model.py

import torch
import torch.nn as nn
from torch.nn.utils import weight_norm

class Chomp1d(nn.Module):
    def __init__(self, chomp_size):
        super(Chomp1d, self).__init__()
        self.chomp_size = chomp_size

    def forward(self, x):
        return x[:, :, :-self.chomp_size].contiguous()

class TemporalBlock(nn.Module):
    def __init__(self, n_inputs, n_outputs, kernel_size, stride, dilation, padding, dropout=0.2):
        super(TemporalBlock, self).__init__()
        self.conv1 = weight_norm(nn.Conv1d(n_inputs, n_outputs, kernel_size,
                                           stride=stride, padding=padding, dilation=dilation))
        self.chomp1 = Chomp1d(padding)
        self.relu1 = nn.ReLU()
        self.dropout1 = nn.Dropout(dropout)

        self.conv2 = weight_norm(nn.Conv1d(n_outputs, n_outputs, kernel_size,
                                           stride=stride, padding=padding, dilation=dilation))
        self.chomp2 = Chomp1d(padding)
        self.relu2 = nn.ReLU()
        self.dropout2 = nn.Dropout(dropout)

        self.net = nn.Sequential(self.conv1, self.chomp1, self.relu1, self.dropout1,
                                 self.conv2, self.chomp2, self.relu2, self.dropout2)
        self.downsample = nn.Conv1d(n_inputs, n_outputs, 1) if n_inputs != n_outputs else None
        self.relu = nn.ReLU()
        self.init_weights()

    def init_weights(self):
        self.conv1.weight.data.normal_(0, 0.01)
        self.conv2.weight.data.normal_(0, 0.01)
        if self.downsample is not None:
            self.downsample.weight.data.normal_(0, 0.01)

    def forward(self, x):
        out = self.net(x)
        res = x if self.downsample is None else self.downsample(x)
        return self.relu(out + res)

class TemporalConvNet(nn.Module):
    def __init__(self, num_inputs, num_channels, kernel_size=2, dropout=0.2):
        super(TemporalConvNet, self).__init__()
        layers = []
        num_levels = len(num_channels)
        for i in range(num_levels):
            dilation_size = 2 ** i
            in_channels = num_inputs if i == 0 else num_channels[i-1]
            out_channels = num_channels[i]
            layers += [TemporalBlock(in_channels, out_channels, kernel_size, stride=1, dilation=dilation_size,
                                     padding=(kernel_size-1) * dilation_size, dropout=dropout)]

        self.network = nn.Sequential(*layers)

    def forward(self, x):
        return self.network(x)

class TCN(nn.Module):
    def __init__(self, input_size, output_size, num_channels, kernel_size = 2, dropout = 0.3):
        super(TCN,self).__init__()
        # self.encoder = nn.Embedding(output_size,input_size)
        self.tcn = TemporalConvNet(input_size,num_channels,kernel_size,dropout=dropout)
        self.linear = nn.Linear(num_channels[-1],output_size)
        self.init_weights()
        
    def init_weights(self):
        # self.encoder.weight.data.normal_(0,0.01)
        self.linear.bias.data.fill_(0)
        self.linear.weight.data.normal_(0,0.01)
    
    def forward(self, x):
        y = self.tcn(x) # (Batch, input_channel, seq_len)
        out = self.linear(y[:, :, -1])
        return out



# model = TCN(7, 64, [100, 100, 500, 500, 500])
# device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# model = model.to(device)

# y = torch.randn((5000, 1)).cuda()
# x = torch.ones((5000, 7, 63)).cuda()
# yhat = model(x)
# loss = corr_loss(yhat, y)
# print("loss:", loss.item())