电子商务网站建设评估工具有哪些/优化推广网站怎么做

30Kaggle竞赛：图片分类

比赛链接： https://www.kaggle.com/c/classify-leaves

导入包

import torch
import torchvision
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms
import numpy as np
import pandas as pd
from torch import nn
import matplotlib.pyplot as plt
from PIL import Image
import os
from torch.nn import functional as F
import torch.optim as optim
import liliPytorch as lp
import torchvision.models as models

预处理：数据集分析

train_path = '../data/classify-leaves/train.csv'
test_path = '../data/classify-leaves/test.csv'
file_path = '../data/classify-leaves/'# # 读取训练和测试数据
train_data = pd.read_csv(train_path)
test_data = pd.read_csv(test_path)# 打印数据形状
print(train_data.shape) # (18353, 2)
print(test_data.shape) # (8800, 1)#生成描述性统计数据
print(train_data.describe())
"""image             label
count          18353             18353
unique         18353               176
top     images/0.jpg  maclura_pomifera
freq               1               353
"""# 查看不同树叶的数量
print(train_data['label'].value_counts())
"""
label
maclura_pomifera            353
ulmus_rubra                 235
prunus_virginiana           223
acer_rubrum                 217
broussonettia_papyrifera    214... 
cedrus_deodara               58
ailanthus_altissima          58
crataegus_crus-galli         54
evodia_daniellii             53
juniperus_virginiana         51
Name: count, Length: 176, dtype: int64
"""

1.数据处理与加载

train_path = '../data/classify-leaves/train.csv'
test_path = '../data/classify-leaves/test.csv'
file_path = '../data/classify-leaves/'# 树叶的名字统计
labels_unique = train_data['label'].unique()
# print(labels_unique)# 树叶标签的数量
labels_num = len(labels_unique)# 提取出树叶标签，并排序
leaves_labels = sorted(list(set(train_data['label'])))
# print(leaves_labels)# 将树叶标签对应数字
labels_to_num = dict(zip(leaves_labels, range(labels_num )))
# print(labels_to_num)# 将数字对应树叶标签(用于后续预测)
num_to_labels = {value : key for key, value in labels_to_num.items()}
# print(num_to_labels)class LeavesDataset(Dataset):def __init__(self, csv_path, file_path, mode='train', valid_ratio=0.2, resize_height=224, resize_width=224):"""初始化 LeavesDataset 对象。参数:csv_path (str): 包含图像路径和标签的 CSV 文件路径。file_path (str): 图像文件所在目录的路径。mode (str, optional): 数据集的模式。可以是 'train', 'valid' 或 'test'。默认值为 'train'。valid_ratio (float, optional): 用于验证的数据比例。默认值为 0.2。resize_height (int, optional): 调整图像高度的大小。默认值为 224。resize_width (int, optional): 调整图像宽度的大小。默认值为 224。"""# 存储图像调整大小的高度和宽度self.resize_height = resize_heightself.resize_width = resize_width# 存储图像文件路径和模式（train/valid/test）self.file_path = file_pathself.mode = mode# 读取包含图像路径和标签的 CSV 文件self.data_info = pd.read_csv(csv_path, header=0)# 获取样本总数self.data_len = len(self.data_info.index)# 计算训练集样本数self.train_len = int(self.data_len * (1 - valid_ratio))# 根据模式处理数据if self.mode == 'train':# 训练模式下的图像和标签self.train_img = np.asarray(self.data_info.iloc[0:self.train_len, 0])self.train_label = np.asarray(self.data_info.iloc[0:self.train_len, 1])self.image_arr = self.train_imgself.label_arr = self.train_labelelif self.mode == 'valid':# 验证模式下的图像和标签self.valid_img = np.asarray(self.data_info.iloc[self.train_len:, 0])self.valid_label = np.asarray(self.data_info.iloc[self.train_len:, 1])self.image_arr = self.valid_imgself.label_arr = self.valid_labelelif self.mode == 'test':# 测试模式下的图像self.test_img = np.asarray(self.data_info.iloc[:, 0])self.image_arr = self.test_img# 获取图像数组的长度self.len_image = len(self.image_arr)print(f'扫描所有 {mode} 数据，共 {self.len_image} 张图像')def __getitem__(self, idx):"""获取指定索引的图像和标签。参数: idx (int): 标签文本对应编号的索引返回:如果是测试模式，返回图像张量；否则返回图像张量和标签。"""# 打开图像文件self.img = Image.open(self.file_path + self.image_arr[idx])if self.mode == 'train':# 训练模式下的数据增强trans = transforms.Compose([transforms.Resize((self.resize_height, self.resize_width)),transforms.RandomHorizontalFlip(p=0.5),transforms.RandomVerticalFlip(p=0.5),transforms.RandomRotation(degrees=30),# transforms.ColorJitter(brightness=0.2, contrast=0.2, saturation=0.2, hue=0.1),# transforms.RandomResizedCrop(size=self.resize_height, scale=(0.8, 1.0)),transforms.ToTensor(),# transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])self.img = trans(self.img)else:# 验证和测试模式下的简单处理trans = transforms.Compose([transforms.Resize((self.resize_height, self.resize_width)),transforms.ToTensor(),# transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])self.img = trans(self.img)if self.mode == 'test':return self.imgelse:# 获取标签文本对应的编号self.label = labels_to_num[self.label_arr[idx]]return self.img, self.labeldef __call__(self, idx):"""使对象可以像函数一样被调用。参数:idx (int):标签文本对应编号的索引 返回: 调用 __getitem__ 方法并返回结果。"""return self.__getitem__(idx)def __len__(self):"""获取数据集的长度。返回: 数据集中图像的数量。"""return self.len_imagetrain_dataset = LeavesDataset(train_path, file_path)
valid_dataset = LeavesDataset(train_path, file_path, mode='valid')
test_dataset = LeavesDataset(test_path, file_path, mode='test')

