文章目录
- 一、PyTorch环境的配置及安装
- 二、Pycharm、jupyter的安装
- 三、Python学习中的两大法宝函数（help、dir）
- 四、加载数据（Dataset）
- 五、TensorBorad的使用
- 六、Transformer
- 七、torchvision中数据集的使用
- 八、dataloader
- 十一、卷积层
- 十二、池化层
- 十三、非线性激活
- 十四、线性层
- 十五、Sequential
- 十六、损失函数和反向传播
- 十七、现有模型的使用及修改
- 十八、网络模型的保存和修改
- 十九、完整的模型训练套路
- 二十、利用GPU训练
- 二十一、完整的模型验证套路
- 总结
官网下载最新版Anaconda，完成后打开Anaconda Prompt，显示（base）即安装成功
2.conda create -n pytorch python=3.6建立一个命名为pytorch的环境，且环境python版本为3.6
3.conda activate pytorch激活并进入pytorch这个环境;linux：source activate pytorch
4.pip list来查看环境内安装了哪些包，可以发现并没有我们需要的pytorch
5.打开PyTorch官网，直接找到最新版pytorch指令conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch（无脑最新版就完事了。。。。老版本调了半天，最后还出问题了），打开pytorch环境，输入指令下载安装
6.检验是否安装成功。输入python，import torch不报错即pytorch安装成功。输入torch.cuda.is_available(),若返回True即机器显卡是可以被pytorch使用的（如失败，建议去英伟达官网下载更新驱动程序，并删除环境，使用各种最新版重新安装）。
7.linux服务器安装时出现环境安装不到conda/envs下，而在.conda下，进行如下操作
other:conda info -e （查看所有的虚拟环境）
删除环境：
第一步：首先退出环境
conda deactivate
第二步：删除环境
conda remove -n 需要删除的环境名 --all
rm -rf + 文件名 删除文件夹
df -h查看linux系统各分区的情况
nohup 命令 > 文件 2>&1 & # 使模型在后台训练 exit退出黑窗口
1.> 会重写文件，如果文件里面有内容会覆盖，没有则创建并写入。
2.>> 将内容追加到文件中，即如果文件里面有内容会把新内容追加到文件尾，如果文件不存在，就创建文件
kill -9 PID # 关闭特定进程
tar -xvf #解压tar包
查看当前文件夹的大小：du -ah
查看当前文件夹下面各个文件夹的大小：du -ah --max-depth=1
anaconda下的pkgs怎么清理:conda clean -a
ps u pid 查询显卡谁在使用
sudo chmod -R 777 myResources 修改文件的权限为所有用户拥有最高权限
pip install *** -i https://pypi.tuna.tsinghua.edu.cn/simple 镜像加速安装
ps -f -p 26359 可以看到进程26359在跑训练
cp -r /TEST/test1 /TEST/test2 复制文件夹
Defaulting to user installation because normal site-packages is not writeable ： python3 -m pip install requests
fuser -v /dev/nvidia* nvidia-smi 无进程占用GPU，但GPU显存却被占用了
1. Pycharm
pycharm官网下载安装
2.新建项目（lean_pytorch)，
点击已存在的编译器，点进去寻找刚刚我们安装好的环境。
导入成功。
2.jupyter
- 安装好anaconda后无需再次安装。
- jupyter默认安装在base环境中，所以我们需要在pytorch环境中安装jupyter.
