ss网站代码做商城网站需要多大的服务器

ss网站代码,做商城网站需要多大的服务器,建站seo怎么赚钱,365优化大师软件下载#x1f368; 本文为#x1f517;365天深度学习训练营中的学习记录博客#x1f356; 原作者#xff1a;K同学啊 一、前置知识 1、YOLOv5算法中的Backbone模块介绍 很高兴能和你一起探索 YOLOv5 的奥秘。YOLOv5 是一个非常经典且高效的目标检测算法#xff0c;而 Backbo…本文为365天深度学习训练营中的学习记录博客原作者K同学啊一、前置知识1、YOLOv5算法中的Backbone模块介绍很高兴能和你一起探索 YOLOv5 的奥秘。YOLOv5 是一个非常经典且高效的目标检测算法而Backbone主干网络是它最基础也最重要的部分。你可以把 Backbone 想象成读书笔记的“提炼者”读一本厚厚的书原始图片你不可能把每一个字都背下来。Backbone 就像是你大脑中负责提炼重点的机制。它在阅读过程中过滤掉了“的、地、得”这些无意义的连接词背景噪声只把书中的核心观点、关键数据、人物关系关键特征提取出来。最后你得到的一张薄薄的思维导图就是 Backbone 输出的成果——它比原书薄得多但包含了所有关键信息。二、代码实现1、设置GPU若设备支持GPU就使用GPU,否则使用CPUimport torch import torch.nn as nn import matplotlib.pyplot as plt import torchvision import warnings import torchvision.transforms as transforms from torchvision import transforms, datasets # 忽略来自 torch.cuda 的 pynvml 弃用警告 warnings.filterwarnings( ignore, messageThe pynvml package is deprecated.*, categoryFutureWarning, moduletorch.cuda ) device torch.device(cuda if torch.cuda.is_available() else cpu) devicedevice(typecuda)2、数据准备2.1、识别数据路径import os import pathlib # 查看当前工作路径确认路径是否正确 print(当前工作路径, os.getcwd()) # 定义数据目录建议用绝对路径更稳妥相对路径依赖当前工作路径 data_dir ./data/天气识别数据集/ data_dir pathlib.Path(data_dir) # 获取数据目录下的所有子路径文件夹或文件 data_paths list(data_dir.glob(*)) # 提取每个子路径的名称即类别名自动适配系统分隔符 classeNames [path.name for path in data_paths] classeNames当前工作路径 /root/365天训练营/Pytorch实战 [cloudy, rain, shine, sunrise]2.2、获取数据data_dir ./data/天气识别数据集/ # 关于transforms.Compose的更多介绍可以参考https://blog.csdn.net/qq_38251616/article/details/124878863 train_transforms transforms.Compose([ transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸 # transforms.RandomHorizontalFlip(), # 随机水平翻转 transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor并归一化到[0,1]之间 transforms.Normalize( # 标准化处理--转换为标准正太分布高斯分布使模型更容易收敛 mean[0.485, 0.456, 0.406], std[0.229, 0.224, 0.225]) # 其中 mean[0.485,0.456,0.406]与std[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。 ]) test_transform transforms.Compose([ transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸 transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor并归一化到[0,1]之间 transforms.Normalize( # 标准化处理--转换为标准正太分布高斯分布使模型更容易收敛 mean[0.485, 0.456, 0.406], std[0.229, 0.224, 0.225]) # 其中 mean[0.485,0.456,0.406]与std[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。 ]) total_data datasets.ImageFolder(data_dir, transformtrain_transforms) total_dataDataset ImageFolder Number of datapoints: 1125 Root location: ./data/天气识别数据集/ StandardTransform Transform: Compose( Resize(size[224, 224], interpolationbilinear, max_sizeNone, antialiaswarn) ToTensor() Normalize(mean[0.485, 0.456, 0.406], std[0.229, 0.224, 0.225]) )total_data.class_to_idx{cloudy: 0, rain: 1, shine: 2, sunrise: 3}2.3、划分数据集train_size int(0.8 * len(total_data)) test_size len(total_data) - train_size train_dataset, test_dataset torch.utils.data.random_split(total_data, [train_size, test_size]) train_dataset, test_dataset batch_size 4 train_dl torch.utils.data.DataLoader(train_dataset, batch_sizebatch_size, shuffleTrue, num_workers1) test_dl