2.模型构建Resnet

class Residual(nn.Module):def __init__(self, input_channels, num_channels, use_1x1conv=False, strides=1):super().__init__()self.conv1 = nn.Conv2d(input_channels, num_channels, kernel_size=3, padding=1, stride=strides)self.conv2 = nn.Conv2d(num_channels, num_channels, kernel_size=3, padding=1)if use_1x1conv:self.conv3 = nn.Conv2d(input_channels, num_channels, kernel_size=1, stride=strides)else:self.conv3 = Noneself.bn1 = nn.BatchNorm2d(num_channels)self.bn2 = nn.BatchNorm2d(num_channels)def forward(self, X):Y = F.relu(self.bn1(self.conv1(X)))Y = self.bn2(self.conv2(Y))if self.conv3:X = self.conv3(X)Y += Xreturn F.relu(Y)b1 = nn.Sequential(nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3),nn.BatchNorm2d(64),nn.ReLU(),nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
)def resnet_block(input_channels, num_channels, num_residuals, first_block=False):blk = []for i in range(num_residuals):if i == 0 and not first_block:blk.append(Residual(input_channels, num_channels, use_1x1conv=True, strides=2))else:blk.append(Residual(num_channels, num_channels))return blk#ResNet34
# b2 = nn.Sequential(*resnet_block(64, 64, 3, first_block=True))
# b3 = nn.Sequential(*resnet_block(64, 128, 4))
# b4 = nn.Sequential(*resnet_block(128, 256, 6))
# b5 = nn.Sequential(*resnet_block(256, 512, 3))#ResNet18
b2 = nn.Sequential(*resnet_block(64, 64, 2, first_block=True))
b3 = nn.Sequential(*resnet_block(64, 128, 2))
b4 = nn.Sequential(*resnet_block(128, 256, 2))
b5 = nn.Sequential(*resnet_block(256, 512, 2))net = nn.Sequential(b1, b2, b3, b4, b5,nn.AdaptiveAvgPool2d((1, 1)),nn.Flatten(),nn.Linear(512, labels_num)
)