- 进入pytorch环境，输入
conda install nb_conda安装juypter - 安装完成后输入
juypter notebook即可打开。 
新建pytorch环境下的juypter文件。- 输入
import torch,torch.cuda.is_available()，返回TRUE即安装成功。
进入pycharm的python console，输入dir(torch),dir(torch.cuda),dir(torch.cuda.is_available()),help(torch.cuda.is_available)。
from torch.utils.data import Dataset, DataLoaderimport numpy as npfrom PIL import Imageimport osfrom torchvision import transformsfrom torch.utils.tensorboard import SummaryWriterfrom torchvision.utils import make_gridwriter = SummaryWriter("logs")class MyData(Dataset): def __init__(self, root_dir, image_dir, label_dir, transform): self.root_dir = root_dir self.image_dir = image_dir self.label_dir = label_dir self.label_path = os.path.join(self.root_dir, self.label_dir) self.image_path = os.path.join(self.root_dir, self.image_dir) self.image_list = os.listdir(self.image_path) self.label_list = os.listdir(self.label_path) self.transform = transform # 因为label 和 Image文件名相同，进行一样的排序，可以保证取出的数据和label是一一对应的 self.image_list.sort() self.label_list.sort() def __getitem__(self, idx): img_name = self.image_list[idx] label_name = self.label_list[idx] img_item_path = os.path.join(self.root_dir, self.image_dir, img_name) label_item_path = os.path.join(self.root_dir, self.label_dir, label_name) img = Image.open(img_item_path) with open(label_item_path, 'r') as f: label = f.readline() # img = np.array(img) img = self.transform(img) sample = {'img': img, 'label': label} return sample def __len__(self): assert len(self.image_list) == len(self.label_list) return len(self.image_list)if __name__ == '__main__': transform = transforms.Compose([transforms.Resize((256, 256)), transforms.ToTensor()]) root_dir = "dataset/train" image_ants = "ants_image" label_ants = "ants_label" ants_dataset = MyData(root_dir, image_ants, label_ants, transform) image_bees = "bees_image" label_bees = "bees_label" bees_dataset = MyData(root_dir, image_bees, label_bees, transform) train_dataset = ants_dataset + bees_dataset # transforms = transforms.Compose([transforms.Resize(256, 256)]) dataloader = DataLoader(train_dataset, batch_size=1, num_workers=2) writer.add_image('error', train_dataset[119]['img']) writer.close() # for i, j in enumerate(dataloader): # # imgs, labels = j # print(type(j)) # print(i, j['img'].shape) # # writer.add_image("train_data_b2", make_grid(j['img']), i) # # writer.close()安装tensorborad:pip install tensorboard
更改端口：
进入structure
1.compose
将几个步骤合为一个
2.toTensor
将PIL和numpy类型的图片转为Tensor（可用于训练）
__call__的使用：
ctrl+p提示函数参数
3.Normalize
讲一个tensor类型进行归一化
4.Resize
tips:
torchvision 是PyTorch中专门用来处理图像的库。这个包中有四个大类。
torchvision.datasets
torchvision.models
torchvision.transforms
torchvision.utils
这里主要介绍前三个。
1.torchvision.datasets
drop_last=true,舍去最后的余数图片，如上半张图片将会舍去，下半张图片为FALSE
九、nn.module
十、卷积操作
import torchimport torchvisionfrom torch import nnfrom torch.nn import Conv2dfrom torch.utils.data import DataLoaderfrom torch.utils.tensorboard import SummaryWriterdataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(), download=True)dataloader = DataLoader(dataset, batch_size=64)class Tudui(nn.Module): def __init__(self): super(Tudui, self).__init__() self.conv1 = Conv2d(in_channels=3, out_channels=6, kernel_size=3, stride=1, padding=0) def forward(self, x): x = self.conv1(x) return xtudui = Tudui()writer = SummaryWriter("../logs")step = 0for data in dataloader: imgs, targets = data output = tudui(imgs) print(imgs.shape) print(output.shape) # torch.Size([64, 3, 32, 32]) writer.add_images("input", imgs, step) # torch.Size([64, 6, 30, 30]) -> [xxx, 3, 30, 30] output = torch.reshape(output, (-1, 3, 30, 30)) writer.add_images("output", output, step) step = step + 1import torchimport torchvisionfrom torch import nnfrom torch.nn import MaxPool2dfrom torch.utils.data import DataLoaderfrom torch.utils.tensorboard import SummaryWriterdataset = torchvision.datasets.CIFAR10("../data", train=False, download=True, transform=torchvision.transforms.ToTensor())dataloader = DataLoader(dataset, batch_size=64)class Tudui(nn.Module): def __init__(self): super(Tudui, self).__init__() self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=False) def forward(self, input): output = self.maxpool1(input) return outputtudui = Tudui()writer = SummaryWriter("../logs_maxpool")step = 0for data in dataloader: imgs, targets = data writer.add_images("input", imgs, step) output = tudui(imgs) writer.add_images("output", output, step) step = step + 1writer.close()
