Pytorch第一部分数据模块

news2024/10/1 16:32:30

数据划分：

从数据集中将数据划分为训练集，测试集，验证集

# -*- coding: utf-8 -*-
"""
# @file name  : 1_split_dataset.py
# @author     : tingsongyu
# @date       : 2019-09-07 10:08:00
# @brief      : 将数据集划分为训练集，验证集，测试集
"""

import os
import random
import shutil


def makedir(new_dir):
    if not os.path.exists(new_dir):
        os.makedirs(new_dir)


if __name__ == '__main__':

    random.seed(1)

    dataset_dir = "F:\\depthlearning data\\RMB_data"
    split_dir = "F:\\depthlearning data\\rmb_split"
    train_dir = os.path.join(split_dir, "train")
    valid_dir = os.path.join(split_dir, "valid")
    test_dir = os.path.join(split_dir, "test")

    train_pct = 0.8
    valid_pct = 0.1
    test_pct = 0.1

    for root, dirs, files in os.walk(dataset_dir):
        for sub_dir in dirs:

            imgs = os.listdir(os.path.join(root, sub_dir))
            imgs = list(filter(lambda x: x.endswith('.jpg'), imgs))
            random.shuffle(imgs)
            img_count = len(imgs)

            train_point = int(img_count * train_pct)
            valid_point = int(img_count * (train_pct + valid_pct))

            for i in range(img_count):
                if i < train_point:
                    out_dir = os.path.join(train_dir, sub_dir)
                elif i < valid_point:
                    out_dir = os.path.join(valid_dir, sub_dir)
                else:
                    out_dir = os.path.join(test_dir, sub_dir)

                makedir(out_dir)

                target_path = os.path.join(out_dir, imgs[i])
                src_path = os.path.join(dataset_dir, sub_dir, imgs[i])

                shutil.copy(src_path, target_path)

            print('Class:{}, train:{}, valid:{}, test:{}'.format(sub_dir, train_point, valid_point-train_point,
                                                                 img_count-valid_point))

整体代码：人民币二分类训练，这里只关注数据部分

# -*- coding: utf-8 -*-
"""
# @file name  : train_lenet.py
# @author     : tingsongyu
# @date       : 2019-09-07 10:08:00
# @brief      : 人民币分类模型训练
"""
import os
import random
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


def set_seed(seed=1):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed(seed)


set_seed()  # 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.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()

            loss_val_epoch = loss_val / len(valid_loader)
            valid_curve.append(loss_val_epoch)
            # valid_curve.append(loss.item())    # 20191022改，记录整个epoch样本的loss，注意要取平均
            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_epoch, correct_val / total_val))


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
    print("模型获得{}元".format(rmb))

数据部分：

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

#读取数据路径
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]

#训练集 数据预处理  缩放 裁剪 转换为张量 
train_transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.RandomCrop(32, padding=4),
    transforms.ToTensor(),
    transforms.Normalize(norm_mean, norm_std),
])
#验证集 少了裁剪的方法
valid_transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.ToTensor(),
    transforms.Normalize(norm_mean, norm_std),
])

# 构建MyDataset实例  传入数据路径 数据预处理
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)

dataloader分为sampler（索引）和dataset（标签）