pytorch基础教程(目标检测)
文章目录
-
- 1 python ；两大法宝函数
- 2 加载数据
- 3 TensorBoard 的使用
- 4 transforms的使用
- 5 torchvision中的数据集使用
- 6 dataloader的使用
- 7 卷积操作
- 8 卷积层
- 9 最大池化
- 10 非线性激化
- 11 线性层
- 12 Sequential的使用
- 13 损失函数
- 14 优化器
- 15 现有网络模型的使用及修改
- 16 网络模型的保存及读取
- 17 完整的模型训练套路
- 18 利用gpu训练
- 19 完整的模型验证套路
1 python ；两大法宝函数
dir(): 打开，看见
helo(): 说明书
使用python控制台运行
import torch
tourch.cuda.is_available()
dir(torch)
dir(torch.cuda)
dir(torch.cuda.is_available)
help(torch.cuda.is_available())
命令行输入：jupyter notebook打开jupyter
2 加载数据
import os.path
from torch.utils.data import Dataset
from PIL import Image
class MyData(Dataset):
def __init__(self, root_dir, label_dir):
self.root_dir = root_dir
self.label_dir = label_dir
self.path = os.path.join(self.root_dir, self.label_dir)
self.img_path = os.listdir(self.path)
def __getitem__(self, idx):
img_name = self.img_path[idx]
img_item_path = os.path.join(self.root_dir, self.label_dir, img_name)
img = Image.open(img_item_path)
label = self.label_dir
return img, label
def __len__(self):
return len(self.img_path)
root_dir = 'hymenoptera_data/train'
ants_label_dir = 'ants'
bees_label_dir = 'bees'
bees_dataset= MyData(root_dir,bees_label_dir)
ants_dataset = MyData(root_dir, ants_label_dir)
train_dataset=ants_dataset+bees_dataset
3 TensorBoard 的使用
from torch.utils.tensorboard import SummaryWriter
writer=SummaryWriter("logs")
for i in range(100):
writer.add_scalar("y=x", i, i)
writer.close()
使用查看图像
tensorboard --logdir=logs # --port=6007 更换端口号
显示图像
from torch.utils.tensorboard import SummaryWriter
import numpy as np
from PIL import Image
writer=SummaryWriter("logs")
image_path= "hymenoptera_data/train/bees/85112639_6e860b0469.jpg"
img_PIL=Image.open(image_path)
img_array=np.array(img_PIL)
print(type(img_array))
print(img_array.shape)
writer.add_image("test",img_array,1,dataformats="HWC")
writer.close()
4 transforms的使用
from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
img_path="hymenoptera_data/train/ants/175998972.jpg"
img=Image.open(img_path)
writer=SummaryWriter("logs")
print(img)
# 1. 如何使用transforms
tensor_trans= transforms.ToTensor()
tensor_img=tensor_trans(img)
writer.add_image("Tensor_img",tensor_img)
print(tensor_img)
from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
writer = SummaryWriter('logs')
img = Image.open("hymenoptera_data/train/ants/kurokusa.jpg")
print(img)
# ToTensor
trans_totensor = transforms.ToTensor()
img_tensor = trans_totensor(img)
writer.add_image("ToTensor", img_tensor)
# Normalize
print((img_tensor[0][0][0]))
trans_norm = transforms.Normalize([0.5, 5, 0.5], [9, 0.5, 0.5])
img_norm = trans_norm(img_tensor)
print((img_tensor[0][0][0]))
writer.add_image("Normalize", img_norm, 2)
# Resize
print(img.size)
transforms_resize = transforms.Resize((512, 512))
resize_img = transforms_resize(img)
resize_img = trans_totensor(resize_img)
writer.add_image("Resize", resize_img, 0)
print(resize_img)
# Compose
trans_resize2 = transforms.Resize(512)
transforms_compose = transforms.Compose([trans_resize2, trans_totensor])
resize_img2 = transforms_compose(img)
writer.add_image("Resize", resize_img2, 1)
# RandomCrop
trans_random = transforms.RandomCrop(500, 1000)
trans_compose2 = transforms.Compose([trans_random, trans_totensor])
for i in range(10):
img_crop = trans_compose2(img)
writer.add_image("RandomCrop", img_crop, i)
writer.close()
5 torchvision中的数据集使用
import torchvision
from tensorboardX import SummaryWriter
dataset_transform=torchvision.transforms.Compose([
