test.py

from __future__ import print_function
import argparse
import torch
import torch.utils.data
from torch import nn, optim
from torch.autograd import Variable
from torch.nn import functional as F
from torchvision import datasets, transforms
from torchvision.utils import save_image


parser = argparse.ArgumentParser(description='VAE MNIST Example')
parser.add_argument('--batch-size', type=int, default=128, metavar='N',
                    help='input batch size for training (default: 128)')
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='enables 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.ToTensor()),
    batch_size=args.batch_size, shuffle=True, **kwargs)
test_loader = torch.utils.data.DataLoader(
    datasets.MNIST('../data', train=False, transform=transforms.ToTensor()),
    batch_size=args.batch_size, shuffle=True, **kwargs)


class VAE(nn.Module):
    def __init__(self):
        super(VAE, self).__init__()

        self.fc1 = nn.LSTM(784, 400)
        self.fc21 = nn.Linear(400, 20)
        self.fc22 = nn.Linear(400, 20)
        self.fc3 = nn.Linear(20, 400)
        self.fc4 = nn.Linear(400, 784)

        self.relu = nn.ReLU()
        self.sigmoid = nn.Sigmoid()

    def encode(self, x):
        out,hidden=self.fc1(x)
        print('Output of first layer is')
        print(out)
        h1 = self.relu(out)
        return self.fc21(h1), self.fc22(h1)

    def reparameterize(self, mu, logvar):
        if self.training:
            std = logvar.mul(0.5).exp_()
            eps = Variable(std.data.new(std.size()).normal_())
            return eps.mul(std).add_(mu)
        else:
            return mu

    def decode(self, z):
        h3 = self.relu(self.fc3(z))
        return self.sigmoid(self.fc4(h3))

    def forward(self, x):
        #mu, logvar = self.encode(x.view(-1, 784))
        mu, logvar = self.encode(x)
        z = self.reparameterize(mu, logvar)
        return self.decode(z), mu, logvar


model = VAE()
if args.cuda:
    model.cuda()


def loss_function(recon_x, x, mu, logvar):
    tol=1e-10
    BCE = -torch.sum(torch.mul(x,torch.log(tol+recon_x))+(1-x).mul(torch.log(1+tol-recon_x)))
    BCE/=(args.batch_size * 784*seq_length/1.443)

    # see Appendix B from VAE paper:
    # Kingma and Welling. Auto-Encoding Variational Bayes. ICLR, 2014
    # https://arxiv.org/abs/1312.6114
    # 0.5 * sum(1 + log(sigma^2) - mu^2 - sigma^2)
    KLD = -0.5 * torch.sum(1 + logvar - mu.pow(2) - logvar.exp())
    # Normalise by same number of elements as in reconstruction
    KLD /= args.batch_size * 784*seq_length

    return BCE + KLD
#model.train()
def prepareData(train_loader, seq_length, batch_index):
    index_start=batch_index*seq_length
    index_end=index_start+seq_length
    for i, (data, _) in enumerate(train_loader):
        data=data.view(-1,784)
        data=data.resize_((128,784,1))
        if i==index_start:
            outData=data
        elif i > index_start and i < index_end:
            outData=torch.cat((outData,data),2)
    return outData.permute(2,0,1)
batch_index=1
seq_length=50
data_batch=Variable(prepareData(train_loader,seq_length,batch_index))
print(data_batch)

recon_batch, mu, logvar = model(data_batch)
print('Batch reconstruction is')
print(recon_batch)
print(mu)
print(logvar)
loss = loss_function(recon_batch, data_batch, mu, logvar)
print('Loss is')
print(loss)
'''
data_new=data.view(-1,784)
print(data_new)
print(len(train_loader.dataset))
'''