Hello,
I have tried implementing an autoencoder for mnist, but the loss function does not seem to be accepting this type of network.
Code is as follows:
from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.autograd import Variable
parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
parser.add_argument('--batch-size', type=int, default=64, metavar='N',
help='input batch size for training (default: 64)')
parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
help='input batch size for testing (default: 1000)')
parser.add_argument('--epochs', type=int, default=10, metavar='N',
help='number of epochs to train (default: 10)')
parser.add_argument('--no-cuda', action='store_true', default=False,
help='disables CUDA training')
parser.add_argument('--seed', type=int, default=1, metavar='S',
help='random seed (default: 1)')
parser.add_argument('--log-interval', type=int, default=10, metavar='N',
help='how many batches to wait before logging training status')
args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
train_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', train=True, download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.batch_size, shuffle=True, **kwargs)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.batch_size, shuffle=True, **kwargs)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.hidden = nn.Linear(784,1000)
self.hidden2 = nn.Linear(1000,500)
self.hidden3 = nn.Linear(500,250)
self.hidden4 = nn.Linear(250,30)
self.hidden5 = nn.Linear(30,250)
self.hidden6 = nn.Linear(250,500)
self.hidden7 = nn.Linear(500,1000)
self.hidden8 = nn.Linear(1000,784)
self.out = nn.Linear(784,784)
def forward(self, x):
x = x.view (-1, 784)
x = F.sigmoid(self.hidden(x))
x = F.dropout(x,0.1)
x = F.sigmoid(self.hidden2(x))
x = F.dropout(x,0.1)
x = F.sigmoid(self.hidden3(x))
x = F.dropout(x,0.1)
x = F.sigmoid(self.hidden4(x))
x = F.dropout(x,0.1)
x = F.sigmoid(self.hidden5(x))
x = F.dropout(x,0.1)
x = F.sigmoid(self.hidden6(x))
x = F.dropout(x,0.1)
x = F.sigmoid(self.hidden7(x))
x = F.dropout(x,0.1)
x = F.sigmoid(self.hidden8(x))
x = self.out(x)
return x #F.log_softmax(x)
def num_flat_features(self, x):
size = x.size()[1:] # all dimensions except the batch dimension
num_features = 1
for s in size:
num_features *= s
return num_features
model = Net()
print(model)
if args.cuda:
model.cuda()
optimizer = optim.SGD(model.parameters(), lr=.01, momentum=0)
def train(epoch):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
if args.cuda:
data, target = data.cuda(), data.cuda()
target = Variable(target)
data = Variable(data)
optimizer.zero_grad()
output = model(data)
loss = F.cross_entropy(output, data)#F.nll_loss(output, data)
loss.backward()
optimizer.step()
if batch_idx % args.log_interval == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.data[0]))
def test():
model.eval()
test_loss = 0
correct = 0
for (data, target) in test_loader:
if args.cuda:
data, target = data.cuda(), data.cuda()
target = Variable(target, volatile=True)
data = Variable(data)
output = model(data)
test_loss += F.cross_entropy(output, data).data[0]# F.nll_loss(output, target).data[0] #F.nll_loss(output, target, size_average=False).data[0] # sum up batch loss
pred = output.data.max(1)[1] # get the index of the max log-probability
correct += pred.eq(target.data).cpu().sum()
test_loss /= len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
for epoch in range(1, args.epochs + 1):
train(epoch)
test()
and the error I get is,
File âmymodelc.pyâ, line 139, in train
loss = F.cross_entropy(output, data)#F.nll_loss(output, data)
File â/home/slava/dev/miniconda2/lib/python2.7/site-packages/torch/nn/functional.pyâ, line 533, in cross_entropy
return nll_loss(log_softmax(input), target, weight, size_average)
File â/home/slava/dev/miniconda2/lib/python2.7/site-packages/torch/nn/functional.pyâ, line 501, in nll_loss
return f(input, target)
File â/home/slava/dev/miniconda2/lib/python2.7/site-packages/torch/nn/_functions/thnn/auto.pyâ, line 41, in forward
output, *self.additional_args)
TypeError: FloatClassNLLCriterion_updateOutput received an invalid combination of arguments - got (int, torch.FloatTensor, torch.FloatTensor, torch.FloatTensor, bool, NoneType, torch.FloatTensor), but expected (int state, torch.FloatTensor input, torch.LongTensor target, torch.FloatTensor output, bool sizeAverage, [torch.FloatTensor weights or None], torch.FloatTensor total_weight)
Thank you