zoukankan      html  css  js  c++  java
  • Pytorch学习笔记01----pytorch框架介绍

    1.深度学习框架

    pytorch与其他框架的比较

    pytorch的学习方法:

    课程安排:

    PyTorch是一个基于Python的科学计算库,它有以下特点:

    • 类似于NumPy,但是它可以使用GPU
    • 可以用它定义深度学习模型,可以灵活地进行深度学习模型的训练和使用

    2.tensor的运算

    Tensor类似与NumPy的ndarray,唯一的区别是Tensor可以在GPU上加速运算。

    (1)加法

    x = torch.rand(5,3)
    y = torch.rand(5,3)
    z=x+y
    print(x)
    print(y)
    print(z)

    效果图:

    (2)Torch Tensor和NumPy array会共享内存,所以改变其中一项也会改变另一项。

    把Torch Tensor转变成NumPy Array

    # Torch Tensor和NumPy array会共享内存,所以改变其中一项也会改变另一项。
    # 把Torch Tensor转变成NumPy Array
    a = torch.ones(5)
    b = a.numpy()
    print(a)
    print(b)
    b[1] = 2
    print(a)

    效果图:

    (3)在Torch Tensor和NumPy array之间相互转化非常容易。

    # 把NumPy ndarray转成Torch Tensor
    a = np.ones(5)
    b = torch.from_numpy(a)
    np.add(a, 1, out=a)
    print(a)
    print(b)

    效果图:

    3.利用Pytorch的nn库来构建神经网络

    这次我们使用PyTorch中nn这个库来构建网络。 用PyTorch autograd来构建计算图和计算gradients, 然后PyTorch会帮我们自动计算gradient。

    import torch.nn as nn
    import torch
    N, D_in, H, D_out = 64, 1000, 100, 10
    
    # 随机创建一些训练数据
    x = torch.randn(N, D_in)
    y = torch.randn(N, D_out)
    
    model = torch.nn.Sequential(
        torch.nn.Linear(D_in, H, bias=False),  # w_1 * x + b_1
        torch.nn.ReLU(),
        torch.nn.Linear(H, D_out, bias=False),
    )
    
    torch.nn.init.normal_(model[0].weight)
    torch.nn.init.normal_(model[2].weight)
    
    # model = model.cuda()
    
    loss_fn = nn.MSELoss(reduction='sum')
    
    learning_rate = 1e-6
    for it in range(500):
        # Forward pass
        y_pred = model(x)  # model.forward()
    
        # compute loss
        loss = loss_fn(y_pred, y)  # computation graph
        print(it, loss.item())
    
        # Backward pass
        loss.backward()
    
        # update weights of w1 and w2
        with torch.no_grad():
            for param in model.parameters():  # param (tensor, grad)
                param -= learning_rate * param.grad
    
        model.zero_grad()

    效果图:

    4.自定义nn modules

    我们可以定义一个模型,这个模型继承自nn.Module类。如果需要定义一个比Sequential模型更加复杂的模型,就需要定义nn.Module模型。

    import torch.nn as nn
    import torch
    
    N, D_in, H, D_out = 64, 1000, 100, 10
    
    # 随机创建一些训练数据
    x = torch.randn(N, D_in)
    y = torch.randn(N, D_out)
    
    # 自定义模型,定义一个类继承torch.nn.Module
    class TwoLayerNet(torch.nn.Module):
        def __init__(self, D_in, H, D_out):
            super(TwoLayerNet, self).__init__()
            # define the model architecture
            self.linear1 = torch.nn.Linear(D_in, H, bias=False)
            self.linear2 = torch.nn.Linear(H, D_out, bias=False)
    
        def forward(self, x):
            y_pred = self.linear2(self.linear1(x).clamp(min=0))
            return y_pred
    
    
    model = TwoLayerNet(D_in, H, D_out)
    # 定义损失函数
    loss_fn = nn.MSELoss(reduction='sum')
    learning_rate = 1e-4
    optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
    
    for it in range(500):
        # Forward pass
        y_pred = model(x)  # model.forward()
    
        # compute loss
        loss = loss_fn(y_pred, y)  # computation graph
        print(it, loss.item())
    
        optimizer.zero_grad()
        # Backward pass
        loss.backward()
    
        # update model parameters
        optimizer.step()
  • 相关阅读:
    配置HDFS HttpFS和WebHDFS
    编译hbase-1.2.3源代码
    Yarn application has already exited with state FINISHED
    一种基于Redis的10行代码实现IP频率控制方法
    PRId64的正确用法
    cmake检测g++编译器是否支持c++11
    定时取指定进程内存脚本
    C++常见gcc编译链接错误解决方法
    Congestion Avoidance in TCP
    Studying TCP's Throughput and Goodput using NS
  • 原文地址:https://www.cnblogs.com/luckyplj/p/13131838.html
Copyright © 2011-2022 走看看