Ready Neural

#!/usr/bin/python3
import torch
from torch import nn
from torch import optim
import random

model = nn.Sequential(
    nn.Linear(2,2),
    nn.Sigmoid(),
    nn.Linear(2,1),
    nn.Sigmoid())

learning_rate = torch.tensor(0.0001)
minibatch_size = 25

criterion = nn.MSELoss()
#optimizer = optim.SGD(model.parameters(),lr=learning_rate,momentum=0.9)
optimizer = optim.Adam(model.parameters())
def get_item():
    x1 = random.choice([0,1])
    x2 = random.choice([0,1])
    x = torch.tensor([x1,x2],dtype=torch.float)
    yexpected = torch.tensor(float(x1 ^ x2))
    return x,yexpected


for i in range(100000):
    optimizer.zero_grad()
    xb = []
    yexpectedb = []
    for _ in range(1,minibatch_size):
        x1,yexpected1 = get_item()
        xb.append(x1)
        yexpectedb.append(yexpected1)

    x = torch.stack(xb)
    yexpectedb = torch.stack(yexpectedb)
    yp = model(x)
    y = torch.squeeze(yp)
    loss = criterion(y,yexpectedb)
    print(loss)
    loss.backward()
    optimizer.step()