initializer_variance_scaling
Initializer capable of adapting its scale to the shape of weights.
Description
With distribution="normal", samples are drawn from a truncated normal distribution centered on zero, with stddev = sqrt(scale / n) where n is:
number of input units in the weight tensor, if mode = “fan_in”
number of output units, if mode = “fan_out”
average of the numbers of input and output units, if mode = “fan_avg”
Usage
initializer_variance_scaling(
scale = 1,
mode = c("fan_in", "fan_out", "fan_avg"),
distribution = c("normal", "uniform", "truncated_normal", "untruncated_normal"),
seed = NULL
) Arguments
| Arguments | Description |
|---|---|
| scale | Scaling factor (positive float). |
| mode | One of “fan_in”, “fan_out”, “fan_avg”. |
| distribution | One of “truncated_normal”, “untruncated_normal” and “uniform”. For backward compatibility, “normal” will be accepted and converted to “untruncated_normal”. |
| seed | Integer used to seed the random generator. |
Details
With distribution="uniform", samples are drawn from a uniform distribution within -limit, limit, with limit = sqrt(3 * scale / n).
See Also
Other initializers: initializer_constant(), initializer_glorot_normal(), initializer_glorot_uniform(), initializer_he_normal(), initializer_he_uniform(), initializer_identity(), initializer_lecun_normal(), initializer_lecun_uniform(), initializer_ones(), initializer_orthogonal(), initializer_random_normal(), initializer_random_uniform(), initializer_truncated_normal(), initializer_zeros()