Tag: perceptron

linear1 = torch.nn.Linear(2, 10, bias=True)
linear2 = torch.nn.Linear(10, 10, bias=True)
linear3 = torch.nn.Linear(10, 10, bias=True)
linear4 = torch.nn.Linear(10, 1, bias=True)
sigmoid = torch.nn.Sigmoid()

model = torch.nn.Sequential(linear1, sigmoid, linear2, sigmoid, linear3, sigmoid, linear4, sigmoid).to(device)

for step in range(10001):
    optimizer.zero_grad()
    hypothesis = model(X)

    # cost/loss function
    cost = criterion(hypothesis, Y)
    cost.backward()
    optimizer.step()

    if step % 100 == 0:
        print(step, cost.item())

'''output
0 0.6948983669281006
100 0.6931558847427368
200 0.6931535005569458
300 0.6931513547897339
400 0.6931493282318115
500 0.6931473016738892
600 0.6931453943252563
700 0.6931434869766235
800 0.6931416988372803
900 0.6931397914886475
1000 0.6931380033493042
...
9700 0.00016829342348501086
9800 0.00016415018762927502
9900 0.00016021561168599874
10000 0.0001565046259202063
'''

linear = torch.nn.Linear(2, 1, bias=True)
sigmoid = torch.nn.Sigmoid()

# Sequential로 여러 모듈을 묶어 하나의 레이어로 사용
model = torch.nn.Sequential(linear, sigmoid).to(device)

criterion = torch.nn.BCELoss().to(device)
optimizer = torch.optim.SGD(model.parameters(), lr=1)

'''output
0 0.7273974418640137
100 0.6931475400924683
200 0.6931471824645996
300 0.6931471824645996
400 0.6931471824645996
500 0.6931471824645996
600 0.6931471824645996
...
9700 0.6931471824645996
9800 0.6931471824645996
9900 0.6931471824645996
10000 0.6931471824645996
'''