s = data[case]
hidden = model.initHidden()
t, o = makeForOneCase(s, one_hot_var_target)
output, hidden = model(t.cuda(), hidden)
loss += criterion(output, o.cuda())
counts += 1
loss = loss / counts
print "=====", loss.data[0]
print "start training"
for epoch in range(epochNum):
for batchIndex in range(int(TRAINSIZE / batch)):
model.zero_grad()
loss = 0
counts = 0
for case in range(batchIndex * batch,
min((batchIndex + 1) * batch, TRAINSIZE)):
s = data[case]
hidden = model.initHidden()
t, o = makeForOneCase(s, one_hot_var_target)
output, hidden = model(t.cuda(), hidden)
loss += criterion(output, o.cuda())
counts += 1
loss = loss / counts
loss.backward()
print epoch, loss.data[0]
optimizer.step()
test()
torch.save(model, 'poetry-gen.pt')
output, hidden = model(s_in, hidden)
loss += criterion(output, s_o)
counts += 1
loss = loss / counts
return loss.item()
print("start training")
for epoch in range(epochs):
for batchIndex in range(int(data_size / batch_size)):
loss = 0
counts = 0
for case in range(batchIndex * batch_size,
min((batchIndex + 1) * batch_size, data_size)):
s = data[case]
hidden = model.initHidden(device=device)
s_in, s_o = makeForOneCase(s, one_hot_var_target)
s_in, s_o = s_in.to(device), s_o.to(device)
output, hidden = model(s_in, hidden)
loss += criterion(output, s_o)
counts += 1
loss = loss / counts
print("epoch {}, batch {}, loss {}".format(epoch, batchIndex,
loss.item()))
# compute accuracy and record loss
optimizer.zero_grad()
loss.backward()
optimizer.step()
# every epoch evaluate the model
valid_loss = evaluate()
print("epoch {}, current valid loss {}".format(epoch, valid_loss))