Pytorch实战笔记

Posted 2022-03-16 GoAI

实战配套视频：《PyTorch深度学习实践》完结合集

实战笔记：

Learning_AI的博客_学习CV的研一小白_PyTorch学习笔记,

刘二大人：pytorch深度学习实践（代码详细笔记，适合零基础）

pytorch实战教学（一篇管够）_小星AI-CSDN博客_pytorch实战

Pytorch学习笔记--Bilibili刘二大人Pytorch教学代码汇总

线性模型

import numpy as np
import matplotlib.pyplot as plt

x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]

def forward(x):
    return x * w

def loss(x, y):
    y_pred = forward(x)
    return (y_pred - y) * (y_pred - y)

w_list = []
mse_list = []
for w in np.arange(0.0, 4.1, 0.1):
    print('w=', w)
    l_sum = 0
    for x_val, y_val in zip(x_data, y_data):
        y_pred_val = forward(x_val)
        loss_val = loss(x_val, y_val)
        l_sum += loss_val
        print('\\t', x_val, y_val, y_pred_val, loss_val)
    print('MSE=', l_sum / 3)
    w_list.append(w)
    mse_list.append(l_sum / 3)

plt.plot(w_list, mse_list)
plt.ylabel('Loss')
plt.xlabel('w')
plt.show()

运行截图如下：

梯度下降

     以模型 为例，梯度下降算法就是一种训练参数  到最佳值的一种算法， 每次变化的趋势由 （学习率：一种超参数，由人手动设置调节），以及 的导数来决定，具体公式如下：  

注： 此时函数是指所有的损失函数之和

针对模型  的梯度下降算法的公式化简如下：

# 输入训练数据
x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]
 
# 设置初始参数
w = 1.0  # 初始权重
alpha = 0.005 #初始梯度下降法的学习率
 
# 定义计算y_hat的函数
def forward(x):
    return x * w
 
# 定义计算平均损失的函数
def cost(xs, ys):
    sum_cost = 0
    for x, y in zip(xs, ys):  # zip函数的功能是打包为元组列表
        y_pred = forward(x)
        sum_cost += (y_pred - y) ** 2
    return sum_cost / len(xs)
 
def gradient(xs, ys):
    grad = 0
    for x, y in zip(xs, ys):
        grad += 2 * x * (x * w - y)
    return grad / len(xs)
 
print('Predict (before training)', 4, forward(4))  # 计算训练前初始参数对应的y_hat值
for epoch in range(1000):
    cost_val = cost(x_data, y_data)   # 计算平均损失值
    grad_val = gradient(x_data, y_data) # 计算梯度值
    w -= alpha * grad_val # 更新权重w
    print('Epoch', epoch, 'w = ', w, 'loss = ', cost_val) # 输出当前迭代次数的权重值和平均损失值
 
print('Predict (after training)', 4, forward(4)) #计算训练权重w后，对应的y_hat值
 

随机梯度下降：

       随机梯度下降算法与梯度下降算法的不同之处在于，随机梯度下降算法不再计算损失函数之和的导数，而是随机选取任一随机函数计算导数，随机的决定  下次的变化趋势，具体公式变化如图：

# 输入训练数据
x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]
 
# 设置初始参数
w = 1.0  # 初始权重
alpha = 0.005 #初始梯度下降法的学习率
 
# 定义计算y_hat的函数
def forward(x):
    return x * w
 
# 定义计算单个样本损失的函数
def loss(xs, ys):
    y_pred = forward(x) # 计算预测值y_hat
    single_lost = (y_pred - ys) ** 2 # 计算误差
    return single_lost
 
def gradient(xs, ys):
    grad = 2 * x * (x * w - y)
    return grad
 
print('Predict (before training)', 4, forward(4))  # 计算训练前初始参数对应的y_hat值
for epoch in range(1000): # 迭代次数
    for x, y in zip(x_data, y_data): # 遍历数据
        grad_val = gradient(x, y)    # 计算当前数据的梯度值
        w -= alpha * grad_val        # 更新权重w
        print("\\tgrad: ", x, y, grad_val)
        los = loss(x, y)  # 计算当前数据的损失值
    print('progress: ', epoch, 'w = ', w, 'loss = ', los)
 
