def fit(x_view, y_view, ZDIMS, input_dim, epochs):
EPOCHS = epochs
data1 = x_view
data2 = y_view
train_loader = torch.utils.data.DataLoader(ConcatDataset(data1, data2),
batch_size=BATCH_SIZE,
shuffle=True)
model = Autoencoder(ZDIMS, input_dim)
optimizer = optim.Adam(model.parameters(), lr=0.0001)
for epoch in range(1, EPOCHS + 1):
train(model, epoch, train_loader, optimizer, input_dim)
#est(epoch)
model.eval()
# 64 sets of random ZDIMS-float vectors, i.e. 64 locations / MNIST
# digits in latent space
sample = Variable(torch.randn(64, ZDIMS))
sample1 = model.decode_1(sample).cpu()
# print(sample1)
sample2 = model.decode_2(sample).cpu()
