TensorPlay
latest (dev)
Copy
View Markdown

Latest development documentation · Updated 2026-10-15

tensorplay.nn.init.kaiming_uniform_

tensorplay.nn.init.kaiming_uniform_(tensor, a=0, mode='fan_in', nonlinearity='leaky_relu', generator=None)[source]

Fill tensor in-place with U(-bound, bound) where bound = gain * sqrt(3 / fan).

On this page

Ask DeepWiki