input = torch.tensor([[1, -0.5], [-1, 3]])input = torch.reshape(input, (-1, 1, 2, 2))print(input.shape)dataset = torchvision.datasets.CIFAR10("../data", train=False, download=True, transform=torchvision.transforms.ToTensor())dataloader = DataLoader(dataset, batch_size=64)class Tudui(nn.Module): def __init__(self): super(Tudui, self).__init__() self.relu1 = ReLU() self.sigmoid1 = Sigmoid() def forward(self, input): output = self.sigmoid1(input) return outputtudui = Tudui()writer = SummaryWriter("../logs_relu")step = 0for data in dataloader: imgs, targets = data writer.add_images("input", imgs, global_step=step) output = tudui(imgs) writer.add_images("output", output, step) step += 1writer.close()import torchimport torchvisionfrom torch import nnfrom torch.nn import Linearfrom torch.utils.data import DataLoaderdataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(), download=True)dataloader = DataLoader(dataset, batch_size=64)class Tudui(nn.Module): def __init__(self): super(Tudui, self).__init__() self.linear1 = Linear(196608, 10) def forward(self, input): output = self.linear1(input) return outputtudui = Tudui()for data in dataloader: imgs, targets = data print(imgs.shape) output = torch.flatten(imgs) print(output.shape) output = tudui(output) print(output.shape)import torchfrom torch import nnfrom torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequentialfrom torch.utils.tensorboard import SummaryWriterclass Tudui(nn.Module): def __init__(self): super(Tudui, self).__init__() self.model1 = Sequential( Conv2d(3, 32, 5, padding=2), MaxPool2d(2), Conv2d(32, 32, 5, padding=2), MaxPool2d(2), Conv2d(32, 64, 5, padding=2), MaxPool2d(2), Flatten(), Linear(1024, 64), Linear(64, 10) ) def forward(self, x): x = self.model1(x) return xtudui = Tudui()print(tudui)input = torch.ones((64, 3, 32, 32))output = tudui(input)print(output.shape)writer = SummaryWriter("../logs_seq")writer.add_graph(tudui, input)writer.close()1.损失函数
import torchvisionfrom torch import nnfrom torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linearfrom torch.utils.data import DataLoaderdataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(), download=True)dataloader = DataLoader(dataset, batch_size=1)class Tudui(nn.Module): def __init__(self): super(Tudui, self).__init__() self.model1 = Sequential( Conv2d(3, 32, 5, padding=2), MaxPool2d(2), Conv2d(32, 32, 5, padding=2), MaxPool2d(2), Conv2d(32, 64, 5, padding=2), MaxPool2d(2), Flatten(), Linear(1024, 64), Linear(64, 10) ) def forward(self, x): x = self.model1(x) return xloss = nn.CrossEntropyLoss()tudui = Tudui()for data in dataloader: imgs, targets = data outputs = tudui(imgs) result_loss = loss(outputs, targets) print("ok")2.反向传播及优化
import torchimport torchvisionfrom torch import nnfrom torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linearfrom torch.optim.lr_scheduler import StepLRfrom torch.utils.data import DataLoaderdataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(), download=True)dataloader = DataLoader(dataset, batch_size=1)class Tudui(nn.Module): def __init__(self): super(Tudui, self).