main.py

from __future__ import print_function
import argparse
import pyvarinf
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

# Training settings
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('--lr', type=float, default=0.01, metavar='LR',
                    help='learning rate (default: 0.01)')
parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
                    help='SGD momentum (default: 0.5)')
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')
parser.add_argument('--prior', type=str, default='gaussian', metavar='P',
                    help='prior used (default: gaussian)',
                    choices=['gaussian', 'mixtgauss', 'conjugate', 'conjugate_known_mean'])

args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()

# setting up prior parameters
prior_parameters = {}
if args.prior != 'gaussian':
    prior_parameters['n_mc_samples'] = 1
if args.prior == 'mixtgauss':
    prior_parameters['sigma_1'] = 0.02
    prior_parameters['sigma_2'] = 0.2
    prior_parameters['pi'] = 0.5
if args.prior == 'conjugate':
    prior_parameters['mu_0'] = 0.
    prior_parameters['kappa_0'] = 3.
    prior_parameters['alpha_0'] = .5
    prior_parameters['beta_0'] = .5
if args.prior == 'conjugate_known_mean':
    prior_parameters['alpha_0'] = .5
    prior_parameters['beta_0'] = .5
    prior_parameters['mean'] = 0.

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.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)
        self.bn1 = nn.BatchNorm2d(10)
        self.bn2 = nn.BatchNorm2d(20)

    def forward(self, x):
        x = self.bn1(F.relu(F.max_pool2d(self.conv1(x), 2)))
        x = self.bn2(F.relu(F.max_pool2d(self.conv2(x), 2)))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return F.log_softmax(x)

model = Net()
var_model = pyvarinf.Variationalize(model)
var_model.set_prior(args.prior, **prior_parameters)
if args.cuda:
    var_model.cuda()

optimizer = optim.Adam(var_model.parameters(), lr=args.lr)



def train(epoch):
    var_model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data), Variable(target)
        optimizer.zero_grad()
        output = var_model(data)
        loss_error = F.nll_loss(output, target)
        loss_prior = var_model.prior_loss() / 60000
        loss = loss_error + loss_prior
        loss.backward()
        optimizer.step()
        if batch_idx % args.log_interval == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}\tLoss error: {:.6f}\tLoss weights: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.data[0], loss_error.data[0], loss_prior.data[0]))

def test(epoch):
    var_model.eval()
    test_loss = 0
    correct = 0
    for data, target in test_loader:
        if args.cuda:
            data, target = data.cuda(), target.cuda()
        data, target = Variable(data, volatile=True), Variable(target)
        output = var_model(data)
        test_loss += F.nll_loss(output, target).data[0]
        pred = output.data.max(1)[1] # get the index of the max log-probability
        correct += pred.eq(target.data).cpu().sum()

    test_loss = test_loss
    test_loss /= len(test_loader) # loss function already averages over batch size
    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(epoch)