Models

Recurrent

class ezflow.modules.models.recurrent.ConvGRU(hidden_dim=128, input_dim=320, kernel_size=3)[source]

Convolutinal GRU layer

Parameters

hidden_dim (int, optional) – Hidden dimension of the GRU
input_dim (int, optional) – Input dimension of the GRU
kernel_size (int, optional) – Kernel size of the convolutional layers

forward(h, x)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.