__init__() self.model1 = Sequential( Conv2d(3, 32, 5, padding=2), MaxPool2d(2), Conv2d(32, 32, 5, padding=2), MaxPool2d(2), Conv2d(32, 64, 5, padding=2), MaxPool2d(2), Flatten(), Linear(1024, 64), Linear(64, 10) ) def forward(self, x): x = self.model1(x) return xloss = nn.CrossEntropyLoss()tudui = Tudui()optim = torch.optim.SGD(tudui.parameters(), lr=0.01)scheduler = StepLR(optim, step_size=5, gamma=0.1)for epoch in range(20): running_loss = 0.0 for data in dataloader: imgs, targets = data outputs = tudui(imgs) result_loss = loss(outputs, targets) optim.zero_grad() result_loss.backward() scheduler.step() running_loss = running_loss + result_loss print(running_loss)import torchvision# train_data = torchvision.datasets.ImageNet("../data_image_net", split='train', download=True,# transform=torchvision.transforms.ToTensor())from torch import nnvgg16_false = torchvision.models.vgg16(pretrained=False)vgg16_true = torchvision.models.vgg16(pretrained=True)print(vgg16_true)train_data = torchvision.datasets.CIFAR10('../data', train=True, transform=torchvision.transforms.ToTensor(), download=True)vgg16_true.classifier.add_module('add_linear', nn.Linear(1000, 10))print(vgg16_true)print(vgg16_false)vgg16_false.classifier[6] = nn.Linear(4096, 10)print(vgg16_false)1.保存
import torchimport torchvisionfrom torch import nnvgg16 = torchvision.models.vgg16(pretrained=False)# 保存方式1,模型结构+模型参数torch.save(vgg16, "vgg16_method1.pth")# 保存方式2，模型参数（官方推荐）torch.save(vgg16.state_dict(), "vgg16_method2.pth")# 陷阱class Tudui(nn.Module): def __init__(self): super(Tudui, self).__init__() self.conv1 = nn.Conv2d(3, 64, kernel_size=3) def forward(self, x): x = self.conv1(x) return xtudui = Tudui()torch.save(tudui, "tudui_method1.pth")2.读取
import torchfrom model_save import *# 方式1-》保存方式1，加载模型import torchvisionfrom torch import nnmodel = torch.load("vgg16_method1.pth")# print(model)# 方式2，加载模型vgg16 = torchvision.models.vgg16(pretrained=False)vgg16.load_state_dict(torch.load("vgg16_method2.pth"))# model = torch.load("vgg16_method2.pth")# print(vgg16)# 陷阱1# class Tudui(nn.Module):# def __init__(self):# super(Tudui, self).__init__()# self.conv1 = nn.Conv2d(3, 64, kernel_size=3)## def forward(self, x):# x = self.conv1(x)# return xmodel = torch.load('tudui_method1.pth')print(model)只用方式2！！！！
import torchvisionfrom my_model import *from torch.utils.tensorboard import SummaryWriter#准备数据集from torch import nnfrom torch.utils.data import DataLoadertrain_data = torchvision.datasets.CIFAR10(root="../data",train=True,transform=torchvision.transforms.ToTensor(),download=True)test_data = torchvision.datasets.CIFAR10(root="../data",train=False,transform=torchvision.transforms.ToTensor(),download=True)# length 长度train_data_size = len(train_data)test_data_size = len(test_data)# 如果train_data_size=10,训练数据集的长度为：10print("训练数据集的长度为:{}".format(train_data_size))print("测试数据集的长度为:{}".format(test_data_size))#利用 DataLoader 来加载数据集train_dataloader = DataLoader(train_data,batch_size=64)test_dataloader = DataLoader(test_data,batch_size=64)#创建网络模型tudui = Tudui()#损失函数loss_fn = nn.CrossEntropyLoss()#优化器learning_rate = 1e-2optimizer = torch.optim.SGD(tudui.parameters(),lr=learning_rate)#训练网络的一些参数#记录训练的次数total_train_step = 0#记录测试的次数total_test_step = 0#训练的轮数epoch = 10#添加tensorboardwriter = SummaryWriter("../logs_train")for i in range(epoch): print("-----------第{}轮训练开始-----------".format(i+1)) #训练步骤开始 tudui.train() for data in train_dataloader: imgs,targets = data outputs = tudui(imgs) loss = loss_fn(outputs,targets) #优化器优化模型 optimizer.zero_grad() loss.backward() optimizer.step() total_train_step += 1 if total_train_step % 100 == 0: print("训练次数：{},Loss:{}".format(total_train_step,loss.item())) writer.add_scalar("train_loss",loss.item(),total_train_step) # 测试步骤开始 tudui.eval() total_test_loss = 0 total_accuracy = 0 with torch.no_grad(): for data in test_dataloader: imgs,targets = data outputs = tudui(imgs) loss = loss_fn(outputs,targets) total_test_loss += loss accuracy = (outputs.argmax(1)==targets).sum() total_accuracy += accuracy print("整体集上的Loss:{}".format(total_test_loss)) print("整体数据集上的正确率：{}".format(total_accuracy/test_data_size)) writer.add_scalar("test_loss",total_test_loss,total_test_step) writer.add_scalar("test_accuracy",total_accuracy/test_data_size,total_test_step) total_test_step += 1 torch.save(tudui,"tudui_{}.pth".format(i)) #torch.save(tudui.state_dict(),"tudui_{}".format(i)) print("模型已保存")writer.close()