print('Predict (after training)', 4, forward(4)) # 计算训练权重w后，对应的y_hat值

反向传播

import torch

x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]

w = torch.Tensor([1.0])
w.requires_grad = True  # 需要计算梯度

def forward(x):
    return x * w  # tensor
    
def loss(x, y):
    y_pred = forward(x)
    return (y_pred - y) ** 2

print('predict (before training)', 4, forward(4).item())
for epoch in range(100):
    for x, y in zip(x_data, y_data):
        l = loss(x, y) # 前向，计算loss
        l.backward() # 做完后计算图会释放
        print('\\tgrad:', x, y, w.grad.item())  # item取值，要是张量计算图一直累积
        w.data -= 0.01 * w.grad.data  # 不取data会是TENSOR有计算图

        w.grad.data.zero_()  # 计算出来的梯度不清零会累加
    print("progress:", epoch, l.item())
print('predict (after training)', 4, forward(4).item())

Pytorch实战--线性回归

# 1、算预测值
# 2、算loss
# 3、梯度设为0，并反向传播
# 3、梯度更新


import torch

x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[2.0], [4.0], [6.0]])


# 构造线性模型,后面都是使用这样的模板
# 至少实现两个函数，__init__构造函数和forward()前馈函数
# backward()会根据我们的计算图自动构建
# 可以继承Functions来构建自己的计算块
class LinerModel(torch.nn.Module):
    def __init__(self):
        # 调用父类的构造
        super(LinerModel, self).__init__()
        # 构造Linear这个对象，对输入数据做线性变换
        # class torch.nn.Linear(in_features, out_features, bias=True)
        # in_features - 每个输入样本的大小
        # out_features - 每个输出样本的大小
        # bias - 若设置为False，这层不会学习偏置。默认值：True
        self.linear = torch.nn.Linear(1, 1)

    def forward(self, x):
        y_pred = self.linear(x)
        return y_pred


model = LinerModel() # 实例化，可调用
# 定义MSE(均方差)损失函数，size_average=False不求均值
criterion = torch.nn.MSELoss(size_average=False)
# optim优化模块的SGD，第一个参数就是传递权重，model.parameters()model的所有权重
# 优化器对象
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

for epoch in range(100):
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    # loss为一个对象，loss不会产生计算图，但会自动调用__str__()所以不会出错
    print(epoch, loss)
    # 梯度归零
    optimizer.zero_grad()
    # 反向传播
    loss.backward()
    # 根据梯度和预先设置的学习率进行更新（权重更新）
    optimizer.step()

# 打印权重和偏置值,weight是一个值但是一个矩阵
print('w=', model.linear.weight.item())
print('b=', model.linear.bias.item())

# 测试
x_test = torch.Tensor([4.0])
y_test = model(x_test)
print('y_pred=', y_test.data)

结果图：

Pytorch实战--逻辑回归

import torch
import torch.nn.functional as F
import numpy as np
import matplotlib.pyplot as plt
 
x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[0], [0], [1]])
 
##
class LogisticRegressionModel(torch.nn.Module):
    def __init__(self): #构造函数
        super(LogisticRegressionModel, self).__init__()
        self.linear = torch.nn.Linear(1, 1) #线性层
 
    def forward(self, x):
        y_pred = F.sigmoid(self.linear(x)) #激活函数
        return y_pred
 
model = LogisticRegressionModel()
 
##
criterion = torch.nn.BCELoss(size_average = False) #计算损失
optimizer = torch.optim.SGD(model.parameters(), lr = 0.01) #优化器
 
##
for epoch in range(1000):
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    print(epoch, loss.item())
 
    optimizer.zero_grad() # 梯度置0
    loss.backward() # 计算梯度，反向传播
    optimizer.step() # 更新参数
 
