def evaluate_accuracy_gpu(net, data_iter, device=None):
net.eval()
if not device:
device = next(iter(net.parameters())).device
metric = d2l.Accumulator(2)
for X, y in data_iter:
X, y = X.to(device), y.to(device)
metric.add(d2l.accuracy(net(X), y), d2l.size(y))
return metric[0] / metric[1]
def train_model(net,
train_iter,
test_iter,
num_epochs,
lr,
device=d2l.try_gpu()):
# for idx, (X, y) in enumerate(train_iter):
"""Train and evaluate a model with CPU or GPU."""
def init_weights(m):
if type(m) == nn.Linear or type(m) == nn.Conv2d:
torch.nn.init.xavier_uniform_(m.weight) # Part 2.2
net.apply(init_weights)
print('training on', device)
net.to(device)
optimizer = torch.optim.SGD(net.parameters(), lr=lr)
loss = nn.BCELoss()
animator = d2l.Animator(xlabel='epoch',
xlim=[0, num_epochs],
legend=['train loss', 'train acc', 'test acc'])
timer = d2l.Timer()
for epoch in range(num_epochs):
metric = d2l.Accumulator(3) # train_loss, train_acc, num_examples
for i, (X, y) in enumerate(train_iter):
timer.start()
net.train()
optimizer.zero_grad()
X = X.float()
X, y = X.to(device), y.to(device)
output = net(X)
# y_hat = torch.round(torch.exp(output)/(1+torch.exp(output)))
y_hat = torch.sigmoid(output)
y = y.to(torch.float)
y = torch.unsqueeze(y, 1)
l = loss(y_hat, y.type(torch.float32)) #.type(torch.float32)
l.backward()
optimizer.step()
with torch.no_grad():
metric.add(l * X.shape[0], d2l.accuracy(y_hat, y), X.shape[0])
timer.stop()
train_loss, train_acc = metric[0] / metric[2], metric[1] / metric[2]
if (i + 1) % 50 == 0:
animator.add(epoch + i / len(train_iter),
(train_loss, train_acc, None))
print(
"BatchNo.=%3i, Epoch No.=%3i, loss=%.3f, train acc=%.3f" %
(i + 1, epoch + 1, train_loss, train_acc))
test_acc = evaluate_accuracy_gpu(net, test_iter)
print("test_acc=", test_acc)
animator.add(epoch + 1, (None, None, test_acc))
print('loss %.3f, train acc %.3f, test acc %.3f' %
(train_loss, train_acc, test_acc))
print('%.1f examples/sec on %s' %
(metric[2] * num_epochs / timer.sum(), device))
def train_ch6(net, train_iter, test_iter, num_epochs, lr, device):
"""用GPU训练模型(在第六章定义)
Defined in :numref:`sec_lenet`"""
print('training on', device)
net.to(device)
optimizer = torch.optim.SGD(net.parameters(), lr=lr)
loss = nn.CrossEntropyLoss()
animator = d2l.Animator(xlabel='epoch',
xlim=[1, num_epochs],
legend=['train loss', 'train acc', 'test acc'])
timer = d2l.Timer()
num_batches = len(train_iter)
multiplier_anim = max(1, num_batches // 5)
multiplier_save = max(1, num_epochs // 10)
for epoch in tqdm(range(num_epochs)):
# 训练损失之和，训练准确率之和，样本数
metric = d2l.Accumulator(3)
net.train()
for i, (X, y) in enumerate(train_iter):
timer.start()
optimizer.zero_grad()
X, y = X.to(device), y.to(device)
y_hat = net(X)
l = loss(y_hat, y)
l.backward()
optimizer.step()
with torch.no_grad():
metric.add(l * X.shape[0], d2l.accuracy(y_hat, y), X.shape[0])
timer.stop()
train_l = metric[0] / metric[2]
train_acc = metric[1] / metric[2]
if (i + 1) % multiplier_anim == 0 or i == num_batches - 1:
animator.add(epoch + (i + 1) / num_batches,
(train_l, train_acc, None))
if test_iter is not None:
test_acc = d2l.evaluate_accuracy_gpu(net, test_iter)
else:
test_acc = 0
animator.add(epoch + 1, (None, None, test_acc))
# save net state_dict
if epoch == epochs - 1 or (epoch + 1) % multiplier_save == 0:
net_param_file = 'net_param_{:d}.pth'.format(epoch)
path_net = os.path.join(net_save_dir, net_param_file)
torch.save(net.state_dict(), path_net)
print('net param saved to \n\t{}'.format(path_net))
print(f'loss {train_l:.3f}, train acc {train_acc:.3f}, '
f'test acc {test_acc:.3f}')
print(f'{metric[2] * num_epochs / timer.sum():.1f} examples/sec '
f'on {str(device)}')
def evaluate_accuracy_gpu(net, data_iter, device=None): #@save
"""Compute the accuracy for a model on a dataset using a GPU."""