import torchvisionfrom torch.utils.tensorboard import SummaryWriterimport torchimport time#准备数据集from torch import nnfrom torch.utils.data import DataLoaderdevice = torch.device("cuda")train_data = torchvision.datasets.CIFAR10(root="../data",train=True,transform=torchvision.transforms.ToTensor(),download=True)test_data = torchvision.datasets.CIFAR10(root="../data",train=False,transform=torchvision.transforms.ToTensor(),download=True)# length 长度train_data_size = len(train_data)test_data_size = len(test_data)# 如果train_data_size=10,训练数据集的长度为：10print("训练数据集的长度为:{}".format(train_data_size))print("测试数据集的长度为:{}".format(test_data_size))#利用 DataLoader 来加载数据集train_dataloader = DataLoader(train_data,batch_size=64)test_dataloader = DataLoader(test_data,batch_size=64)#创建网络模型class Tudui(nn.Module): def __init__(self): super(Tudui, self).__init__() self.model = nn.Sequential( nn.Conv2d(3,32,5,1,2), nn.MaxPool2d(2), nn.Conv2d(32,32,5,1,2), nn.MaxPool2d(2), nn.Conv2d(32,64,5,1,2), nn.MaxPool2d(2), nn.Flatten(), nn.Linear(64*4*4,64), nn.Linear(64,10) ) def forward(self,x): x=self.model(x) return xtudui = Tudui()tudui=tudui.to(device)#损失函数loss_fn = nn.CrossEntropyLoss()loss_fn = loss_fn.to(device)#优化器learning_rate = 1e-2optimizer = torch.optim.SGD(tudui.parameters(),lr=learning_rate)#训练网络的一些参数#记录训练的次数total_train_step = 0#记录测试的次数total_test_step = 0#训练的轮数epoch = 10#添加tensorboardwriter = SummaryWriter("../logs_train")start_time=time.time()for i in range(epoch): print("-----------第{}轮训练开始-----------".format(i+1)) #训练步骤开始 tudui.train() for data in train_dataloader: imgs,targets = data imgs = imgs.to(device) targets = targets.to(device) outputs = tudui(imgs) loss = loss_fn(outputs,targets) #优化器优化模型 optimizer.zero_grad() loss.backward() optimizer.step() total_train_step += 1 if total_train_step % 100 == 0: end_time = time.time() print(end_time-start_time) print("训练次数：{},Loss:{}".format(total_train_step,loss.item())) writer.add_scalar("train_loss",loss.item(),total_train_step) # 测试步骤开始 tudui.eval() total_test_loss = 0 total_accuracy = 0 with torch.no_grad(): for data in test_dataloader: imgs,targets = data imgs = imgs.to(device) targets = targets.to(device) outputs = tudui(imgs) loss = loss_fn(outputs,targets) total_test_loss += loss accuracy = (outputs.argmax(1)==targets).sum() total_accuracy += accuracy print("整体集上的Loss:{}".format(total_test_loss)) print("整体数据集上的正确率：{}".format(total_accuracy/test_data_size)) writer.add_scalar("test_loss",total_test_loss,total_test_step) writer.add_scalar("test_accuracy",total_accuracy/test_data_size,total_test_step) total_test_step += 1 torch.save(tudui,"tudui_{}.pth".format(i)) #torch.save(tudui.state_dict(),"tudui_{}".format(i)) print("模型已保存")writer.close()# -*- coding: utf-8 -*-# 作者：小土堆# 公众号：土堆碎念import torchimport torchvisionfrom PIL import Imagefrom torch import nnimage_path = "../imgs/airplane.png"image = Image.open(image_path)print(image)image = image.convert('RGB') # 因为png格式是四通道，除了RGB三通道外，还有一个透明度通道，# 调用convert保留其颜色通道。当然，如果图片本来就是三个颜色通道，经此操作，不变。加上这一步可以适应png jpg各种格式的图片transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32, 32)), torchvision.transforms.ToTensor()])image = transform(image)print(image.shape)class Tudui(nn.Module): def __init__(self): super(Tudui, self).__init__() self.model = nn.Sequential( nn.Conv2d(3, 32, 5, 1, 2), nn.MaxPool2d(2), nn.Conv2d(32, 32, 5, 1, 2), nn.MaxPool2d(2), nn.Conv2d(32, 64, 5, 1, 2), nn.MaxPool2d(2), nn.Flatten(), nn.Linear(64*4*4, 64), nn.Linear(64, 10) ) def forward(self, x): x = self.model(x) return xmodel = torch.load("tudui_29_gpu.pth", map_location=torch.device('cpu'))print(model)image = torch.reshape(image, (1, 3, 32, 32))model.eval()with torch.no_grad(): output = model(image)print(output)print(output.argmax(1))。
来源地址：https://blog.csdn.net/qq_44428997/article/details/127117489
