inference/compute/pt/pytorch_linear.py [13:31]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class Net(nn.Module):
    def __init__(self, input_size, hidden_size, output_size, layer_num):
        super(Net, self).__init__()
        self.layer_num = layer_num
        self.linear_in = nn.Linear(input_size, hidden_size)
        self.linear_hid_list = nn.ModuleList(
            [nn.Linear(hidden_size, hidden_size) for _ in range(self.layer_num)]
        )
        self.linear_out = nn.Linear(hidden_size, output_size)

    def forward(self, x):
        x = self.linear_in(x)
        x = F.relu(x)
        for linear_hid in self.linear_hid_list:
            x = linear_hid(x)
            x = F.relu(x)
        x = self.linear_out(x)
        x = F.softmax(x, dim=1)
        return x
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



train/compute/pt/pytorch_linear.py [13:31]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class Net(nn.Module):
    def __init__(self, input_size, hidden_size, output_size, layer_num):
        super(Net, self).__init__()
        self.layer_num = layer_num
        self.linear_in = nn.Linear(input_size, hidden_size)
        self.linear_hid_list = nn.ModuleList(
            [nn.Linear(hidden_size, hidden_size) for _ in range(self.layer_num)]
        )
        self.linear_out = nn.Linear(hidden_size, output_size)

    def forward(self, x):
        x = self.linear_in(x)
        x = F.relu(x)
        for linear_hid in self.linear_hid_list:
            x = linear_hid(x)
            x = F.relu(x)
        x = self.linear_out(x)
        x = F.softmax(x, dim=1)
        return x
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -