PyTorch 基础篇（1）：Pytorch 基础

  import torchprint(torch.version)

  0.4.1

  # 包import torch import torchvisionimport torch.nn as nnimport numpy as npimport torchvision.transforms as transforms

  # 创建张量（tensors）x = torch.tensor(1., requires_grad=True)w = torch.tensor(2., requires_grad=True)b = torch.tensor(3., requires_grad=True) # 构建计算图（ computational graph）：前向计算y = w * x + b    # y = 2 * x + 3 # 反向传播，计算梯度（gradients）y.backward() # 输出梯度print(x.grad)    # x.grad = 2 print(w.grad)    # w.grad = 1 print(b.grad)    # b.grad = 1

  tensor(2.)tensor(1.)tensor(1.)

  # 创建大小为 (10, 3) 和 (10, 2)的张量.x = torch.randn(10, 3)y = torch.randn(10, 2) # 构建全连接层（fully connected layer）linear = nn.Linear(3, 2)print ('w: ', linear.weight)print ('b: ', linear.bias) # 构建损失函数和优化器（loss function and optimizer）# 损失函数使用均方差# 优化器使用随机梯度下降，lr是learning ratecriterion = nn.MSELoss()optimizer = torch.optim.SGD(linear.parameters(), lr=0.01) # 前向传播pred = linear(x) # 计算损失loss = criterion(pred, y)print('loss: ', loss.item()) # 反向传播loss.backward() # 输出梯度print ('dL/dw: ', linear.weight.grad) print ('dL/db: ', linear.bias.grad) # 执行一步-梯度下降（1-step gradient descent）optimizer.step() # 更底层的实现方式是这样子的# linear.weight.data.sub_(0.01 * linear.weight.grad.data)# linear.bias.data.sub_(0.01 * linear.bias.grad.data) # 进行一次梯度下降之后，输出新的预测损失# loss的确变少了pred = linear(x)loss = criterion(pred, y)print(‘loss after 1 step optimization: ‘, loss.item())

  w:  Parameter containing:tensor([[ 0.5180,  0.2238, -0.5470],        [ 0.1531,  0.2152, -0.4022]], requires_grad=True)b:  Parameter containing:tensor([-0.2110, -0.2629], requires_grad=True)loss:  0.8057981729507446dL/dw:  tensor([[-0.0315,  0.1169, -0.8623],        [ 0.4858,  0.5005, -0.0223]])dL/db:  tensor([0.1065, 0.0955])loss after 1 step optimization:  0.7932316660881042

  # 创建Numpy数组x = np.array([[1, 2], [3, 4]])print(x) # 将numpy数组转换为torch的张量y = torch.from_numpy(x)print(y) # 将torch的张量转换为numpy数组z = y.numpy()print(z)

  [[1 2] [3 4]]tensor([[1, 2],        [3, 4]])[[1 2] [3 4]]

  # 下载和构造CIFAR-10 数据集# Cifar-10数据集介绍：https://www.cs.toronto.edu/~kriz/cifar.htmltrain_dataset = torchvision.datasets.CIFAR10(root=’…/…/…/data/’,                                             train=True,                                              transform=transforms.ToTensor(),                                             download=True) # 获取一组数据对（从磁盘中读取）image, label = train_dataset[0]print (image.size())print (label) # 数据加载器（提供了队列和线程的简单实现）train_loader = torch.utils.data.DataLoader(dataset=train_dataset,                                           batch_size=64,                                            shuffle=True) # 迭代的使用# 当迭代开始时，队列和线程开始从文件中加载数据data_iter = iter(train_loader) # 获取一组mini-batchimages, labels = data_iter.next()  # 正常的使用方式如下：for images, labels in train_loader:    # 在此处添加训练用的代码    pass

  Files already downloaded and verifiedtorch.Size([3, 32, 32])6

  # 构建自定义数据集的方式如下：class CustomDataset(torch.utils.data.Dataset):    def init(self):        # TODO        # 1. 初始化文件路径或者文件名        pass    def getitem(self, index):        # TODO        # 1. 从文件中读取一份数据（比如使用nump.fromfile，PIL.Image.open）        # 2. 预处理数据（比如使用 torchvision.Transform）        # 3. 返回数据对（比如 image和label）        pass    def len(self):        # 将0替换成数据集的总长度        return 0     # 然后就可以使用预置的数据加载器（data loader）了custom_dataset = CustomDataset()train_loader = torch.utils.data.DataLoader(dataset=custom_dataset,                                           batch_size=64,                                            shuffle=True) 预训练模型

  # 下载并加载预训练好的模型 ResNet-18resnet = torchvision.models.resnet18(pretrained=True)  # 如果想要在模型仅对Top Layer进行微调的话，可以设置如下：# requieres_grad设置为False的话，就不会进行梯度更新，就能保持原有的参数for param in resnet.parameters():    param.requires_grad = False        # 替换TopLayer，只对这一层做微调resnet.fc = nn.Linear(resnet.fc.in_features, 100)  # 100 is an example. # 前向传播images = torch.randn(64, 3, 224, 224)outputs = resnet(images)print (outputs.size())     # (64, 100)

  torch.Size([64, 100])

  # 保存和加载整个模型torch.save(resnet, ‘model.ckpt’)model = torch.load(‘model.ckpt’) # 仅保存和加载模型的参数（推荐这个方式）torch.save(resnet.state_dict(), ‘params.ckpt’)resnet.load_state_dict(torch.load(‘params.ckpt’))