判别器loss为0_PyTorch 9.优化器

操作：

返回参数param_groups和缓存信息state。

一般在10或50个epoch的时候执行一次保存状态信息，用来由于意外导致模型的终止。

---

再回到之前的人民币二分类代码：

import os
import numpy as np
import torch
import torch.nn as nn
from torch.utils.data import DataLoader
import torchvision.transforms as transforms
import torch.optim as optim
from matplotlib import pyplot as plt
from model.lenet import LeNet
from tools.my_dataset import RMBDataset
from tools.common_tools import transform_invert, set_seed

set_seed(1)  # 设置随机种子
rmb_label = {"1": 0, "100": 1}

# 参数设置
MAX_EPOCH = 10
BATCH_SIZE = 16
LR = 0.01
log_interval = 10
val_interval = 1

# ============================ step 1/5 数据 ============================

split_dir = os.path.join("..", "..", "data", "rmb_split")
train_dir = os.path.join(split_dir, "train")
valid_dir = os.path.join(split_dir, "valid")

norm_mean = [0.485, 0.456, 0.406]
norm_std = [0.229, 0.224, 0.225]

train_transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.RandomCrop(32, padding=4),
    transforms.RandomGrayscale(p=0.8),
    transforms.ToTensor(),
    transforms.Normalize(norm_mean, norm_std),
])

valid_transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.ToTensor(),
    transforms.Normalize(norm_mean, norm_std),
])

# 构建MyDataset实例
train_data = RMBDataset(data_dir=train_dir, transform=train_transform)
valid_data = RMBDataset(data_dir=valid_dir, transform=valid_transform)

# 构建DataLoder
train_loader = DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
valid_loader = DataLoader(dataset=valid_data, batch_size=BATCH_SIZE)

# ============================ step 2/5 模型 ============================

net = LeNet(classes=2)
net.initialize_weights()

# ============================ step 3/5 损失函数 ============================
criterion = nn.CrossEntropyLoss()                                                   # 选择损失函数

# ============================ step 4/5 优化器 ============================
optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9)                        # 选择优化器
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=10, gamma=0.1)     # 设置学习率下降策略

# ============================ step 5/5 训练 ============================
train_curve = list()
valid_curve = list()

for epoch in range(MAX_EPOCH):

    loss_mean = 0.
    correct = 0.
    total = 0.

    net.train()
    for i, data in enumerate(train_loader):

        # forward
        inputs, labels = data
        outputs = net(inputs)

        # backward
        optimizer.zero_grad()
        loss = criterion(outputs, labels)
        loss.backward()

        # update weights
        optimizer.step()

        # 统计分类情况
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).squeeze().sum().numpy()

        # 打印训练信息
        loss_mean += loss.item()
        train_curve.append(loss.item())
        if (i+1) % log_interval == 0:
            loss_mean = loss_mean / log_interval
            print("Training:Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} Acc:{:.2%}".format(
                epoch, MAX_EPOCH, i+1, len(train_loader), loss_mean, correct / total))
            loss_mean = 0.

    scheduler.step()  # 更新学习率

    # validate the model
    if (epoch+1) % val_interval == 0:

        correct_val = 0.
        total_val = 0.
        loss_val = 0.
        net.eval()
        with torch.no_grad():
            for j, data in enumerate(valid_loader):
                inputs, labels = data
                outputs = net(inputs)
                loss = criterion(outputs, labels)

                _, predicted = torch.max(outputs.data, 1)
                total_val += labels.size(0)
                correct_val += (predicted == labels).squeeze().sum().numpy()

                loss_val += loss.item()

            valid_curve.append(loss_val)
            print("Valid:t Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} Acc:{:.2%}".format(
                epoch, MAX_EPOCH, j+1, len(valid_loader), loss_val, correct / total))


train_x = range(len(train_curve))
train_y = train_curve

train_iters = len(train_loader)
valid_x = np.arange(1, len(valid_curve)+1) * train_iters*val_interval # 由于valid中记录的是epochloss，需要对记录点进行转换到iterations
valid_y = valid_curve

plt.plot(train_x, train_y, label='Train')
plt.plot(valid_x, valid_y, label='Valid')

plt.legend(loc='upper right')
plt.ylabel('loss value')
plt.xlabel('Iteration')
plt.show()

