1,基本配置
导入包和版本查询
import torch
import torch.nn as nn
import torchvision
print(torch.__version__)
print(torch.version.cuda)
print(torch.backends.cudnn.version())
print(torch.cuda.get_device_name(0))
显卡设置
如果只需要一张显卡
# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
如果需要指定多张显卡,比如0,1号显卡。
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0,1'
也可以在命令行运行代码时设置显卡:
CUDA_VISIBLE_DEVICES=0,1 python train.py
清除显存:
torch.cuda.empty_cache()
也可以使用在命令行重置GPU的指令:
nvidia-smi --gpu-reset -i [gpu_id]
2. 张量(Tensor)处理
张量基本信息
tensor = torch.randn(3,4,5)
print(tensor.type()) # 数据类型
print(tensor.size()) # 张量的shape,是个元组
print(tensor.dim()) # 维度的数量
命名张量
张量命名是一个非常有用的方法,这样可以方便地使用维度的名字来做索引或其他操作,大大提高了可读性、易用性,防止出错。
# 在PyTorch 1.3之前,需要使用注释
# Tensor[N, C, H, W]
images = torch.randn(32, 3, 56, 56)
images.sum(dim=1)
images.select(dim=1, index=0)
# PyTorch 1.3之后
NCHW = [‘N’, ‘C’, ‘H’, ‘W’]
images = torch.randn(32, 3, 56, 56, names=NCHW)
images.sum('C')
images.select('C', index=0)
# 也可以这么设置
tensor = torch.rand(3,4,1,2,names=('C', 'N', 'H', 'W'))
# 使用align_to可以对维度方便地排序
tensor = tensor.align_to('N', 'C', 'H', 'W')
数据类型转换
# 设置默认类型,pytorch中的FloatTensor远远快于DoubleTensor
torch.set_default_tensor_type(torch.FloatTensor)
# 类型转换
tensor = tensor.cuda()
tensor = tensor.cpu()
tensor = tensor.float()
tensor = tensor.long()
torch.Tensor与np.ndarray转换
除了CharTensor,其他所有CPU上的张量都支持转换为numpy格式然后再转换回来。
ndarray = tensor.cpu().numpy()
tensor = torch.from_numpy(ndarray).float()
tensor = torch.from_numpy(ndarray.copy()).float() # If ndarray has negative stride.
Torch.tensor与PIL.Image转换
# pytorch中的张量默认采用[N, C, H, W]的顺序,并且数据范围在[0,1],需要进行转置和规范化
# torch.Tensor -> PIL.Image
image = PIL.Image.fromarray(torch.clamp(tensor*255, min=0, max=255).byte().permute(1,2,0).cpu().numpy())
image = torchvision.transforms.functional.to_pil_image(tensor) # Equivalently way
# PIL.Image -> torch.Tensor
path = r'./figure.jpg'
tensor = torch.from_numpy(np.asarray(PIL.Image.open(path))).permute(2,0,1).float() / 255
tensor = torchvision.transforms.functional.to_tensor(PIL.Image.open(path)) # Equivalently way
np.ndarray与PIL.Image的转换‘
image = PIL.Image.fromarray(ndarray.astype(np.uint8))
ndarray = np.asarray(PIL.Image.open(path))
从只包含一个元素的张量中提取值
value = torch.rand(1).item()
3. 模型定义和操作
一个简单两层卷积网络的示例
# convolutional neural network (2 convolutional layers)
class ConvNet(nn.Module):
def __init__(self, num_classes=10):
super(ConvNet, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(16),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.layer2 = nn.Sequential(
nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.fc = nn.Linear(7*7*32, num_classes)
def forward(self, x):
out = self.layer1(x)
out = self.layer2(out)
out = out.reshape(out.size(0), -1)
out = self.fc(out)
return out
model = ConvNet(num_classes).to(device)
双线性汇合(bilinear pooling)
X = torch.reshape(N, D, H * W) # Assume X has shape N*D*H*W
X = torch.bmm(X, torch.transpose(X, 1, 2)) / (H * W) # Bilinear pooling
assert X.size() == (N, D, D)
X = torch.reshape(X, (N, D * D))
X = torch.sign(X) * torch.sqrt(torch.abs(X) + 1e-5) # Signed-sqrt normalization
X = torch.nn.functional.normalize(X) # L2 normalization
多卡同步 BN(Batch normalization)*
当使用 torch.nn.DataParallel 将代码运行在多张 GPU 卡上时,PyTorch 的 BN 层默认操作是各卡上数据独立地计算均值和标准差,同步 BN 使用所有卡上的数据一起计算 BN 层的均值和标准差,缓解了当批量大小(batch size)比较小时对均值和标准差估计不准的情况,是在目标检测等任务中一个有效的提升性能的技巧。
sync_bn = torch.nn.SyncBatchNorm(num_features, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
将已有网络的所有BN层改为同步BN层
def convertBNtoSyncBN(module, process_group=None):
'''Recursively replace all BN layers to SyncBN layer.
Args:
module[torch.nn.Module]. Network
'''
if isinstance(module, torch.nn.modules.batchnorm._BatchNorm):
sync_bn = torch.nn.SyncBatchNorm(module.num_features, module.eps, module.momentum,
module.affine, module.track_running_stats, process_group)
sync_bn.running_mean = module.running_mean
sync_bn.running_var = module.running_var
if module.affine:
sync_bn.weight = module.weight.clone().detach()
sync_bn.bias = module.bias.clone().detach()
return sync_bn
else:
for name, child_module in module.named_children():
setattr(module, name) = convert_syncbn_model(child_module, process_group=process_group))
return module
计算模型整体参数量
num_parameters = sum(torch.numel(parameter) for parameter in model.parameters())
查看网络中的参数
可以通过model.state_dict()或者model.named_parameters()函数查看现在的全部可训练参数(包括通过继承得到的父类中的参数)
params = list(model.named_parameters())
(name, param) = params[28]
print(name)
print(param.grad)
print('-------------------------------------------------')
(name2, param2) = params[29]
print(name2)
print(param2.grad)
print('----------------------------------------------------')
(name1, param1) = params[30]
print(name1)
print(param1.grad)
模型可视化(使用pytorchviz)
....
4. 模型训练和测试
分类模型训练代码
# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
for i ,(images, labels) in enumerate(train_loader):
images = images.to(device)
labels = labels.to(device)
# Forward pass
outputs = model(images)
loss = criterion(outputs, labels)
# Backward and optimizer
optimizer.zero_grad()
loss.backward()
optimizer.step()
if (i+1) % 100 == 0:
print('Epoch: [{}/{}], Step: [{}/{}], Loss: {}'
.format(epoch+1, num_epochs, i+1, total_step, loss.item()))
分类模型测试代码
# Test the model
model.eval() # eval mode(batch norm uses moving mean/variance
#instead of mini-batch mean/variance)
with torch.no_grad():
correct = 0
total = 0
for images, labels in test_loader:
images = images.to(device)
labels = labels.to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Test accuracy of the model on the 10000 test images: {} %'
.format(100 * correct / total))
自定义loss
继承torch.nn.Module类写自己的loss。
class MyLoss(torch.nn.Moudle):
def __init__(self):
super(MyLoss, self).__init__()
def forward(self, x, y):
loss = torch.mean((x - y) ** 2)
return loss
标签平滑(label smoothing)
写一个label_smoothing.py的文件,然后在训练代码里引用,用LSR代替交叉熵损失即可。label_smoothing.py内容如下:
import torch
import torch.nn as nn
class LSR(nn.Module):
def __init__(self, e=0.1, reduction='mean'):
super().__init__()
self.log_softmax = nn.LogSoftmax(dim=1)
self.e = e
self.reduction = reduction
def _one_hot(self, labels, classes, value=1):
"""
Convert labels to one hot vectors
Args:
labels: torch tensor in format [label1, label2, label3, ...]
classes: int, number of classes
value: label value in one hot vector, default to 1
Returns:
return one hot format labels in shape [batchsize, classes]
"""
one_hot = torch.zeros(labels.size(0), classes)
#labels and value_added size must match
labels = labels.view(labels.size(0), -1)
value_added = torch.Tensor(labels.size(0), 1).fill_(value)
value_added = value_added.to(labels.device)
one_hot = one_hot.to(labels.device)
one_hot.scatter_add_(1, labels, value_added)
return one_hot
def _smooth_label(self, target, length, smooth_factor):
"""convert targets to one-hot format, and smooth
them.
