1.图像增广
transform_train = torchvision.transforms.Compose([
torchvision.transforms.Resize(40),
torchvision.transforms.RandomResizedCrop(32, scale=(0.64, 1.0), ratio=(1.0, 1.0)),
torchvision.transforms.RandomHorizontalFlip(),
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize([0.4914, 0.4822, 0.4465],
[0.2023, 0.1994, 0.2010])
])
transform_test = torchvision.transforms.Compose([
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize([0.4914, 0.4822, 0.4465],
[0.2023, 0.1994, 0.2010])
])
2.读取由原始图像组成的数据集
#按照类文件夹读取文件
train_ds, train_valid_ds = [torchvision.datasets.ImageFolder(
os.path.join(data_dir, 'train_valid_test', folder),
transform=transform_train) for folder in ['train', 'train_valid']]
valid_ds, test_ds = [torchvision.datasets.ImageFolder(
os.path.join(data_dir, 'train_valid_test', folder),
transform=transform_test) for folder in ['valid', 'test']]
#DataLoader
train_iter, train_valid_iter = [torch.utils.data.DataLoader(
dataset, batch_size, shuffle=True, drop_last=True)
for dataset in (train_ds, train_valid_ds)]
valid_iter = torch.utils.data.DataLoader(valid_ds, batch_size, shuffle=False,
drop_last=True)
test_iter = torch.utils.data.DataLoader(test_ds, batch_size, shuffle=False,
drop_last=False)
3.定义模型
def get_net():
num_classes = 10
# 有10类 通道数是3的RGB图片
net = d2l.resnet18(num_classes, 3)
return net
# reduction=none 不用自动加和
loss = nn.CrossEntropyLoss(reduction="none")
def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
params=None, lr=None, optimizer=None):
for epoch in range(num_epochs):
train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
for X, y in train_iter:
y_hat = net(X)
l = loss(y_hat, y).sum()
# 梯度清零
if optimizer is not None:
optimizer.zero_grad()
elif params is not None and params[0].grad is not None:
for param in params:
param.grad.data.zero_()
l.backward()
if optimizer is None:
sgd(params, lr, batch_size)
else:
optimizer.step() # “softmax回归的简洁实现”一节将用到
train_l_sum = train_l_sum + l.item()
train_acc_sum = train_acc_sum + (y_hat.argmax(dim=1) == y).sum().item()
n =n + y.shape[0]
test_acc = evaluate_accuracy(test_iter, net)
print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
% (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))
4.定义训练函数
这里用了学习率衰退，lr_period, lr_decay表示每过lr_period轮训练，学习率乘以lr_decay。
这样保证在临近最优时不会乱走。
def train(net, train_iter, valid_iter, num_epochs, lr, wd, devices, lr_period,
lr_decay):
trainer = torch.optim.SGD(net.parameters(), lr=lr, momentum=0.9,
weight_decay=wd)
scheduler = torch.optim.lr_scheduler.StepLR(trainer, lr_period, lr_decay)
num_batches, timer = len(train_iter), d2l.Timer()
legend = ['train loss', 'train acc']
if valid_iter is not None:
legend.append('valid acc')
animator = d2l.Animator(xlabel='epoch', xlim=[1, num_epochs],
legend=legend)
net = nn.DataParallel(net, device_ids=devices).to(devices[0])
for epoch in range(num_epochs):
net.train()
metric = d2l.Accumulator(3)
for i, (features, labels) in enumerate(train_iter):
timer.start()
l, acc = d2l.train_batch_ch13(net, features, labels,
loss, trainer, devices)
metric.add(l, acc, labels.shape[0])
timer.stop()
if (i + 1) % (num_batches // 5) == 0 or i == num_batches - 1:
animator.add(epoch + (i + 1) / num_batches,
(metric[0] / metric[2], metric[1] / metric[2],
None))
if valid_iter is not None:
valid_acc = d2l.evaluate_accuracy_gpu(net, valid_iter)
animator.add(epoch + 1, (None, None, valid_acc))
scheduler.step()
measures = (f'train loss {metric[0] / metric[2]:.3f}, '
f'train acc {metric[1] / metric[2]:.3f}')
if valid_iter is not None:
measures += f', valid acc {valid_acc:.3f}'
print(measures + f'\n{metric[2] * num_epochs / timer.sum():.1f}'
f' examples/sec on {str(devices)}')
补一个train_ch13
def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
params=None, lr=None, optimizer=None):
for epoch in range(num_epochs):
train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
for X, y in train_iter:
y_hat = net(X)
l = loss(y_hat, y).sum()
# 梯度清零
if optimizer is not None:
optimizer.zero_grad()
elif params is not None and params[0].grad is not None:
for param in params:
param.grad.data.zero_()
l.backward()
if optimizer is None:
sgd(params, lr, batch_size)
else:
optimizer.step() # “softmax回归的简洁实现”一节将用到
train_l_sum = train_l_sum + l.item()
train_acc_sum = train_acc_sum + (y_hat.argmax(dim=1) == y).sum().item()
n =n + y.shape[0]
test_acc = evaluate_accuracy(test_iter, net)
print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
% (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))
5.训练和验证
devices, num_epochs, lr, wd = d2l.try_all_gpus(), 20, 2e-4, 5e-4
lr_period, lr_decay, net = 4, 0.9, get_net()
train(net, train_iter, valid_iter, num_epochs, lr, wd, devices, lr_period,
lr_decay)
验证
net, preds = get_net(), []
train(net, train_valid_iter, None, num_epochs, lr, wd, devices, lr_period,
lr_decay)
for X, _ in test_iter:
y_hat = net(X.to(devices[0]))
preds.extend(y_hat.argmax(dim=1).type(torch.int32).cpu().numpy())
sorted_ids = list(range(1, len(test_ds) + 1))
sorted_ids.sort(key=lambda x: str(x))
df = pd.DataFrame({'id': sorted_ids, 'label': preds})
df['label'] = df['label'].apply(lambda x: train_valid_ds.classes[x])
df.to_csv('submission.csv', index=False)
