Created
April 1, 2017 01:53
-
-
Save user01/68514db1127eb007f24d28bfd11dd60e to your computer and use it in GitHub Desktop.
Toy XOR network with pyTorch
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import torch | |
from torch.autograd import Variable | |
import torch.nn as nn | |
import torch.nn.functional as F | |
import torch.optim as optim | |
EPOCHS_TO_TRAIN = 50000 | |
class Net(nn.Module): | |
def __init__(self): | |
super(Net, self).__init__() | |
self.fc1 = nn.Linear(2, 3, True) | |
self.fc2 = nn.Linear(3, 1, True) | |
def forward(self, x): | |
x = F.sigmoid(self.fc1(x)) | |
x = self.fc2(x) | |
return x | |
net = Net() | |
inputs = list(map(lambda s: Variable(torch.Tensor([s])), [ | |
[0, 0], | |
[0, 1], | |
[1, 0], | |
[1, 1] | |
])) | |
targets = list(map(lambda s: Variable(torch.Tensor([s])), [ | |
[0], | |
[1], | |
[1], | |
[0] | |
])) | |
criterion = nn.MSELoss() | |
optimizer = optim.SGD(net.parameters(), lr=0.01) | |
print("Training loop:") | |
for idx in range(0, EPOCHS_TO_TRAIN): | |
for input, target in zip(inputs, targets): | |
optimizer.zero_grad() # zero the gradient buffers | |
output = net(input) | |
loss = criterion(output, target) | |
loss.backward() | |
optimizer.step() # Does the update | |
if idx % 5000 == 0: | |
print("Epoch {: >8} Loss: {}".format(idx, loss.data.numpy()[0])) | |
print("") | |
print("Final results:") | |
for input, target in zip(inputs, targets): | |
output = net(input) | |
print("Input:[{},{}] Target:[{}] Predicted:[{}] Error:[{}]".format( | |
int(input.data.numpy()[0][0]), | |
int(input.data.numpy()[0][1]), | |
int(target.data.numpy()[0]), | |
round(float(output.data.numpy()[0]), 4), | |
round(float(abs(target.data.numpy()[0] - output.data.numpy()[0])), 4) | |
)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Noticed an error in line 48:
IndexError: too many indices for array
Just change
loss.data.numpy()[0]
toloss.data.numpy()