##
x = np.linspace(0, 10, 200)
x_t = torch.Tensor(x).view((200, 1))
y_t = model(x_t)
y = y_t.data.numpy()
plt.plot(x, y)
plt.plot([0, 10], [0.5, 0.5], c='r')
plt.xlabel('Hours')
plt.ylabel('Probability of Pass')
plt.grid()
plt.show()

RNN

1.准备数据
定义一个数据集类，并读取数据文件。

from torch.utils.data import Dataset
import pandas as pd

class NameDataset(Dataset):
    """数据集类"""
    def __init__(self, is_train_set=True):
        filename = './name_data/names_train.csv' if is_train_set else './name_data/names_test.csv'
        data = pd.read_csv(filename, header=None)
        self.names = data[0]
        self.len = len(self.names)
        self.countries = data[1]
        self.country_list = list(sorted(set(self.countries)))
        self.country_dict = self.getCountryDict()
        self.country_num = len(self.country_list)
    
    def __getitem__(self, index):
        return self.names[index], self.country_dict[self.countries[index]]
    
    def __len__(self):
        return self.len

    def idx2country(self, index):
        return self.country_list[index]

    def getCountryDict(self):
        country_dict = dict()
        for idx, country_name in enumerate(self.country_list, 0):
            country_dict[country_name] = idx
        return country_dict

    def getCountriesNum(self):
        return self.country_num

定义函数，用于将读取到的数据转化为tensor。

def name2list(name):
    """返回ASCII码表示的姓名列表与列表长度"""
    arr = [ord(c) for c in name]
    return arr, len(arr)


def make_tensors(names, countries):
    # 元组列表，每个元组包含ASCII码表示的姓名列表与列表长度
    sequences_and_lengths = [name2list(name) for name in names]
    # 取出所有的ASCII码表示的姓名列表
    name_sequences = [sl[0] for sl in sequences_and_lengths]
    # 取出所有的列表长度
    seq_lengths = torch.LongTensor([sl[1] for sl in sequences_and_lengths])
    # 将countries转为long型
    countries = countries.long()

    # 接下来每个名字序列补零，使之长度一样。
    # 先初始化一个全为零的tensor，大小为 所有姓名的数量*最长姓名的长度
    seq_tensor = torch.zeros(len(name_sequences), seq_lengths.max()).long()

    # 将姓名序列覆盖到初始化的全零tensor上
    for idx, (seq, seq_len) in enumerate(zip(name_sequences, seq_lengths), 0):
        seq_tensor[idx, :seq_len] = torch.LongTensor(seq)
    # 根据序列长度seq_lengths对补零后tensor进行降序怕排列，方便后面加速计算。
    # 返回排序后的seq_lengths与索引变化列表
    seq_lengths, perm_idx = seq_lengths.sort(dim=0, descending=True)
    # 根据索引变化列表对ASCII码表示的姓名列表进行排序
    seq_tensor = seq_tensor[perm_idx]
    # 根据索引变化列表对countries进行排序，使姓名与国家还是一一对应关系
    # seq_tensor.shape : batch_size*max_seq_lengths,
    # seq_lengths.shape : batch_size
    # countries.shape : batch_size
    countries = countries[perm_idx]
    return seq_tensor, seq_lengths, countries

2.定义模型

import torch
from torch.nn.utils.rnn import pack_padded_sequence

class RNNClassifier(torch.nn.Module):
    # input_size=128, hidden_size=100, output_size=18
    def __init__(self, input_size, hidden_size, output_size, n_layers=1, bidirectional=True):
        super(RNNClassifier, self).__init__()
        self.hidden_size = hidden_size
        self.n_layers = n_layers
        self.n_directions = 2 if bidirectional else 1  # 是否双向
        self.embedding = torch.nn.Embedding(input_size, hidden_size)  # 输入大小128，输出大小100。
        # 经过Embedding后input的大小是100，hidden_size的大小也是100，所以形参都是hidden_size。
        self.gru = torch.nn.GRU(hidden_size, hidden_size, n_layers, bidirectional=bidirectional)
        # 如果是双向，会输出两个hidden层，要进行拼接，所以线形成的input大小是 hidden_size * self.n_directions，输出是大小是18，是为18个国家的概率。
        self.fc = torch.nn.Linear(hidden_size * self.n_directions, output_size)
    