3.模型训练

def train_ch6(net, train_iter, test_iter, num_epochs, lr, device):"""用GPU训练模型参数:net (torch.nn.Module): 要训练的神经网络模型train_iter (torch.utils.data.DataLoader): 训练数据加载器test_iter (torch.utils.data.DataLoader): 测试数据加载器num_epochs (int): 训练的轮数lr (float): 学习率device (torch.device): 计算设备（CPU或GPU）"""# 初始化模型权重def init_weights(m):if(type(m) == nn.Linear or type(m) == nn.Conv2d):nn.init.xavier_uniform_(m.weight)net.apply(init_weights)print('training on', device)net.to(device)# 应用初始化权重函数# optimizer = torch.optim.SGD(net.parameters(), lr = lr)optimizer = torch.optim.Adam(net.parameters(), lr=lr, weight_decay = 0.001)# 每5个epoch学习率减少到原来的0.1倍# scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=10, gamma=0.1)  loss = nn.CrossEntropyLoss()   # 损失函数，使用交叉熵损失animator = lp.Animator(xlabel='epoch', xlim=[1, num_epochs],legend=['train loss', 'train acc', 'test acc'])timer, num_batches = lp.Timer(), len(train_iter)for epoch in range(num_epochs):# 训练损失之和，训练准确率之和，样本数metric = lp.Accumulator(3)net.train() #训练模式for i, (X, y) in enumerate(train_iter):timer.start()optimizer.zero_grad() # 梯度清零X, y = X.to(device), y.to(device)y_hat = net(X)# 前向传播l = loss(y_hat, y) # 计算损失l.backward()# 反向传播optimizer.step() # 更新参数with torch.no_grad():metric.add(l * X.shape[0], lp.accuracy(y_hat, y), X.shape[0]) # 更新指标timer.stop()train_l = metric[0] / metric[2] # 计算训练损失train_acc = metric[1] / metric[2] # 计算训练准确率# 每训练完一个批次或每5个批次更新动画if (i + 1) % (num_batches // 5) == 0 or i == num_batches - 1:animator.add(epoch + (i + 1) / num_batches,(train_l, train_acc, None))# 在验证集上计算准确率test_acc = lp.evaluate_accuracy_gpu(net, test_iter, device)animator.add(epoch + 1, (None, None, test_acc))# 打印当前epoch的训练损失，训练准确率和测试准确率print(f'loss {train_l:.3f}, train acc {train_acc:.3f}, 'f'test acc {test_acc:.3f}')# scheduler.step()animator.show()print(f'loss {train_l:.3f}, train acc {train_acc:.3f}, 'f'test acc {test_acc:.3f}')print(f'{metric[2] * num_epochs / timer.sum():.1f} examples/sec 'f'on {str(device)}')# 打印每秒处理的样本数# 超参数设置
lr, num_epochs, batch_size = 1e-5, 120, 128# 数据加载器
train_iter = DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=4)
valid_iter = DataLoader(valid_dataset, batch_size=batch_size, shuffle=False, num_workers=4)train_ch6(net, train_iter, valid_iter, num_epochs, lr, lp.try_gpu())
plt.show()# 保存模型参数
file_path_module = '../limuPytorch/module/'
torch.save(net.state_dict(), file_path_module + 'classify_leaves.params')

4.训练调参

resNet-18,num_epochs = 10,lr=1e-4,
loss 2.239, train acc 0.429, test acc 0.149
444.5 examples/sec on cuda:0resNet-34, num_epochs = 10,lr=1e-4
loss 1.991, train acc 0.443, test acc 0.147
270.7 examples/sec on cuda:0resNet-34,num_epochs = 50,lr=1e-4,train数据增强，使用Adam
loss 0.281, train acc 0.914, test acc 0.378
244.6 examples/sec on cuda:0resNet-34,num_epochs = 50,lr=1e-5,train数据增强，使用Adam
loss 0.189, train acc 0.925, test acc 0.398
258.0 examples/sec on cuda:0resNet-18,num_epochs = 50,lr=1e-4,train数据增强，使用Adam
loss 0.199, train acc 0.955, test acc 0.338
458.0 examples/sec on cuda:0resNet-18,num_epochs = 50,lr=1e-4,train数据增强,调整数据集比例8：2
数据增强过度导致测试准确率（test accuracy）曲线上下震荡resNet-18,num_epochs = 50,lr=1e-4,train数据增强,调整数据集比例为8：2
数据增强过度导致测试准确率（test accuracy）曲线上下震荡resNet-18,num_epochs = 50,lr=1e-4,train数据增强（仅旋转）,调整数据集比例为8：2
loss 0.129, train acc 0.966, test acc 0.838
350.7 examples/sec on cuda:0resNet-18,num_epochs = 50,lr=1e-5,train数据增强,调整数据集比例为8：2
loss 0.808, train acc 0.788, test acc 0.701
420.6 examples/sec on cuda:0resNet-18,num_epochs = 100,lr=1e-5,train数据增强,调整数据集比例为8：2
loss 0.285, train acc 0.927, test acc 0.825
409.2 examples/sec on cuda:0