Args:
target: target in form with [label1, label2, label_batchsize]
length: length of one-hot format(number of classes)
smooth_factor: smooth factor for label smooth
Returns:
smoothed labels in one hot format
"""
one_hot = self._one_hot(target, length, value=1 - smooth_factor)
one_hot += smooth_factor / (length - 1)
return one_hot.to(target.device)
def forward(self, x, target):
if x.size(0) != target.size(0):
raise ValueError('Expected input batchsize ({}) to match target batch_size({})'
.format(x.size(0), target.size(0)))
if x.dim() < 2:
raise ValueError('Expected input tensor to have least 2 dimensions(got {})'
.format(x.size(0)))
if x.dim() != 2:
raise ValueError('Only 2 dimension tensor are implemented, (got {})'
.format(x.size()))
smoothed_target = self._smooth_label(target, x.size(1), self.e)
x = self.log_softmax(x)
loss = torch.sum(- x * smoothed_target, dim=1)
if self.reduction == 'none':
return loss
elif self.reduction == 'sum':
return torch.sum(loss)
elif self.reduction == 'mean':
return torch.mean(loss)
else:
raise ValueError('unrecognized option, expect reduction to be one of none, mean, sum')
模型训练可视化
PyTorch可以使用tensorboard来可视化训练过程。安装和运行TensorBoard。
pip install tensorboard
tensorboard --logdir=runs
使用SummaryWriter类来收集和可视化相应的数据,放了方便查看,可以使用不同的文件夹,比如'Loss/train'和'Loss/test'。
from torch.utils.tensorboard import SummaryWriter
import numpy as np
writer = SummaryWriter()
for n_iter in range(100):
writer.add_scalar('Loss/train', np.random.random(), n_iter)
writer.add_scalar('Loss/test', np.random.random(), n_iter)
writer.add_scalar('Accuracy/train', np.random.random(), n_iter)
writer.add_scalar('Accuracy/test', np.random.random(), n_iter)
保存与加载断点
注意为了能够恢复训练,我们需要同时保存模型和优化器的状态,以及当前的训练轮数。
start_epoch = 0
# Load checkpoint.
if resume: # resume为参数,第一次训练时设为0,中断再训练时设为1
model_path = os.path.join('model', 'best_checkpoint.pth.tar')
assert os.path.isfile(model_path)
checkpoint = torch.load(model_path)
best_acc = checkpoint['best_acc']
start_epoch = checkpoint['epoch']
model.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
print('Load checkpoint at epoch {}.'.format(start_epoch))
print('Best accuracy so far {}.'.format(best_acc))
# Train the model
for epoch in range(start_epoch, num_epochs):
...
# Test the model
...
# save checkpoint
is_best = current_acc > best_acc
best_acc = max(current_acc, best_acc)
checkpoint = {
'best_acc': best_acc,
'epoch': epoch + 1,
'model': model.state_dict(),
'optimizer': optimizer.state_dict(),
}
model_path = os.path.join('model', 'checkpoint.pth.tar')
best_model_path = os.path.join('model', 'best_checkpoint.pth.tar')
torch.save(checkpoint, model_path)
if is_best:
shutil.copy(model_path, best_model_path)
5,其他注意事项
不要使用太大的线性层。因为nn.Linear(m,n)使用的是O(mn)的内存,线性层太大很容易超出现有显存。
不要在太长的序列上使用RNN。因为RNN反向传播使用的是BPTT算法,其需要的内存和输入序列的长度呈线性关系。
model(x) 前用 model.train() 和 model.eval() 切换网络状态。
不需要计算梯度的代码块用 with torch.no_grad() 包含起来。
model.eval() 和 torch.no_grad() 的区别在于,model.eval() 是将网络切换为测试状态,例如 BN 和dropout在训练和测试阶段使用不同的计算方法。torch.no_grad() 是关闭 PyTorch 张量的自动求导机制,以减少存储使用和加速计算,得到的结果无法进行 loss.backward()。
model.zero_grad()会把整个模型的参数的梯度都归零, 而optimizer.zero_grad()只会把传入其中的参数的梯度归零.
torch.nn.CrossEntropyLoss 的输入不需要经过 Softmax。torch.nn.CrossEntropyLoss 等价于 torch.nn.functional.log_softmax + torch.nn.NLLLoss。
loss.backward() 前用 optimizer.zero_grad() 清除累积梯度。
torch.utils.data.DataLoader 中尽量设置 pin_memory=True,对特别小的数据集如 MNIST 设置 pin_memory=False 反而更快一些。num_workers 的设置需要在实验中找到最快的取值。
用 del 及时删除不用的中间变量,节约 GPU 存储。
使用 inplace 操作可节约 GPU 存储,如
x = torch.nn.functional.relu(x, inplace=True)
减少 CPU 和 GPU 之间的数据传输。例如如果你想知道一个 epoch 中每个 mini-batch 的 loss 和准确率,先将它们累积在 GPU 中等一个 epoch 结束之后一起传输回 CPU 会比每个 mini-batch 都进行一次 GPU 到 CPU 的传输更快。
使用半精度浮点数 half() 会有一定的速度提升,具体效率依赖于 GPU 型号。需要小心数值精度过低带来的稳定性问题。
时常使用 assert tensor.size() == (N, D, H, W) 作为调试手段,确保张量维度和你设想中一致。
除了标记 y 外,尽量少使用一维张量,使用 n*1 的二维张量代替,可以避免一些意想不到的一维张量计算结果。