import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import numpy as np

class NeuralNetworkCalculator(nn.Module):
    def __init__(self):
        super(NeuralNetworkCalculator, self).__init__()
        self.layer_1 =
        self.layer_2 = torch.nn.Linear(3, 1)

    def forward(self, x):
        x = F.relu(self.layer_1(x))
        x = F.relu(self.layer_2(x))
        return x

net = NeuralNetworkCalculator()

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr = 0.0001)

device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
net.to(device)

##############################
# REPLACE WITH YOUR OWN DATA #
##############################
x = torch.from_numpy(np.random.rand(1042,32,)).type(dtype=torch.float).to(device) #(samples, channels, heigth, width)
y = torch.from_numpy(np.random.randint(1,size=(1042, 32))).to(device) #(number_of_classes, samples)

for epoch in range(2):  # loop over the dataset multiple times
    running_loss = 0.0
    for i in range(0, x.shape[0]):
        # get the inputs
        inputs, labels = x[i], y[i]

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        if i % 200 == 199:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 200))
            running_loss = 0.0
print('Finished Training')