# ============================ inference ============================

BASE_DIR = os.path.dirname(os.path.abspath(__file__))
test_dir = os.path.join(BASE_DIR, "test_data")

test_data = RMBDataset(data_dir=test_dir, transform=valid_transform)
valid_loader = DataLoader(dataset=test_data, batch_size=1)

for i, data in enumerate(valid_loader):
    # forward
    inputs, labels = data
    outputs = net(inputs)
    _, predicted = torch.max(outputs.data, 1)

    rmb = 1 if predicted.numpy()[0] == 0 else 100

    img_tensor = inputs[0, ...]  # C H W
    img = transform_invert(img_tensor, train_transform)
    plt.imshow(img)
    plt.title("LeNet got {} Yuan".format(rmb))
    plt.show()
    plt.pause(0.5)
    plt.close()

运行之后可以看到优化器的三个属性：

---

通过一个实验感受下optimizer的几个方法的作用：

先初始化一些变量：

import os
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
import torch
import torch.optim as optim
from tools.common_tools import set_seed

set_seed(1)  # 设置随机种子

weight = torch.randn((2, 2), requires_grad=True)
weight.grad = torch.ones((2, 2))

optimizer = optim.SGD([weight], lr=0.1)

flag = 1
# flag = 1
if flag:
    print("weight before step:{}".format(weight.data))
    optimizer.step()        # 修改lr=1 0.1观察结果
    print("weight after step:{}".format(weight.data))

可以发现，step()执行一次，weights朝着梯度的反方向更新了一次。

再看zero_grad()函数：

flag = 0
# flag = 1
if flag:

    print("weight before step:{}".format(weight.data))
    optimizer.step()        # 修改lr=1 0.1观察结果
    print("weight after step:{}".format(weight.data))

    print("weight in optimizer:{}nweight in weight:{}n".format(id(optimizer.param_groups[0]['params'][0]), id(weight)))

    print("weight.grad is {}n".format(weight.grad))
    optimizer.zero_grad()
    print("after optimizer.zero_grad(), weight.grad isn{}".format(weight.grad))

可以发现，梯度被置0了。

add_param_group()函数：添加了一组参数：

flag = 1
# flag = 1
if flag:
    print("optimizer.param_groups isn{}".format(optimizer.param_groups))

    w2 = torch.randn((3, 3), requires_grad=True)

    optimizer.add_param_group({"params": w2, 'lr': 0.0001})

    print("optimizer.param_groups isn{}".format(optimizer.param_groups))

输出为：原来param_groups只有1个字典，现在就有了2个字典。

optimizer.param_groups is
[{'params': [tensor([[0.6614, 0.2669],
        [0.0617, 0.6213]], requires_grad=True)], 'lr': 0.1, 'momentum': 0, 'dampening': 0, 'weight_decay': 0, 'nesterov': False}]

optimizer.param_groups is
[{'params': [tensor([[0.6614, 0.2669],
        [0.0617, 0.6213]], requires_grad=True)], 'lr': 0.1, 'momentum': 0, 'dampening': 0, 'weight_decay': 0, 'nesterov': False}, 
 {'params': [tensor([[-0.4519, -0.1661, -1.5228],
        [ 0.3817, -1.0276, -0.5631],
        [-0.8923, -0.0583, -0.1955]], requires_grad=True)], 'lr': 0.0001, 'momentum': 0, 'dampening': 0, 'weight_decay': 0, 'nesterov': False}]

flag = 0
# flag = 1
if flag:

    optimizer = optim.SGD([weight], lr=0.1, momentum=0.9)
    opt_state_dict = optimizer.state_dict()

    print("state_dict before step:n", opt_state_dict)

    for i in range(10):
        optimizer.step()

    print("state_dict after step:n", optimizer.state_dict())

    torch.save(optimizer.state_dict(), os.path.join(BASE_DIR, "optimizer_state_dict.pkl"))

# -----------------------------------load state_dict -----------------------------------
flag = 0
# flag = 1
if flag:

    optimizer = optim.SGD([weight], lr=0.1, momentum=0.9)
    state_dict = torch.load(os.path.join(BASE_DIR, "optimizer_state_dict.pkl"))

    print("state_dict before load state:n", optimizer.state_dict())
    optimizer.load_state_dict(state_dict)
    print("state_dict after load state:n", optimizer.state_dict())

params：是个list，每个元素是dict，字典里面有个key是params，对应的value就是参数了。