From fa4c1bf2fc24f97938266ff94b7457df5b0193b6 Mon Sep 17 00:00:00 2001 From: less IS more <13190735+wnflt@user.noreply.gitee.com> Date: Sun, 16 Jul 2023 07:10:04 +0000 Subject: [PATCH] =?UTF-8?q?=E5=88=A0=E9=99=A4=E6=96=87=E4=BB=B6=203.?= =?UTF-8?q?=E5=AE=9D=E5=8F=AF=E6=A2=A6=E6=95=B0=E6=8D=AE=E9=9B=86=E5=88=86?= =?UTF-8?q?=E6=9E=90/torch=E5=AE=9E=E7=8E=B0CNN=E6=9C=8D=E9=A5=B0=E5=88=86?= =?UTF-8?q?=E7=B1=BB.py?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- 3.宝可梦数据集分析/torch实现CNN服饰分类.py | 307 --------------------- 1 file changed, 307 deletions(-) delete mode 100644 3.宝可梦数据集分析/torch实现CNN服饰分类.py diff --git a/3.宝可梦数据集分析/torch实现CNN服饰分类.py b/3.宝可梦数据集分析/torch实现CNN服饰分类.py deleted file mode 100644 index 987215e..0000000 --- a/3.宝可梦数据集分析/torch实现CNN服饰分类.py +++ /dev/null @@ -1,307 +0,0 @@ -import os -import numpy as np -import pandas as pd -import torch -import torch.nn as nn -import torch.optim as optim -from torch.utils.data import Dataset, DataLoader - -# 配置训练环境和超参数 -# 根据系统的可用设备选择将张量放到GPU1或CPU上进行运算 -device = torch.device('cuda:1' if torch.cuda.is_available() else 'cpu') - -# 配置其他超参数 -batch_size = 256 # 每个批次训练的样本数 -num_workers = 0 -learning_rate = 1e-4 -epochs = 20 # 迭代次数 - -# 数据的读入和加载 -from torchvision import transforms - -image_size = 28 -data_transform = transforms.Compose([ - transforms.ToPILImage(), # 将张量转化为PIL图像对象 - transforms.Resize(image_size), - transforms.ToTensor() # 将PIL图像转化为张量 -]) - -# 读入csv格式的数据，自行构建Dataset类 -class FMDataset(Dataset): - def __init__(self, df, transform=None): # 默认没有数据转换操作 - self.df = df - self.transform = transform - self.images = df.iloc[:, 1:].values.astype(np.uint8) # .values将提取到的DataFrame数据转化为(无符号八位整数)numpy数组 - self.labels = df.iloc[:, 0].values - - def __len__(self): # 魔术方法，用于定义类的行为和操作，以模拟内置类型或实现类的特定功能 - return len(self.images) # 这里用于返回图片数据集的长度 - - def __getitem__(self, idx): # 用于通过索引来访问数据集和标签 - image = self.images[idx].reshape(28, 28, 1) - label = int(self.labels[idx]) # 根据索引获取对应对象 - if self.transform is not None: - image = self.transform(image) - else: - image = torch.tensor(image/255., dtype=torch.float) # 归一化 - label = torch.tensor(label, dtype=torch.long) - return image, label # 返回图像和标签元组 - - -train_df = pd.read_csv('fashion-mnist_train.csv') -test_df = pd.read_csv('fashion-mnist_test.csv') -train_data = FMDataset(train_df, data_transform) -test_data = FMDataset(test_df, data_transform) - -# 定义DataLoader类，以便在训练和测试时加载数据。 -# DataLoader类是pytorch自带的类，将数据集封装为可迭代的数据加载器 -train_loader = DataLoader(train_data, batch_size=batch_size, - shuffle=True, num_workers=num_workers, # shuffle=True：在每个epoch开始时对数据集进行随机重排 - drop_last=True) # 如果最后一个批次样本数不足将被丢弃 -test_loader = DataLoader(test_data, batch_size=batch_size, - shuffle=False, num_workers=num_workers) - -# 可视化操作，用于验证读入的数据是否正确 -import matplotlib.pyplot as plt - -image, label = next(iter(train_loader)) # iter()将train_loader转化为一个迭代器对象，next()用于获得下一个批次的数据 -print(image.shape, label.shape) -plt.imshow(image[0][0], cmap='gray') # matplotlib中用于显示图像的函数 -plt.show() - - -# 手搭CNN网络 -class Net(nn.Module): - def __init__(self): - super(Net, self).__init__() - self.conv = nn.Sequential( - nn.Conv2d(1, 32, 5), - nn.ReLU(), - nn.MaxPool2d(2, stride=2), - nn.Dropout(0.3), - nn.Conv2d(32, 64, 5), - nn.ReLU(), - nn.MaxPool2d(2, stride=2), - nn.Dropout(0.3) - ) - self.fc = nn.Sequential( - nn.Linear(64 * 4 * 4, 512), - nn.ReLU(), - nn.Linear(512, 10) - ) - - def forward(self, x): - x = self.conv(x) - x = x.view(-1, 64 * 4 * 4) - x = self.fc(x) - return x - - -model = Net() -model = model.cpu() - -# 设定损失函数 -# torch.nn模块自带交叉熵损失 -criterion = nn.CrossEntropyLoss() - -# 设定优化器 -optimizer = optim.Adam(model.parameters(), lr=0.001) - -# 训练和测试 -def train(epoch): - model.train() - train_loss = 0 - for data, label in train_loader: - data, label = data.cpu(), label.cpu() - optimizer.zero_grad() - output = model(data) - loss = criterion(output, label) - loss.backward() - optimizer.step() - train_loss += loss.item() * data.size(0) - train_loss = train_loss / len(train_loader.dataset) - print('Epoch: {}\tTraining Loss: {:.4f}'.format(epoch, train_loss)) - -def val(epoch): - model.eval() - val_loss = 0 - gt_labels = [] - pred_labels = [] - with torch.no_grad(): - for data, label in test_loader: - data, label = data.cpu(), label.cpu() - output = model(data) - preds = torch.argmax(output, 1) - gt_labels.append(preds.cpu().data.numpy()) - pred_labels.append(preds.cpu().data.numpy()) - loss = criterion(output, label) - val_loss += loss.item() * data.size(0) - val_loss = val_loss / len(test_loader.dataset) - gt_labels, pred_labels = np.concatenate(gt_labels), np.concatenate(pred_labels) - acc = np.sum(gt_labels == pred_labels) / len(pred_labels) - print('Epoch: {} \tValidation Loss: {:.4f}, Accuracy:{:.4f}'.format(epoch, val_loss, acc)) - - -for epoch in range(1, epochs + 1): - train(epoch) - val(epoch) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -