, dims[1], 3, device=device) |
| 53 | |
| 54 | |
| 55 | def _norm_no_nan(x, axis=-1, keepdims=False, eps=1e-8, sqrt=True): |
nothing calls this directly
no outgoing calls
no test coverage detected