torchvision.transforms.ToTensor()
])
# S = torchvision.datasets.SBDataset("./dataset", "train", "boundaries", True)
train_set = torchvision.datasets.CIFAR10(root="./dataset",train=True,transform=dataset_transform,download=True)
test_set = torchvision.datasets.CIFAR10(root="./dataset",train=False,transform=dataset_transform,download=True)
# print(test_set[0])
# print(test_set.classes)
#
# img, target=test_set[0]
# print(img)
# print(target)
# print(test_set.classes[target])
# img.show()
# print(test_set[0])
writer=SummaryWriter("p10")
for i in range(10):
img,target=test_set[i]
writer.add_image("test_set",img,i)
writer.close()
6 dataloader的使用
import torchvision
from tensorboardX import SummaryWriter
from torch.utils.data import DataLoader
test_data=torchvision.datasets.CIFAR10("dataset",False,torchvision.transforms.ToTensor())
test_loader=DataLoader(dataset=test_data,batch_size=4,shuffle=False,num_workers=0,drop_last=True)
# 测试数据集的图片
img,target=test_data[0]
print(img.shape)
print(target)
writer=SummaryWriter("dataloader")
for epoch in range(2):
step=0
for data in test_loader:
imgs, target=data
writer.add_images("Epoch:{}".format(epoch),imgs,step)
step=step+1
writer.close()
7 卷积操作
import torch
import torch.nn.functional as F
input =torch.tensor([[1,2,0,3,1],
[0,1,2,3,2],
[1,2,1,0,0],
[5,2,3,1,1],
[2,1,0,1,1]])
kernel=torch.tensor([[1,2,1],
[0,1,0],
[2,1,0]])
input =torch.reshape(input,(1,1,5,5)) # size channel
kernel=torch.reshape(kernel,(1,1,3,3))
print(input.shape)
print(kernel.shape)
output=F.conv2d(input,kernel,stride=1，padding=1) # stride 步长 padding 填充的行列数
print(output)
8 卷积层
dataset = 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)
# 输出通道数和卷积核个数一样
def forward(self, x):
x = self.conv1(x)
return x
tudui = Tudui()
writer = SummaryWriter("../logs")
step = 0
for 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)) #-1代替size
writer.add_images("output", output, step)
step = step + 1
9 最大池化
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.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=False) // 不足池化数，是否保留池化
def forward(self, input):
output = self.maxpool1(input)
return output
tudui = Tudui()
writer = SummaryWriter("../logs_maxpool")
step = 0
for data in dataloader:
imgs, targets = data
writer.add_images("input", imgs, step)
output = tudui(imgs)
writer.add_images("output", output, step)
step = step + 1
writer.close()
10 非线性激化
input = torch.tensor([[1, -11],
[-3, 99]])
input = torch.reshape(input, (-1, 1, 2, 2))
print(input)
print(input.shape)
relu = ReLU()
print(relu(input))
dataset = torchvision.datasets.CIFAR10("dataset", False, torchvision.transforms.ToTensor()
, download=True)
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 output
tudui = Tudui()
writer = SummaryWriter("logs_relu")
step = 0
for data in dataloader:
imgs, targets = data
writer.add_images("input", imgs, global_step=step)
output = tudui(imgs)
writer.add_images("output", output, step)
step += 1
writer.close()
11 线性层
dataset = 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 output
tudui = Tudui()
for data in dataloader:
imgs, targets = data
print(imgs.shape)
output = torch.flatten(imgs)
print(output.shape)
output = tudui(output)
print(output.shape)
12 Sequential的使用
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 x
tudui = Tudui()
print(tudui)
input=torch.ones((64,3,32,32))
output=tudui(input)
print(output)
writer=SummaryWriter("log_seq")
# 网络结构图超好用
writer.add_graph(tudui,input)
writer.close()