torch.utils.data.DataLoader(test_dataset, batch_sizebatch_size, shuffleTrue, num_workers1) for X, y in test_dl: print(Shape of X [N, C, H, W]: , X.shape) print(Shape of y: , y.shape, y.dtype) breakShape of X [N, C, H, W]: torch.Size([4, 3, 224, 224]) Shape of y: torch.Size([4]) torch.int643、模型搭建3.1、搭建Backbone模型import torch.nn.functional as F def autopad(k, pNone): # kernel, padding # Pad to same if p is None: p k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad return p class Conv(nn.Module): # Standard convolution def __init__(self, c1, c2, k1, s1, pNone, g1, actTrue): # ch_in, ch_out, kernel, stride, padding, groups super().__init__() self.conv nn.Conv2d(c1, c2, k, s, autopad(k, p), groupsg, biasFalse) self.bn nn.BatchNorm2d(c2) self.act nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity()) def forward(self, x): return self.act(self.bn(self.conv(x))) class Bottleneck(nn.Module): # Standard bottleneck def __init__(self, c1, c2, shortcutTrue, g1, e0.5): # ch_in, ch_out, shortcut, groups, expansion super().__init__() c_ int(c2 * e) # hidden channels self.cv1 Conv(c1, c_, 1, 1) self.cv2 Conv(c_, c2, 3, 1, gg) self.add shortcut and c1 c2 def forward(self, x): return x self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x)) class C3(nn.Module): # CSP Bottleneck with 3 convolutions def __init__(self, c1, c2, n1, shortcutTrue, g1, e0.5): # ch_in, ch_out, number, shortcut, groups, expansion super().__init__() c_ int(c2 * e) # hidden channels self.cv1 Conv(c1, c_, 1, 1) self.cv2 Conv(c1, c_, 1, 1) self.cv3 Conv(2 * c_, c2, 1) # actFReLU(c2) self.m nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e1.0) for _ in range(n))) def forward(self, x): return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim1)) class SPPF(nn.Module): # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher def __init__(self, c1, c2, k5): # equivalent to SPP(k(5, 9, 13)) super().__init__() c_ c1 // 2 # hidden channels self.cv1 Conv(c1, c_, 1, 1) self.cv2 Conv(c_ * 4, c2, 1, 1) self.m nn.MaxPool2d(kernel_sizek, stride1, paddingk // 2) def forward(self, x): x self.cv1(x) with warnings.catch_warnings(): warnings.simplefilter(ignore) # suppress torch 1.9.0 max_pool2d() warning y1 self.m(x) y2 self.m(y1) return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1)) 这个是YOLOv5, 6.0版本的主干网络这里进行复现 注有部分删改详细讲解将在后续进行展开 class YOLOv5_backbone(nn.Module): def __init__(self): super(YOLOv5_backbone, self).__init__() self.Conv_1 Conv(3, 64, 3, 2, 2) self.Conv_2 Conv(64, 128, 3, 2) self.C3_3 C3(128,128) self.Conv_4 Conv(128, 256, 3, 2) self.C3_5 C3(256,256) self.Conv_6 Conv(256, 512, 3, 2) self.C3_7 C3(512,512) self.Conv_8 Conv(512, 1024, 3, 2) self.C3_9 C3(1024, 1024) self.SPPF SPPF(1024, 1024, 5) # 全连接网络层用于分类 self.classifier nn.Sequential( nn.Linear(in_features65536, out_features100), nn.ReLU(), nn.Linear(in_features100, out_features4) ) def forward(self, x): x self.Conv_1(x) x self.Conv_2(x) x self.C3_3(x) x self.Conv_4(x) x self.C3_5(x) x self.Conv_6(x) x self.C3_7(x) x