def truncated_linear(min_x, max_x, min_y, max_y, x) -> float

Truncated linear function. Implements the following function:

\[ \begin{cases} f1(x) = \frac{min_y + (x - min_x)}{ (max_x - min_x) * (max_y - min_y)} \\ f(x) = min(max_y, max(min_y, f1(x))) \end{cases} \] If max_x - min_x < 1e-10, then it behaves as the constant \(f(x) = max_y\)

Arguments:

• min_x(float)
• max_x(float)
• min_y(float)
• max_y(float)
• x(float)

def truncated_normal_(tensor, mean, std) -> torch.Tensor

Samples from a truncated normal distribution in-place.

Arguments:

• tensor(torch.Tensor): the tensor in which sampled values will be stored.
• mean(float): the desired mean (default = 0).
• std(float): the desired standard deviation (default = 1). (default: 1)

Returns:

• the tensor with the stored values. Note that this modifies the input tensor in place, so this is just a pointer to the same object.