5.模型预测

 def predict(model, data_loader, device):"""使用模型进行预测参数:model (torch.nn.Module): 要进行预测的模型data_loader (torch.utils.data.DataLoader): 数据加载器，用于提供待预测的数据device (torch.device): 计算设备（CPU或GPU）返回: all_preds (list): 包含所有预测结果的列表"""all_preds = []  # 存储所有预测结果model.to(device)  # 将模型移动到指定设备model.eval()  # 设置模型为评估模式with torch.no_grad():  # 在不需要计算梯度的上下文中进行for X in data_loader:  # 遍历数据加载器X = X.to(device)  # 将数据移动到指定设备outputs = model(X)  # 前向传播，计算模型输出_, preds = torch.max(outputs, 1)  # 获取预测结果all_preds.extend(preds.cpu().numpy())  # 将预测结果添加到列表中return all_preds  # 返回所有预测结果# 克隆模型clone_net = net# 加载预训练模型参数clone_net.load_state_dict(torch.load(file_path_module + 'classify_leaves.params'))# 创建验证集的数据加载器valid_iter = DataLoader(test_dataset, batch_size=batch_size, shuffle=False, num_workers=2)# 进行预测predictions = predict(clone_net, valid_iter, lp.try_gpu())# 将预测结果映射到标签for i in predictions:predictions.append(num_to_labels[int(i)])# 读取测试数据test_data = pd.read_csv(test_path)# 将预测结果添加到测试数据中test_data['label'] = pd.Series(predictions)# 创建提交文件submission = pd.concat([test_data['image'], test_data['label']], axis=2)# 保存提交文件submission.to_csv(file_path + 'submission.csv', index=False)

7.扩展学习

# 模型构建
# 加载预训练的ResNet-18模型
#加载一个预训练的ResNet-18模型，这个模型已经在ImageNet数据集上进行了预训练。
#可以利用其提取特征的能力。
pretrained_net = models.resnet18(pretrained=True)# 克隆预训练的ResNet-18模型，用于分类叶子数据集
classify_leaves_net = pretrained_net# 修改最后的全连接层，将其输出特征数改为176（有176个类别）
# classify_leaves_net.fc.in_features 获取原始全连接层的输入特征数。
classify_leaves_net.fc = nn.Linear(classify_leaves_net.fc.in_features, 176)# 使用Xavier均匀分布初始化新的全连接层的权重
nn.init.xavier_uniform_(classify_leaves_net.fc.weight)# 模型训练部分更改优化器
def train_ch6(net, train_iter, test_iter, num_epochs, lr, device,param_group=True):"""param_group (bool, optional): 是否对参数进行分组设置不同的学习率。默认值为True"""# optimizer = torch.optim.SGD(net.parameters(), lr = lr)# optimizer = torch.optim.Adam(net.parameters(), lr=lr, weight_decay = 0.001)if param_group:# 如果参数分组设置为True，分离出最后一层全连接层的参数# 列表params_1x，包含除最后一层全连接层外的所有参数。params_1x = [param for name, param in net.named_parameters()if name not in ["fc.weight", "fc.bias"]]optimizer = torch.optim.Adam([{'params': params_1x},  # 其他层的参数使用默认学习率{'params': net.fc.parameters(), 'lr': lr * 10}  # 全连接层的参数使用更高的学习率], lr=lr, weight_decay=0.001)else:# 如果参数分组设置为False，所有参数使用相同的学习率optimizer = torch.optim.Adam(net.parameters(), lr=lr, weight_decay=0.001)