def __init__(self, net, train_iter, test_iter, num_epochs, device_name):
self.timer = d2l.Timer()
self.animator = d2l.Animator(
xlabel='epoch', xlim=[0, num_epochs], legend=[
'train loss', 'train acc', 'test acc'])
self.net = net
self.train_iter = train_iter
self.test_iter = test_iter
self.num_epochs = num_epochs
self.device_name = device_name
self.loss_arr = []
self.train_acc_arr = []
self.test_acc_arr = []
def train_epoch_ch8(model, train_iter, loss, updater, params, use_random_iter):
"""Train a model within one epoch (defined in Chapter 8)."""
state, timer = None, d2l.Timer()
metric = d2l.Accumulator(2) # Sum of training loss, no. of tokens
for X, Y in train_iter:
if state is None or use_random_iter:
# Initialize `state` when either it is the first iteration or
# using random sampling
state = model._init_state(batch_size=X.shape[0])
with tf.GradientTape(persistent=True) as g:
g.watch(params)
y_hat, state = model(X, state)
y = tf.reshape(Y, (-1))
l = loss(y, y_hat)
grads = g.gradient(l, params)
grads = grad_clipping(grads, 0.5)
updater.apply_gradients(zip(grads, params))
# Keras loss by default returns the average loss in a batch
# l_sum = l * float(tf.size(y).numpy()) if isinstance(
# loss, tf.keras.losses.Loss) else tf.reduce_sum(l)
metric.add(l * tf.size(y).numpy(), tf.size(y).numpy())
return math.exp(metric[0] / metric[1]), metric[1] / timer.stop()