cpp/lltm.py [25:44]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return d_input, d_weights, d_bias, d_old_h, d_old_cell


class LLTM(nn.Module):
    def __init__(self, input_features, state_size):
        super(LLTM, self).__init__()
        self.input_features = input_features
        self.state_size = state_size
        self.weights = nn.Parameter(
            torch.Tensor(3 * state_size, input_features + state_size))
        self.bias = nn.Parameter(torch.Tensor(1, 3 * state_size))
        self.reset_parameters()

    def reset_parameters(self):
        stdv = 1.0 / math.sqrt(self.state_size)
        for weight in self.parameters():
            weight.data.uniform_(-stdv, +stdv)

    def forward(self, input, state):
        return LLTMFunction.apply(input, self.weights, self.bias, *state)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



python/lltm_baseline.py [79:98]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return d_input, d_weights, d_bias, d_old_h, d_old_cell


class LLTM(nn.Module):
    def __init__(self, input_features, state_size):
        super(LLTM, self).__init__()
        self.input_features = input_features
        self.state_size = state_size
        self.weights = nn.Parameter(
            torch.Tensor(3 * state_size, input_features + state_size))
        self.bias = nn.Parameter(torch.Tensor(1, 3 * state_size))
        self.reset_parameters()

    def reset_parameters(self):
        stdv = 1.0 / math.sqrt(self.state_size)
        for weight in self.parameters():
            weight.data.uniform_(-stdv, +stdv)

    def forward(self, input, state):
        return LLTMFunction.apply(input, self.weights, self.bias, *state)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -