第P9周：YOLOv5-Backbone模块实现

一、 前期准备

1. 设置GPU

我的是笔记本电脑，没有GPU

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,warningswarnings.filterwarnings("ignore")             #忽略警告信息device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
cpu

2. 导入数据(数据使用的仍然是天气图片)

import os,PIL,random,pathlibdata_dir = './9-data/'
data_dir = pathlib.Path(data_dir)data_paths  = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[1] for path in data_paths]
classeNames
['cloudy', 'rain', 'shine', 'sunrise']

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("./9-data/",transform=train_transforms)
print(total_data)
Dataset ImageFolderNumber of datapoints: 1125Root location: ./9-data/StandardTransform
Transform: Compose(Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=warn)ToTensor()Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]))
print(total_data.class_to_idx)
{'cloudy': 0, 'rain': 1, 'shine': 2, 'sunrise': 3}

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
(<torch.utils.data.dataset.Subset at 0x2bbb0779330>,<torch.utils.data.dataset.Subset at 0x2bbb0779e10>)
batch_size = 4train_dl = torch.utils.data.DataLoader(train_dataset,batch_size=batch_size,shuffle=True,num_workers=0)
test_dl = torch.utils.data.DataLoader(test_dataset,batch_size=batch_size,shuffle=True,num_workers=0)//这里我在主线程跑，否则一直报错
for X, y in test_dl:print("Shape of X [N, C, H, W]: ", X.shape)print("Shape of y: ", y.shape, y.dtype)break
Shape of X [N, C, H, W]:  torch.Size([4, 3, 224, 224])
Shape of y:  torch.Size([4]) torch.int64

二、搭建包含Backbone模块的模型

1. 搭建模型

import torch.nn.functional as Fdef autopad(k, p=None):  # kernel, padding# Pad to 'same'if p is None:p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-padreturn pclass Conv(nn.Module):# Standard convolutiondef __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groupssuper().__init__()self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)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 bottleneckdef __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansionsuper().__init__()c_ = int(c2 * e)  # hidden channelsself.cv1 = Conv(c1, c_, 1, 1)self.cv2 = Conv(c_, c2, 3, 1, g=g)self.add = shortcut and c1 == c2def 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 convolutionsdef __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansionsuper().__init__()c_ = int(c2 * e)  # hidden channelsself.cv1 = Conv(c1, c_, 1, 1)self.cv2 = Conv(c1, c_, 1, 1)self.cv3 = Conv(2 * c_, c2, 1)  # act=FReLU(c2)self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))def forward(self, x):return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))class SPPF(nn.Module):# Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocherdef __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))super().__init__()c_ = c1 // 2  # hidden channelsself.cv1 = Conv(c1, c_, 1, 1)self.cv2 = Conv(c_ * 4, c2, 1, 1)self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)def forward(self, x):x = self.cv1(x)with warnings.catch_warnings():warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warningy1 = 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_features=65536, out_features=100),nn.ReLU(),nn.Linear(in_features=100, out_features=4))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_dim=1)x = self.classifier(x)return xdevice = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))model = YOLOv5_backbone().to(device)
model
Using cuda deviceYOLOv5_backbone((Conv_1): Conv((conv): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(2, 2), bias=False)(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(Conv_2): Conv((conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(C3_3): C3((cv1): Conv((conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(cv2): Conv((conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(cv3): Conv((conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(m): Sequential((0): Bottleneck((cv1): Conv((conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(cv2): Conv((conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU()))))(Conv_4): Conv((conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(C3_5): C3((cv1): Conv((conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(cv2): Conv((conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(cv3): Conv((conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(m): Sequential((0): Bottleneck((cv1): Conv((conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(cv2): Conv((conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU()))))(Conv_6): Conv((conv): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(C3_7): C3((cv1): Conv((conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(cv2): Conv((conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(cv3): Conv((conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(m): Sequential((0): Bottleneck((cv1): Conv((conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(cv2): Conv((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU()))))(Conv_8): Conv((conv): Conv2d(512, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)(bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(C3_9): C3((cv1): Conv((conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(cv2): Conv((conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(cv3): Conv((conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(m): Sequential((0): Bottleneck((cv1): Conv((conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(cv2): Conv((conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU()))))(SPPF): SPPF((cv1): Conv((conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(cv2): Conv((conv): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(act): SiLU())(m): MaxPool2d(kernel_size=5, stride=1, padding=2, dilation=1, ceil_mode=False))(classifier): Sequential((0): Linear(in_features=65536, out_features=100, bias=True)(1): ReLU()(2): Linear(in_features=100, out_features=4, bias=True))
)

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]           1,728BatchNorm2d-2         [-1, 64, 113, 113]             128SiLU-3         [-1, 64, 113, 113]               0Conv-4         [-1, 64, 113, 113]               0Conv2d-5          [-1, 128, 57, 57]          73,728BatchNorm2d-6          [-1, 128, 57, 57]             256SiLU-7          [-1, 128, 57, 57]               0Conv-8          [-1, 128, 57, 57]               0Conv2d-9           [-1, 64, 57, 57]           8,192BatchNorm2d-10           [-1, 64, 57, 57]             128SiLU-11           [-1, 64, 57, 57]               0Conv-12           [-1, 64, 57, 57]               0Conv2d-13           [-1, 64, 57, 57]           4,096BatchNorm2d-14           [-1, 64, 57, 57]             128SiLU-15           [-1, 64, 57, 57]               0Conv-16           [-1, 64, 57, 57]               0Conv2d-17           [-1, 64, 57, 57]          36,864BatchNorm2d-18           [-1, 64, 57, 57]             128SiLU-19           [-1, 64, 57, 57]               0Conv-20           [-1, 64, 57, 57]               0Bottleneck-21           [-1, 64, 57, 57]               0Conv2d-22           [-1, 64, 57, 57]           8,192BatchNorm2d-23           [-1, 64, 57, 57]             128SiLU-24           [-1, 64, 57, 57]               0Conv-25           [-1, 64, 57, 57]               0Conv2d-26          [-1, 128, 57, 57]          16,384BatchNorm2d-27          [-1, 128, 57, 57]             256SiLU-28          [-1, 128, 57, 57]               0Conv-29          [-1, 128, 57, 57]               0C3-30          [-1, 128, 57, 57]               0Conv2d-31          [-1, 256, 29, 29]         294,912BatchNorm2d-32          [-1, 256, 29, 29]             512SiLU-33          [-1, 256, 29, 29]               0Conv-34          [-1, 256, 29, 29]               0Conv2d-35          [-1, 128, 29, 29]          32,768BatchNorm2d-36          [-1, 128, 29, 29]             256SiLU-37          [-1, 128, 29, 29]               0Conv-38          [-1, 128, 29, 29]               0Conv2d-39          [-1, 128, 29, 29]          16,384BatchNorm2d-40          [-1, 128, 29, 29]             256SiLU-41          [-1, 128, 29, 29]               0Conv-42          [-1, 128, 29, 29]               0Conv2d-43          [-1, 128, 29, 29]         147,456BatchNorm2d-44          [-1, 128, 29, 29]             256SiLU-45          [-1, 128, 29, 29]               0Conv-46          [-1, 128, 29, 29]               0Bottleneck-47          [-1, 128, 29, 29]               0Conv2d-48          [-1, 128, 29, 29]          32,768BatchNorm2d-49          [-1, 128, 29, 29]             256SiLU-50          [-1, 128, 29, 29]               0Conv-51          [-1, 128, 29, 29]               0Conv2d-52          [-1, 256, 29, 29]          65,536BatchNorm2d-53          [-1, 256, 29, 29]             512SiLU-54          [-1, 256, 29, 29]               0Conv-55          [-1, 256, 29, 29]               0C3-56          [-1, 256, 29, 29]               0Conv2d-57          [-1, 512, 15, 15]       1,179,648BatchNorm2d-58          [-1, 512, 15, 15]           1,024SiLU-59          [-1, 512, 15, 15]               0Conv-60          [-1, 512, 15, 15]               0Conv2d-61          [-1, 256, 15, 15]         131,072BatchNorm2d-62          [-1, 256, 15, 15]             512SiLU-63          [-1, 256, 15, 15]               0Conv-64          [-1, 256, 15, 15]               0Conv2d-65          [-1, 256, 15, 15]          65,536BatchNorm2d-66          [-1, 256, 15, 15]             512SiLU-67          [-1, 256, 15, 15]               0Conv-68          [-1, 256, 15, 15]               0Conv2d-69          [-1, 256, 15, 15]         589,824BatchNorm2d-70          [-1, 256, 15, 15]             512SiLU-71          [-1, 256, 15, 15]               0Conv-72          [-1, 256, 15, 15]               0Bottleneck-73          [-1, 256, 15, 15]               0Conv2d-74          [-1, 256, 15, 15]         131,072BatchNorm2d-75          [-1, 256, 15, 15]             512SiLU-76          [-1, 256, 15, 15]               0Conv-77          [-1, 256, 15, 15]               0Conv2d-78          [-1, 512, 15, 15]         262,144BatchNorm2d-79          [-1, 512, 15, 15]           1,024SiLU-80          [-1, 512, 15, 15]               0Conv-81          [-1, 512, 15, 15]               0C3-82          [-1, 512, 15, 15]               0Conv2d-83           [-1, 1024, 8, 8]       4,718,592BatchNorm2d-84           [-1, 1024, 8, 8]           2,048SiLU-85           [-1, 1024, 8, 8]               0Conv-86           [-1, 1024, 8, 8]               0Conv2d-87            [-1, 512, 8, 8]         524,288BatchNorm2d-88            [-1, 512, 8, 8]           1,024SiLU-89            [-1, 512, 8, 8]               0Conv-90            [-1, 512, 8, 8]               0Conv2d-91            [-1, 512, 8, 8]         262,144BatchNorm2d-92            [-1, 512, 8, 8]           1,024SiLU-93            [-1, 512, 8, 8]               0Conv-94            [-1, 512, 8, 8]               0Conv2d-95            [-1, 512, 8, 8]       2,359,296BatchNorm2d-96            [-1, 512, 8, 8]           1,024SiLU-97            [-1, 512, 8, 8]               0Conv-98            [-1, 512, 8, 8]               0Bottleneck-99            [-1, 512, 8, 8]               0Conv2d-100            [-1, 512, 8, 8]         524,288BatchNorm2d-101            [-1, 512, 8, 8]           1,024SiLU-102            [-1, 512, 8, 8]               0Conv-103            [-1, 512, 8, 8]               0Conv2d-104           [-1, 1024, 8, 8]       1,048,576BatchNorm2d-105           [-1, 1024, 8, 8]           2,048SiLU-106           [-1, 1024, 8, 8]               0Conv-107           [-1, 1024, 8, 8]               0C3-108           [-1, 1024, 8, 8]               0Conv2d-109            [-1, 512, 8, 8]         524,288BatchNorm2d-110            [-1, 512, 8, 8]           1,024SiLU-111            [-1, 512, 8, 8]               0Conv-112            [-1, 512, 8, 8]               0MaxPool2d-113            [-1, 512, 8, 8]               0MaxPool2d-114            [-1, 512, 8, 8]               0MaxPool2d-115            [-1, 512, 8, 8]               0Conv2d-116           [-1, 1024, 8, 8]       2,097,152BatchNorm2d-117           [-1, 1024, 8, 8]           2,048SiLU-118           [-1, 1024, 8, 8]               0Conv-119           [-1, 1024, 8, 8]               0SPPF-120           [-1, 1024, 8, 8]               0Linear-121                  [-1, 100]       6,553,700ReLU-122                  [-1, 100]               0Linear-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
----------------------------------------------------------------

三、 训练模型

1. 编写训练函数

# 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losstrain_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss += loss.item()train_acc  /= sizetrain_loss /= num_batchesreturn train_acc, train_loss

2. 编写测试函数

测试函数和训练函数大致相同，但是由于不进行梯度下降对网络权重进行更新，所以不需要传入优化器

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losstarget_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  /= sizetest_loss /= num_batchesreturn test_acc, test_loss

3. 正式训练

import copyoptimizer  = torch.optim.Adam(model.parameters(), lr= 1e-4)
loss_fn    = nn.CrossEntropyLoss() # 创建损失函数epochs     = 60train_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_modelif epoch_test_acc > best_acc:best_acc   = epoch_test_accbest_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(epoch+1, 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 = './best_model.pth'  # 保存的参数文件名
torch.save(best_model.state_dict(), PATH)print('Done')

D:\Code\pythonProject_PyTorch\venv\Scripts\python.exe D:\Code\pythonProject_PyTorch\YOLOv5-Backbone.py 
cpu
['cloudy', 'rain', 'shine', 'sunrise']
Dataset ImageFolderNumber of datapoints: 1125Root location: ./9-data/StandardTransform
Transform: Compose(Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=warn)ToTensor()Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]))
{'cloudy': 0, 'rain': 1, 'shine': 2, 'sunrise': 3}
Shape of X [N, C, H, W]:  torch.Size([4, 3, 224, 224])
Shape of y:  torch.Size([4]) torch.int64
Using cpu device
----------------------------------------------------------------Layer (type)               Output Shape         Param #
================================================================Conv2d-1         [-1, 64, 113, 113]           1,728BatchNorm2d-2         [-1, 64, 113, 113]             128SiLU-3         [-1, 64, 113, 113]               0Conv-4         [-1, 64, 113, 113]               0Conv2d-5          [-1, 128, 57, 57]          73,728BatchNorm2d-6          [-1, 128, 57, 57]             256SiLU-7          [-1, 128, 57, 57]               0Conv-8          [-1, 128, 57, 57]               0Conv2d-9           [-1, 64, 57, 57]           8,192BatchNorm2d-10           [-1, 64, 57, 57]             128SiLU-11           [-1, 64, 57, 57]               0Conv-12           [-1, 64, 57, 57]               0Conv2d-13           [-1, 64, 57, 57]           4,096BatchNorm2d-14           [-1, 64, 57, 57]             128SiLU-15           [-1, 64, 57, 57]               0Conv-16           [-1, 64, 57, 57]               0Conv2d-17           [-1, 64, 57, 57]          36,864BatchNorm2d-18           [-1, 64, 57, 57]             128SiLU-19           [-1, 64, 57, 57]               0Conv-20           [-1, 64, 57, 57]               0Bottleneck-21           [-1, 64, 57, 57]               0Conv2d-22           [-1, 64, 57, 57]           8,192BatchNorm2d-23           [-1, 64, 57, 57]             128SiLU-24           [-1, 64, 57, 57]               0Conv-25           [-1, 64, 57, 57]               0Conv2d-26          [-1, 128, 57, 57]          16,384BatchNorm2d-27          [-1, 128, 57, 57]             256SiLU-28          [-1, 128, 57, 57]               0Conv-29          [-1, 128, 57, 57]               0C3-30          [-1, 128, 57, 57]               0Conv2d-31          [-1, 256, 29, 29]         294,912BatchNorm2d-32          [-1, 256, 29, 29]             512SiLU-33          [-1, 256, 29, 29]               0Conv-34          [-1, 256, 29, 29]               0Conv2d-35          [-1, 128, 29, 29]          32,768BatchNorm2d-36          [-1, 128, 29, 29]             256SiLU-37          [-1, 128, 29, 29]               0Conv-38          [-1, 128, 29, 29]               0Conv2d-39          [-1, 128, 29, 29]          16,384BatchNorm2d-40          [-1, 128, 29, 29]             256SiLU-41          [-1, 128, 29, 29]               0Conv-42          [-1, 128, 29, 29]               0Conv2d-43          [-1, 128, 29, 29]         147,456BatchNorm2d-44          [-1, 128, 29, 29]             256SiLU-45          [-1, 128, 29, 29]               0Conv-46          [-1, 128, 29, 29]               0Bottleneck-47          [-1, 128, 29, 29]               0Conv2d-48          [-1, 128, 29, 29]          32,768BatchNorm2d-49          [-1, 128, 29, 29]             256SiLU-50          [-1, 128, 29, 29]               0Conv-51          [-1, 128, 29, 29]               0Conv2d-52          [-1, 256, 29, 29]          65,536BatchNorm2d-53          [-1, 256, 29, 29]             512SiLU-54          [-1, 256, 29, 29]               0Conv-55          [-1, 256, 29, 29]               0C3-56          [-1, 256, 29, 29]               0Conv2d-57          [-1, 512, 15, 15]       1,179,648BatchNorm2d-58          [-1, 512, 15, 15]           1,024SiLU-59          [-1, 512, 15, 15]               0Conv-60          [-1, 512, 15, 15]               0Conv2d-61          [-1, 256, 15, 15]         131,072BatchNorm2d-62          [-1, 256, 15, 15]             512SiLU-63          [-1, 256, 15, 15]               0Conv-64          [-1, 256, 15, 15]               0Conv2d-65          [-1, 256, 15, 15]          65,536BatchNorm2d-66          [-1, 256, 15, 15]             512SiLU-67          [-1, 256, 15, 15]               0Conv-68          [-1, 256, 15, 15]               0Conv2d-69          [-1, 256, 15, 15]         589,824BatchNorm2d-70          [-1, 256, 15, 15]             512SiLU-71          [-1, 256, 15, 15]               0Conv-72          [-1, 256, 15, 15]               0Bottleneck-73          [-1, 256, 15, 15]               0Conv2d-74          [-1, 256, 15, 15]         131,072BatchNorm2d-75          [-1, 256, 15, 15]             512SiLU-76          [-1, 256, 15, 15]               0Conv-77          [-1, 256, 15, 15]               0Conv2d-78          [-1, 512, 15, 15]         262,144BatchNorm2d-79          [-1, 512, 15, 15]           1,024SiLU-80          [-1, 512, 15, 15]               0Conv-81          [-1, 512, 15, 15]               0C3-82          [-1, 512, 15, 15]               0Conv2d-83           [-1, 1024, 8, 8]       4,718,592BatchNorm2d-84           [-1, 1024, 8, 8]           2,048SiLU-85           [-1, 1024, 8, 8]               0Conv-86           [-1, 1024, 8, 8]               0Conv2d-87            [-1, 512, 8, 8]         524,288BatchNorm2d-88            [-1, 512, 8, 8]           1,024SiLU-89            [-1, 512, 8, 8]               0Conv-90            [-1, 512, 8, 8]               0Conv2d-91            [-1, 512, 8, 8]         262,144BatchNorm2d-92            [-1, 512, 8, 8]           1,024SiLU-93            [-1, 512, 8, 8]               0Conv-94            [-1, 512, 8, 8]               0Conv2d-95            [-1, 512, 8, 8]       2,359,296BatchNorm2d-96            [-1, 512, 8, 8]           1,024SiLU-97            [-1, 512, 8, 8]               0Conv-98            [-1, 512, 8, 8]               0Bottleneck-99            [-1, 512, 8, 8]               0Conv2d-100            [-1, 512, 8, 8]         524,288BatchNorm2d-101            [-1, 512, 8, 8]           1,024SiLU-102            [-1, 512, 8, 8]               0Conv-103            [-1, 512, 8, 8]               0Conv2d-104           [-1, 1024, 8, 8]       1,048,576BatchNorm2d-105           [-1, 1024, 8, 8]           2,048SiLU-106           [-1, 1024, 8, 8]               0Conv-107           [-1, 1024, 8, 8]               0C3-108           [-1, 1024, 8, 8]               0Conv2d-109            [-1, 512, 8, 8]         524,288BatchNorm2d-110            [-1, 512, 8, 8]           1,024SiLU-111            [-1, 512, 8, 8]               0Conv-112            [-1, 512, 8, 8]               0MaxPool2d-113            [-1, 512, 8, 8]               0MaxPool2d-114            [-1, 512, 8, 8]               0MaxPool2d-115            [-1, 512, 8, 8]               0Conv2d-116           [-1, 1024, 8, 8]       2,097,152BatchNorm2d-117           [-1, 1024, 8, 8]           2,048SiLU-118           [-1, 1024, 8, 8]               0Conv-119           [-1, 1024, 8, 8]               0SPPF-120           [-1, 1024, 8, 8]               0Linear-121                  [-1, 100]       6,553,700ReLU-122                  [-1, 100]               0Linear-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
----------------------------------------------------------------
Epoch: 1, Train_acc:55.0%, Train_loss:1.110, Test_acc:58.2%, Test_loss:0.733, Lr:1.00E-04
Epoch: 2, Train_acc:67.2%, Train_loss:0.837, Test_acc:49.3%, Test_loss:1.074, Lr:1.00E-04
Epoch: 3, Train_acc:72.0%, Train_loss:0.674, Test_acc:86.2%, Test_loss:0.367, Lr:1.00E-04
Epoch: 4, Train_acc:76.3%, Train_loss:0.591, Test_acc:82.2%, Test_loss:0.459, Lr:1.00E-04
Epoch: 5, Train_acc:81.7%, Train_loss:0.501, Test_acc:82.2%, Test_loss:0.482, Lr:1.00E-04
Epoch: 6, Train_acc:81.3%, Train_loss:0.471, Test_acc:76.0%, Test_loss:0.592, Lr:1.00E-04
Epoch: 7, Train_acc:82.4%, Train_loss:0.467, Test_acc:82.7%, Test_loss:0.591, Lr:1.00E-04
Epoch: 8, Train_acc:87.4%, Train_loss:0.368, Test_acc:89.8%, Test_loss:0.327, Lr:1.00E-04
Epoch: 9, Train_acc:88.0%, Train_loss:0.377, Test_acc:85.3%, Test_loss:0.433, Lr:1.00E-04
Epoch:10, Train_acc:90.4%, Train_loss:0.274, Test_acc:92.4%, Test_loss:0.135, Lr:1.00E-04
Epoch:11, Train_acc:87.9%, Train_loss:0.310, Test_acc:92.0%, Test_loss:0.279, Lr:1.00E-04
Epoch:12, Train_acc:89.2%, Train_loss:0.277, Test_acc:90.7%, Test_loss:0.234, Lr:1.00E-04
Epoch:13, Train_acc:90.8%, Train_loss:0.250, Test_acc:88.4%, Test_loss:0.322, Lr:1.00E-04
Epoch:14, Train_acc:92.7%, Train_loss:0.213, Test_acc:92.0%, Test_loss:0.192, Lr:1.00E-04
Epoch:15, Train_acc:92.1%, Train_loss:0.201, Test_acc:93.3%, Test_loss:0.200, Lr:1.00E-04
Epoch:16, Train_acc:94.7%, Train_loss:0.137, Test_acc:92.4%, Test_loss:0.185, Lr:1.00E-04
Epoch:17, Train_acc:94.9%, Train_loss:0.136, Test_acc:92.0%, Test_loss:0.274, Lr:1.00E-04
Epoch:18, Train_acc:94.1%, Train_loss:0.187, Test_acc:86.2%, Test_loss:0.434, Lr:1.00E-04
Epoch:19, Train_acc:94.1%, Train_loss:0.174, Test_acc:92.4%, Test_loss:0.163, Lr:1.00E-04
Epoch:20, Train_acc:96.1%, Train_loss:0.111, Test_acc:92.9%, Test_loss:0.174, Lr:1.00E-04
Epoch:21, Train_acc:96.8%, Train_loss:0.098, Test_acc:91.6%, Test_loss:0.298, Lr:1.00E-04
Epoch:22, Train_acc:97.7%, Train_loss:0.066, Test_acc:92.4%, Test_loss:0.213, Lr:1.00E-04