if isinstance(net, torch.nn.Module):
net.eval() # Set the model to evaluation mode
if not device:
device = next(iter(net.parameters())).device
# No. of correct predictions, no. of predictions
metric = d2l.Accumulator(2)
for X, y in data_iter:
if isinstance(X, list):
# Required for BERT Fine-tuning (to be covered later)
X = [x.to(device) for x in X]
else:
X = X.to(device)
y = y.to(device)
metric.add(d2l.accuracy(net(X), y), y.numel())
return metric[0] / metric[1]
def evaluate_accuracy_gpu(net, data_iter, device=None): #@save
"""使用GPU计算模型在数据集上的精度"""
if isinstance(net, nn.Module):
net.eval() # 设置为评估模式
if not device:
device = next(iter(net.parameters())).device
# 正确预测的数量，总预测的数量
metric = d2l.Accumulator(2)
with torch.no_grad():
for X, y in data_iter:
if isinstance(X, list):
# BERT微调所需的（之后将介绍）
X = [x.to(device) for x in X]
else:
X = X.to(device)
y = y.to(device)
metric.add(d2l.accuracy(net(X), y), y.numel())
return metric[0] / metric[1]
def train_ch6(net, train_iter, test_iter, num_epochs, lr,
device=d2l.try_gpu()):
"""Train a model with a GPU (defined in Chapter 6)."""
def init_weights(m):
if type(m) == nn.Linear or type(m) == nn.Conv2d:
nn.init.xavier_uniform_(m.weight)
net.apply(init_weights)
print('training on', device)
net.to(device)
optimizer = torch.optim.SGD(net.parameters(), lr=lr)
loss = nn.CrossEntropyLoss()
animator = d2l.Animator(xlabel='epoch',
xlim=[1, num_epochs],
legend=['train loss', 'train acc', 'test acc'])
timer, num_batches = d2l.Timer(), len(train_iter)
for epoch in range(num_epochs):
# Sum of training loss, sum of training accuracy, no. of examples
metric = d2l.Accumulator(3)
net.train()
for i, (X, y) in enumerate(train_iter):
timer.start()
optimizer.zero_grad()
X, y = X.to(device), y.to(device)
y_hat = net(X)
l = loss(y_hat, y)
l.backward()
optimizer.step()
with torch.no_grad():
metric.add(l * X.shape[0], d2l.accuracy(y_hat, y), X.shape[0])
timer.stop()
train_l = metric[0] / metric[2]
train_acc = metric[1] / metric[2]
if (i + 1) % (num_batches // 5) == 0 or i == num_batches - 1:
animator.add(epoch + (i + 1) / num_batches,
(train_l, train_acc, None))
test_acc = evaluate_accuracy_gpu(net, test_iter)
animator.add(epoch + 1, (None, None, test_acc))
print(f'loss {train_l:.3f}, train acc {train_acc:.3f}, '
f'test acc {test_acc:.3f}')
print(f'{metric[2] * num_epochs / timer.sum():.1f} examples/sec '
f'on {str(device)}')
plt.show()
def train_func(net,
train_iter,
test_iter,
num_epochs,
lr,
device=d2l.try_gpu()):
def init_weights(m):
if type(m) == nn.Linear or type(m) == nn.Conv2d:
torch.nn.init.xavier_uniform_(m.weight)
net.apply(init_weights)
print('training on', device)
net.to(device)
optimizer = torch.optim.SGD(net.parameters(), lr=lr)
loss = nn.CrossEntropyLoss()
timer = d2l.Timer()
for epoch in range(num_epochs):
metric = d2l.Accumulator(3)
for i, (X, y) in enumerate(train_iter):
timer.start()
net.train()
optimizer.zero_grad()
X, y = X.to(device), y.to(device)
y_hat = net(X)
l = loss(y_hat, y)
l.backward()
optimizer.step()
with torch.no_grad():
metric.add(l * X.shape[0], d2l.accuracy(y_hat, y), X.shape[0])
timer.stop()
train_loss = metric[0] / metric[2]
train_acc = metric[1] / metric[2]
if (i + 1) % 50 == 0:
print(f"epoch: {epoch} --- iter: {i} --- of {len(train_iter)}")
print(f"train loss: {train_loss} --- train acc: {train_acc}")
test_acc = evaluate_accuracy_gpu(net, test_iter)
print(f'loss {train_loss:.3f}, train acc {train_acc:.3f}, '
f'test acc {test_acc:.3f}')
print(f'{metric[2] * num_epochs / timer.sum():.1f} examples/sec '
f'on {str(device)}')