    def _init_hidden(self, batch_size):
        hidden = torch.zeros(self.n_layers * self.n_directions, batch_size, self.hidden_size)
        return hidden

    def forward(self, input, seq_lengths):
        # 先对input进行转置，input shape : batch_size*max_seq_lengths -> max_seq_lengths*batch_size 每一列表示姓名
        input = input.t()
        batch_size = input.size(1)  # 总共有多少列，既是batch_size的大小
        hidden = self._init_hidden(batch_size)  # 初始化隐藏层
        embedding = self.embedding(input)  # embedding.shape : max_seq_lengths*batch_size*hidden_size 12*64*100
        # pack_padded_sequence方便批量计算
        gru_input = pack_padded_sequence(embedding, seq_lengths)
        # 进入网络进行计算
        output, hidden = self.gru(gru_input, hidden)

        # 如果是双向的，需要进行拼接
        if self.n_directions == 2:
            hidden_cat = torch.cat([hidden[-1], hidden[-2]], dim=1)

        else:
            hidden_cat = hidden[-1]

        # 线性层输出大小为18
        fc_output = self.fc(hidden_cat)
        return fc_output

3.定义训练函数

def time_since(since):
    s = time.time() - since
    m = math.floor(s/60)
    s-= m*60
    return '%dm %ds' % (m, s)


def trainModel():
    total_loss = 0
    for i, (names, countries) in enumerate(trainloader, 1):  # 这里的1意思是 i 从1开始。
        # make_tensors函数返回经过降序排列后的 姓名列表，列表长度，国家
        inputs, seq_lengths, target = make_tensors(names, countries)
        # 输入姓名列表与列表长度向前计算
        output = classifier(inputs, seq_lengths)
        loss = criterion(output, target)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        total_loss += loss.item()
        if i % 10 == 0:
            print(i)
            print(f'[time_since(start)] Epoch epoch ', end='')
            print(f'[i * len(inputs)/len(trainset)] ', end='')
            print(f'loss=total_loss / (i * len(inputs))')
    return total_loss

4.定义测试函数，跟训练函数相差不大

def testModel():
    correct = 0
    total = len(testset)
    print("evaluating trained model ...")
    with torch.no_grad():
        for i, (names, countries) in enumerate(testloader, 1):
            inputs, seq_lengths, target = make_tensors(names, countries)
            output = classifier(inputs, seq_lengths)
            pred = output.max(dim=1, keepdim=True)[1]
            correct += pred.eq(target.view_as(pred)).sum().item()
        percent = '%.2f' % (100 * correct / total)
        print(f'Test set: Accuracy correct/total percent%')
    return correct / total

5.主函数循环

from torch.utils.data import DataLoader
import time
import math

if __name__ == '__main__':
    
    N_EPOCHS = 30  # epoch
    HIDDEN_SIZE = 100  # 隐藏层的大小，也是Embedding后输出的大小
    BATCH_SIZE = 64
    N_COUNTRY = 18  # 总共有18个类别的国家，为RNN后输出的大小
    N_LAYER = 2
    N_CHARS = 128  # 字母字典的大小，Embedding输入的大小

    trainset = NameDataset(is_train_set=True)
    trainloader = DataLoader(trainset, batch_size=BATCH_SIZE, shuffle=True)

    testset = NameDataset(is_train_set=False)
    testloader = DataLoader(testset, batch_size=BATCH_SIZE, shuffle=False)

    # 建立分类模型
    classifier = RNNClassifier(N_CHARS, HIDDEN_SIZE, N_COUNTRY, N_LAYER)

    # 建立损失函数与优化器
    criterion = torch.nn.CrossEntropyLoss()
    optimizer = torch.optim.Adam(classifier.parameters(), lr=0.001)

    start = time.time()
    print("Training for %d epochs..." % N_EPOCHS)
    acc_list = []
    for epoch in range(1, N_EPOCHS + 1):
        # Train cycle
        trainModel()
        acc = testModel()
        acc_list.append(acc)