Epoch:23, Train_acc:96.1%, Train_loss:0.121, Test_acc:95.1%, Test_loss:0.223, Lr:1.00E-04
Epoch:24, Train_acc:97.4%, Train_loss:0.089, Test_acc:95.6%, Test_loss:0.171, Lr:1.00E-04
Epoch:25, Train_acc:95.7%, Train_loss:0.110, Test_acc:92.0%, Test_loss:0.224, Lr:1.00E-04
Epoch:26, Train_acc:97.9%, Train_loss:0.063, Test_acc:94.2%, Test_loss:0.247, Lr:1.00E-04
Epoch:27, Train_acc:98.8%, Train_loss:0.040, Test_acc:91.6%, Test_loss:0.299, Lr:1.00E-04
Epoch:28, Train_acc:98.0%, Train_loss:0.062, Test_acc:94.2%, Test_loss:0.218, Lr:1.00E-04
Epoch:29, Train_acc:98.1%, Train_loss:0.050, Test_acc:96.0%, Test_loss:0.169, Lr:1.00E-04
Epoch:30, Train_acc:99.6%, Train_loss:0.018, Test_acc:92.4%, Test_loss:0.241, Lr:1.00E-04
Epoch:31, Train_acc:95.2%, Train_loss:0.120, Test_acc:92.9%, Test_loss:0.267, Lr:1.00E-04
Epoch:32, Train_acc:95.1%, Train_loss:0.138, Test_acc:90.7%, Test_loss:0.302, Lr:1.00E-04
Epoch:33, Train_acc:98.2%, Train_loss:0.059, Test_acc:93.3%, Test_loss:0.223, Lr:1.00E-04
Epoch:34, Train_acc:97.1%, Train_loss:0.086, Test_acc:94.2%, Test_loss:0.171, Lr:1.00E-04
Epoch:35, Train_acc:98.1%, Train_loss:0.053, Test_acc:94.7%, Test_loss:0.166, Lr:1.00E-04
Epoch:36, Train_acc:98.7%, Train_loss:0.033, Test_acc:93.8%, Test_loss:0.218, Lr:1.00E-04
Epoch:37, Train_acc:99.9%, Train_loss:0.010, Test_acc:96.0%, Test_loss:0.217, Lr:1.00E-04
Epoch:38, Train_acc:99.2%, Train_loss:0.021, Test_acc:92.4%, Test_loss:0.237, Lr:1.00E-04
Epoch:39, Train_acc:99.7%, Train_loss:0.014, Test_acc:93.3%, Test_loss:0.183, Lr:1.00E-04
Epoch:40, Train_acc:99.2%, Train_loss:0.017, Test_acc:95.1%, Test_loss:0.188, Lr:1.00E-04
Epoch:41, Train_acc:97.1%, Train_loss:0.065, Test_acc:86.7%, Test_loss:0.494, Lr:1.00E-04
Epoch:42, Train_acc:97.0%, Train_loss:0.095, Test_acc:89.3%, Test_loss:0.331, Lr:1.00E-04
Epoch:43, Train_acc:98.0%, Train_loss:0.052, Test_acc:93.8%, Test_loss:0.204, Lr:1.00E-04
Epoch:44, Train_acc:97.8%, Train_loss:0.063, Test_acc:93.3%, Test_loss:0.238, Lr:1.00E-04
Epoch:45, Train_acc:99.6%, Train_loss:0.014, Test_acc:95.6%, Test_loss:0.185, Lr:1.00E-04
Epoch:46, Train_acc:98.1%, Train_loss:0.045, Test_acc:92.4%, Test_loss:0.229, Lr:1.00E-04
Epoch:47, Train_acc:98.7%, Train_loss:0.043, Test_acc:94.7%, Test_loss:0.136, Lr:1.00E-04
Epoch:48, Train_acc:100.0%, Train_loss:0.002, Test_acc:96.0%, Test_loss:0.128, Lr:1.00E-04
Epoch:49, Train_acc:100.0%, Train_loss:0.002, Test_acc:95.1%, Test_loss:0.172, Lr:1.00E-04
Epoch:50, Train_acc:98.1%, Train_loss:0.039, Test_acc:90.7%, Test_loss:0.261, Lr:1.00E-04
Epoch:51, Train_acc:96.7%, Train_loss:0.089, Test_acc:94.2%, Test_loss:0.183, Lr:1.00E-04
Epoch:52, Train_acc:98.0%, Train_loss:0.061, Test_acc:93.3%, Test_loss:0.244, Lr:1.00E-04
Epoch:53, Train_acc:97.8%, Train_loss:0.057, Test_acc:93.3%, Test_loss:0.259, Lr:1.00E-04
Epoch:54, Train_acc:99.3%, Train_loss:0.018, Test_acc:95.1%, Test_loss:0.160, Lr:1.00E-04
Epoch:55, Train_acc:99.6%, Train_loss:0.015, Test_acc:96.9%, Test_loss:0.128, Lr:1.00E-04
Epoch:56, Train_acc:99.9%, Train_loss:0.010, Test_acc:95.1%, Test_loss:0.202, Lr:1.00E-04
Epoch:57, Train_acc:99.4%, Train_loss:0.032, Test_acc:94.7%, Test_loss:0.267, Lr:1.00E-04
Epoch:58, Train_acc:98.9%, Train_loss:0.029, Test_acc:95.1%, Test_loss:0.158, Lr:1.00E-04
Epoch:59, Train_acc:98.0%, Train_loss:0.063, Test_acc:95.1%, Test_loss:0.217, Lr:1.00E-04
Epoch:60, Train_acc:99.1%, Train_loss:0.026, Test_acc:92.4%, Test_loss:0.347, Lr:1.00E-04
Done

笔记本训练模型用了一个多小时，建议还是用有显卡的电脑训练。

本文来自互联网用户投稿，该文观点仅代表作者本人，不代表本站立场。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如若转载，请注明出处：http://www.mzph.cn/news/600544.shtml

如若内容造成侵权/违法违规/事实不符，请联系多彩编程网进行投诉反馈email:809451989@qq.com，一经查实，立即删除！

相关文章

OpenSSL provider

OpenSSL provider

提供者 标准提供者默认提供者传统提供者FIPS 提供者基本提供者空提供者加载提供者 标准提供者 提供者是算法实现的容器。每当通过高级别 API 使用加密算法时&#xff0c;都会选择一个提供者。实际上是由该提供者实现执行所需的工作。OpenSSL 自带了五个提供者。在未来&#…
阅读更多...
视频智能分析/云存储平台EasyCVR接入海康SDK，通道名称未自动更新该如何解决？

视频智能分析/云存储平台EasyCVR接入海康SDK，通道名称未自动更新该如何解决？

视频监控GB28181平台EasyCVR能在复杂的网络环境中&#xff0c;将分散的各类视频资源进行统一汇聚、整合、集中管理&#xff0c;在视频监控播放上&#xff0c;TSINGSEE青犀视频安防监控汇聚平台可支持1、4、9、16个画面窗口播放&#xff0c;可同时播放多路视频流&#xff0c;也能…
阅读更多...
Oracle-存储过程

Oracle-存储过程

简介 存储过程(Stored Procedure)是一组为了完成特定功能的SQL语句集&#xff0c;它大大提高了SQL语句的功能和灵活性。存储过程编译后存储在数据库中&#xff0c;所以执行存储过程比执行存储过程中封装的SQL语句更有效率。 语法 存储过程: 一组为了完成某种特定功能的sql语句…
阅读更多...
Protobuf 编码结构

Protobuf 编码结构

编码结构 什么是protobuf protocol buffers 是一种语言无关、平台无关、可扩展的序列化结构数据的方法&#xff0c;可用于数据通信协议和数据存储等&#xff0c;它是 Google 提供的一个具有高效协议数据交换格式工具库&#xff0c;是一种灵活、高效和自动化机制的结构数据序列…
阅读更多...
MySQL-数据库概述

MySQL-数据库概述

数据库相关概念&#xff1a; 数据库(DateBase)简称DB,就是一个存储数据的仓库&#xff0c;数据有组织的进行存储。 数据库分为关系型数据库简称RDBMS和非关系型数据库 关系型数据库简称RDBMS:建立在关系模型的基础上&#xff0c;由多张相互连接的二维表组成的数据库.简单来说…
阅读更多...
Nginx(十七) 日志轮询/切割

Nginx(十七) 日志轮询/切割

1.编写shell脚本 Nginx_Log_Path"/usr/local/nginx/logs/" Dateformat$(date -d "yesterday" %Y%m%d) mv ${Nginx_Log_Path}/access.log ${Nginx_Log_Path}/access-${Dateformat}.log mv ${Nginx_Log_Path}/access_8688.log ${Nginx_Log_Path}/access_868…
阅读更多...
【Linux软件包管理器】yum详解

【Linux软件包管理器】yum详解

目录 1、什么是软件包 2、yum的操作 1&#xff09;yum源 2&#xff09;三板斧 ① yum list ② yum install [软键名] ③ yum remove [软件名] 1、什么是软件包 在Linux下安装软件, 一个通常的办法是下载到程序的源代码, 并进行编译, 得到可执行程序. 但是这样太麻烦了,…
阅读更多...
除了sd webui，compfy还有一个sd UI

除了sd webui，compfy还有一个sd UI

GitHub - VoltaML/voltaML-fast-stable-diffusion: Beautiful and Easy to use Stable Diffusion WebUI
阅读更多...
国科大图像处理2024速通期末——汇总2017-2019、2023回忆

国科大图像处理2024速通期末——汇总2017-2019、2023回忆

国科大2023.12.28图像处理0854期末重点 图像处理 王伟强 作业 课件 资料 一、填空 一个阴极射线管它的输入与输出满足 s r 2 sr^{2} sr2&#xff0c;这将使得显示系统产生比希望的效果更暗的图像&#xff0c;此时伽马校正通常在信号进入显示器前被进行预处理&#xff0c;令p…
阅读更多...
Unity之键盘鼠标的监控

