Class Conv1dBlock

src/diffusers/models/resnet.py:392–424

Conv1d --> GroupNorm --> Mish Parameters: inp_channels (`int`): Number of input channels. out_channels (`int`): Number of output channels. kernel_size (`int` or `tuple`): Size of the convolving kernel. n_groups (`int`, default `8`): Number of groups to separ

class Conv1dBlock(nn.Module):
    """
    Conv1d --> GroupNorm --> Mish

    Parameters:
        inp_channels (`int`): Number of input channels.
        out_channels (`int`): Number of output channels.
        kernel_size (`int` or `tuple`): Size of the convolving kernel.
        n_groups (`int`, default `8`): Number of groups to separate the channels into.
        activation (`str`, defaults to `mish`): Name of the activation function.
    """

    def __init__(
        self,
        inp_channels: int,
        out_channels: int,
        kernel_size: int | tuple[int, int],
        n_groups: int = 8,
        activation: str = "mish",
    ):
        super().__init__()

        self.conv1d = nn.Conv1d(inp_channels, out_channels, kernel_size, padding=kernel_size // 2)
        self.group_norm = nn.GroupNorm(n_groups, out_channels)
        self.mish = get_activation(activation)

    def forward(self, inputs: torch.Tensor) -> torch.Tensor:
        intermediate_repr = self.conv1d(inputs)
        intermediate_repr = rearrange_dims(intermediate_repr)
        intermediate_repr = self.group_norm(intermediate_repr)
        intermediate_repr = rearrange_dims(intermediate_repr)
        output = self.mish(intermediate_repr)
        return output


# unet_rl.py