# (NETWORK) WEEK9 TIME SERIES

###### tags: `Computer Science` `uscc` `SMART SENSOR`

class LSTM(nn.Module):
    def __init__(self, input_dim, hidden_dim, num_layers, output_dim):
        super(LSTM, self).__init__()
        self.hidden_dim = hidden_dim
        self.num_layers = num_layers
        
        self.lstm = nn.LSTM(input_dim, hidden_dim, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_dim, output_dim)

    def forward(self, x):
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_dim).requires_grad_()
        c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_dim).requires_grad_()
        out, (hn, cn) = self.lstm(x, (h0.detach(), c0.detach()))
        out = self.fc(out[:, -1, :]) 
        return out

## lstm2

device = 'cpu'

class LSTM(nn.Module):
    def __init__(self, input_dim, hidden_dim, num_layers, output_dim):
        super(LSTM, self).__init__()
        self.hidden_dim = hidden_dim
        self.num_layers = num_layers
        
        self.lstm = nn.LSTM(input_dim, hidden_dim, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_dim, output_dim)

    def forward(self, x):
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_dim).to(device)
        c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_dim).to(device)
        out, (hn, cn) = self.lstm(x, (h0, c0))
        out = self.fc(out[:, -1, :]) 
        return out

## GRU

class GRU(nn.Module):
    def __init__(self, input_dim, hidden_dim, num_layers, output_dim):
        super(GRU, self).__init__()
        self.hidden_dim = hidden_dim
        self.num_layers = num_layers
        
        self.gru = nn.GRU(input_dim, hidden_dim, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_dim, output_dim)

    def forward(self, x):
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_dim).requires_grad_()
        out, (hn) = self.gru(x, (h0.detach()))
        out = self.fc(out[:, -1, :]) 
        return out

## lstm example

>>> rnn = nn.LSTM(input_size=10, hidden_size=20, num_layers=2)
>>> # input=(sequence length, batch_size, input_size)
>>> input = torch.randn(5, 3, 10) 
>>> # h0=(D * num_layers, batch_size, H_out) input_size)
>>> h0 = torch.randn(2, 3, 20)
>>> # c0=(D * num_layers, batch_size, H_out) input_size)
>>> c0 = torch.randn(2, 3, 20) 
>>> output, (hn, cn) = rnn(input, (h0, c0))

## gru example

>>> rnn = nn.GRU(input_size=10, hidden_size=20, num_layers=2)
>>> # input=(sequence length, batch_size, input_size)
>>> input = torch.randn(5, 3, 10) 
>>> # h0=(D * num_layers, batch_size, H_out)
>>> h0 = torch.randn(2, 3, 20) 
>>> output, hn = rnn(input, h0)