Unity之键盘鼠标的监控

小编最近在玩大表哥2&#xff0c;通过 W、A、S、D 来移动亚瑟&#xff0c;鼠标左键来不吃牛肉 我们都知道玩家通过按键鼠标来控制游戏人物做出相应的行为动作&#xff0c;那在Unity引擎里是怎么知道玩家是如何操作的呢&#xff1f;本篇来介绍Unity是怎样监控键盘和鼠标的。 首先…
阅读更多...
fatal: Need to specify how to reconcile divergent branches.如何处理

fatal: Need to specify how to reconcile divergent branches.如何处理

错误信息 “fatal: Need to specify how to reconcile divergent branches.” 通常在尝试推送到远程仓库时出现&#xff0c;尤其是当本地分支和远程分支有分歧&#xff08;即它们各自有一些不同的提交&#xff09;时。处理这个问题通常涉及合并&#xff08;merge&#xff09;或…
阅读更多...
计算机网络期末知识汇总

计算机网络期末知识汇总

一、计算机网络概述 1.Internet 的中文译名并不统一。 现有的 Internet 译名有两种&#xff1a; 因特网&#xff0c;这个译名是全国科学技术名词审定委员会推荐的&#xff0c;但却长期未得 到推广&#xff1b; 互联网&#xff0c;这是目前流行最广的、事实上的标准译名。现…
阅读更多...
spring常用注解（三）springbean类

spring常用注解（三）springbean类

一、Service用于标注业务层组件、 二、Repository用于标注数据访问组件&#xff0c;即DAO组件。 三、Component泛指组件&#xff0c;当组件不好归类的时候&#xff0c;我们可以使用这个注解进行标注。&#xff08;pojo&#xff09; 四、Scope用于指定scope作用域的&#xff…
阅读更多...
Node.js + Mysql 防止sql注入的写法

Node.js + Mysql 防止sql注入的写法

关键代码 const queryString SELECT * FROM sys_user LIMIT ?, ?;let data await query(queryString, [startIndex,pageSize]); 访问数据库相关代码 const mysql require(mysql)const pool mysql.createPool({host: 127.0.0.1,user: root,password: 123456,database:…
阅读更多...
【C语言】静动态内存的跨函数访问malloc、free

【C语言】静动态内存的跨函数访问malloc、free

目录 多指针初认识&#xff1a;动态内存和多级指针的跨函数访问动态内存和静态内存的比较&#xff1a;静态内存不可以跨函数访问&#xff1a;动态内存跨函数访问&#xff1a;malloc和free示例 多指针初认识&#xff1a; #include <stdio.h> #include <stdlib.h> in…
阅读更多...
技术查漏补缺（1）Logback

技术查漏补缺（1）Logback

一、下定义&#xff1a;Logback是一个开源的日志组件 二、Logback的maven <!--这个依赖直接包含了 logback-core 以及 slf4j-api的依赖--> <dependency><groupId>ch.qos.logback</groupId><artifactId>logback-classic</artifactId><v…
阅读更多...
新手解锁语言之力：理解 PyTorch 中 Transformer 组件

新手解锁语言之力：理解 PyTorch 中 Transformer 组件

目录 torch.nn子模块transformer详解 nn.Transformer Transformer 类描述 Transformer 类的功能和作用 Transformer 类的参数 forward 方法 参数 输出 示例代码 注意事项 nn.TransformerEncoder TransformerEncoder 类描述 TransformerEncoder 类的功能和作用 Tr…
阅读更多...
vite + vue3引入ant design vue 报错

vite + vue3引入ant design vue 报错

npm install ant-design-vue --save下载插件并在main.ts 全局引入 报错 解决办法一&#xff1a; main.ts注释掉全局引入 模块按需引入 解决办法二 将package.json中的ant-design-vue的版本^4.0.0-rc.4改为 ^3.2.15版本 同时将将package-lock.json中的ant-design-vue的版本…
阅读更多...
Android13 热点默认5G频道配置修改

Android13 热点默认5G频道配置修改

Android13 热点默认5G频道配置修改 文章目录 Android13 热点默认5G频道配置修改一、前言二、修改默认配置1、代码中修改默认配置2、保存默认配置文件设置默认5G频段配置热点配置文件完整信息示例&#xff1a; 3、代码中强制设置配置信息&#xff08;1&#xff09;在关键流程设置…
阅读更多...
Graceful Response 构建 Spring Boot 下优雅的响应处理

Graceful Response 构建 Spring Boot 下优雅的响应处理

一、Graceful Response Graceful Response 是一个 Spring Boot 技术栈下的优雅响应处理器&#xff0c;提供一站式统一返回值封装、全局异常处理、自定义异常错误码等功能&#xff0c;使用Graceful Response进行web接口开发不仅可以节省大量的时间&#xff0c;还可以提高代码质…
阅读更多...
最新文章

Copyright @ 2022~2023