self.Conv_8(x) x self.C3_9(x) x self.SPPF(x) x torch.flatten(x, start_dim1) x self.classifier(x) return x device cuda if torch.cuda.is_available() else cpu print(Using {} device.format(device)) model YOLOv5_backbone().to(device) modelUsing cuda device YOLOv5_backbone( (Conv_1): Conv( (conv): Conv2d(3, 64, kernel_size(3, 3), stride(2, 2), padding(2, 2), biasFalse) (bn): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue) (act): SiLU() ) (Conv_2): Conv( (conv): Conv2d(64, 128, kernel_size(3, 3), stride(2, 2), padding(1, 1), biasFalse) (bn): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue) (act): SiLU() ) ...... (SPPF): SPPF( (cv1): Conv( (conv): Conv2d(1024, 512, kernel_size(1, 1), stride(1, 1), biasFalse) (bn): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue) (act): SiLU() ) (cv2): Conv( (conv): Conv2d(2048, 1024, kernel_size(1, 1), stride(1, 1), biasFalse) (bn): BatchNorm2d(1024, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue) (act): SiLU() ) (m): MaxPool2d(kernel_size5, stride1, padding2, dilation1, ceil_modeFalse) ) (classifier): Sequential( (0): Linear(in_features65536, out_features100, biasTrue) (1): ReLU() (2): Linear(in_features100, out_features4, biasTrue) ) )3.2、查看模型详情# 统计模型参数量以及其他指标 import torchsummary as summary summary.summary(model, (3, 224, 224))---------------------------------------------------------------- Layer (type) Output Shape Param # Conv2d-1 [-1, 64, 113, 113] 1,728 BatchNorm2d-2 [-1, 64, 113, 113] 128 SiLU-3 [-1, 64, 113, 113] 0 Conv-4 [-1, 64, 113, 113] 0 Conv2d-5 [-1, 128, 57, 57] 73,728 ...... Linear-121 [-1, 100] 6,553,700 ReLU-122 [-1, 100] 0 Linear-123 [-1, 4] 404 Total params: 21,729,592 Trainable params: 21,729,592 Non-trainable params: 0 ---------------------------------------------------------------- Input size (MB): 0.57 Forward/backward pass size (MB): 137.59 Params size (MB): 82.89 Estimated Total Size (MB): 221.06 ----------------------------------------------------------------4、训练模型4.1、训练函数# 训练循环 def train(dataloader, model, loss_fn, optimizer): size len(dataloader.dataset) # 训练集的大小 num_batches len(dataloader) # 批次数目, (size/batch_size向上取整) train_loss, train_acc 0, 0 # 初始化训练损失和正确率 for X, y in dataloader: # 获取图片及其标签 X, y X.to(device), y.to(device) # 计算预测误差 pred model(X) # 网络输出 loss loss_fn(pred, y) # 计算网络输出和真实值之间的差距targets为真实值计算二者差值即为损失 # 反向传播 optimizer.zero_grad() # grad属性归零 loss.backward() # 反向传播 optimizer.step() # 每一步自动更新 # 记录acc与loss train_acc (pred.argmax(1) y).type(torch.float).sum().item() train_loss loss.item() train_acc / size train_loss / num_batches return train_acc, train_loss4.2、测试函数def test (dataloader, model, loss_fn): size len(dataloader.dataset) # 测试集的大小 num_batches len(dataloader) # 批次数目, (size/batch_size向上取整) test_loss, test_acc 0, 0 # 当不进行训练时停止梯度更新节省计算内存消耗 with torch.no_grad(): for imgs, target in dataloader: imgs, target imgs.to(device), target.to(device) # 计算loss target_pred model(imgs) loss loss_fn(target_pred, target) test_loss loss.item() test_acc (target_pred.argmax(1) target).type(torch.float).sum().item() test_acc / size test_loss / num_batches return test_acc, test_loss4.3、正式训练import copy optimizer torch.optim.Adam(model.parameters(), lr 1e-4) loss_fn nn.CrossEntropyLoss() # 创建损失函数 epochs 60 train_loss [] train_acc [] test_loss [] test_acc [] best_acc 0 # 设置一个最佳准确率作为最佳模型的判别指标 for epoch in range(epochs): model.train() epoch_train_acc, epoch_train_loss train(train_dl, model, loss_fn, optimizer) model.eval() epoch_test_acc, epoch_test_loss test(test_dl, model, loss_fn) # 保存最佳模型到 best_model if epoch_test_acc best_acc: best_acc epoch_test_acc best_model copy.deepcopy(model) train_acc.append(epoch_train_acc) train_loss.append(epoch_train_loss) test_acc.append(epoch_test_acc) test_loss.append(epoch_test_loss) # 获取当前的学习率 lr optimizer.state_dict()[param_groups][0][lr] template (Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}) print(template.format(epoch1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss, lr)) # 保存最佳模型到文件中 PATH ./model/p9_best_model.pth # 保存的参数文件名 torch.save(best_model.state_dict(), PATH) print(Done)Epoch: 1, Train_acc:57.4%, Train_loss:1.130, Test_acc:64.9%, Test_loss:0.745, Lr:1.00E-04 Epoch: 2, Train_acc:65.9%, Train_loss:0.850, Test_acc:73.8%, Test_loss:0.663, Lr:1.00E-04 Epoch: 3, Train_acc:74.6%, Train_loss:0.672, Test_acc:83.1%, Test_loss:0.430, Lr:1.00E-04 Epoch: 4, Train_acc:75.9%, Train_loss:0.618, Test_acc:84.9%, Test_loss:0.386, Lr:1.00E-04 Epoch: 5, Train_acc:83.4%, Train_loss:0.445, Test_acc:82.2%, Test_loss:0.492, Lr:1.00E-04 ...... Epoch:56, Train_acc:96.7%, Train_loss:0.101, Test_acc:88.4%, Test_loss:0.578, Lr:1.00E-04 Epoch:57, Train_acc:97.1%, Train_loss:0.080, Test_acc:89.8%, Test_loss:0.468, Lr:1.00E-04 Epoch:58, Train_acc:98.4%, Train_loss:0.052, Test_acc:91.1%, Test_loss:0.450, Lr:1.00E-04 Epoch:59, Train_acc:99.1%, Train_loss:0.032, Test_acc:91.1%, Test_loss:0.513, Lr:1.00E-04 Epoch:60, Train_acc:99.4%, Train_loss:0.023, Test_acc:89.8%, Test_loss:0.563, Lr:1.00E-04 Done5、结果可视化5.1、Loss与Accuracy图import matplotlib.pyplot as plt #隐藏警告 import warnings warnings.filterwarnings(ignore) #忽略警告信息 plt.rcParams[font.sans-serif] [SimHei] # 用来正常显示中文标签 plt.rcParams[axes.unicode_minus] False # 用来正常显示负号 plt.rcParams[figure.dpi] 100 #分辨率 from datetime import datetime current_time datetime.now() # 获取当前时间 epochs_range range(epochs) plt.figure(figsize(12, 3)) plt.subplot(1, 2, 1) plt.plot(epochs_range, train_acc, labelTraining Accuracy) plt.plot(epochs_range, test_acc, labelTest Accuracy) plt.legend(loclower right) plt.title(Training and Validation Accuracy) plt.xlabel(current_time) # 打卡请带上时间戳否则代码截图无效 plt.subplot(1, 2, 2) plt.plot(epochs_range, train_loss, labelTraining Loss) plt.plot(epochs_range, test_loss, labelTest Loss) plt.legend(locupper right) plt.title(Training and Validation Loss) plt.show()6、模型评估best_model.load_state_dict(torch.load(PATH, map_locationdevice)) epoch_test_acc, epoch_test_loss test(test_dl, best_model, loss_fn) epoch_test_acc, epoch_test_loss(0.9377777777777778, 0.3814523629184725)