13 损失函数
inputs = torch.tensor([1, 2, 3], dtype=torch.float32)
targets = torch.tensor([1, 2, 5], dtype=torch.float32)
inputs = torch.reshape(inputs, (1, 1, 1, 3))
targets = torch.reshape(targets, (1, 1, 1, 3))
#差的和
loss = L1Loss(reduction='sum')
result = loss(inputs, targets)
#方差的和/个数
loss_mse = nn.MSELoss()
result_mse = loss_mse(inputs, targets)
print(result)
print(result_mse)
x = torch.tensor([0.1, 0.2, 0.3])
y = torch.tensor([1])
x = torch.reshape(x, (1, 3))
loss_cross = nn.CrossEntropyLoss()
result_cross = loss_cross(x, y)
print(result_cross)
dataset=torchvision.datasets.CIFAR10("dataset",False,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 x
loss=nn.CrossEntropyLoss()
tudui = Tudui()
for data in dataloader:
imgs,targets=data
output=tudui(imgs)
print(output)
print(targets)
result_loss=loss(output,targets)
result_loss.backward()
print(result_loss)
14 优化器
dataset=torchvision.datasets.CIFAR10("dataset",False,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 x
loss=nn.CrossEntropyLoss()
tudui=Tudui()
optim=torch.optim.SGD(tudui.parameters(),lr=0.01)
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()
optim.step()
# print(result)
running_loss=running_loss+result_loss
print(running_loss)
15 现有网络模型的使用及修改
vgg16_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)
16 网络模型的保存及读取
保存
vgg16 = 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 x
tudui = Tudui()
torch.save(tudui, "tudui_method1.pth")
读取
#model1
model=torch.load("vgg16_method1.pth")
# print(model)
# model2
# model=torch.load("vgg16_method2.pth")
# print(model)
vgg16=torchvision.models.vgg16(pretrained=False).load_state_dict(torch.load("vgg16_method2.pth"))
# print(vgg16)
# 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=self.conv1(x)
return x
model_tudui=torch.load("tudui_method1.pth")
# print(model_tudui)
# 方法2只能load出字典，vgg16方法用不了
model_tudui2=torch.load("tudui_method2.pth")
print(model_tudui2)
17 完整的模型训练套路
import torch.nn
import torchvision
from tensorboardX import SummaryWriter
from torch import nn
from torch.utils.data import DataLoader
# from model import *
import time
device=torch.device("cuda")
train_data= torchvision.datasets.CIFAR10(root="dataset",train=True,transform= torchvision.transforms.ToTensor(), download=True)
test_data=torchvision.datasets.CIFAR10(root="dataset",train=False,transform=torchvision.transforms.ToTensor(),download=True)
train_data_size=len(train_data)
test_data_size=len(test_data)
print("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))
#加载数据集
train_dataloader=DataLoader(train_data,batch_size=64)
test_dataloader=DataLoader(test_data,batch_size=64)
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(1024,64),
nn.Linear(64,10)
)
def forward(self,x):
x=self.model(x)
return x
# 创建网络模型
tudui=Tudui()
# # 这种判断方法全部都要加
# if torch.cuda.is_available():
# tudui = tudui.cuda()
tudui=tudui.to(device)
# 损失函数
loss_fn=nn.CrossEntropyLoss()
loss_fn = loss_fn.to(device)
# 优化器
# learing_rate=0.01
learing_rate=1e-2
optimizer=torch.optim.SGD(tudui.parameters(),lr=learing_rate)
# 设置训练网络的一些参数
# 训练的次数
total_train_step=0
# 测试的次数
total_test_step=0
# 训练的轮数
epoch=10
# 添加tensorboard
writer=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=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)
# 测试开始
tudui.eval()
total_test_loss=0
#整体正确个数
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=total_test_loss+loss
accuracy=(outputs.argmax(1)==targets).sum()
total_accuracy=total_accuracy+accuracy
print("整体测试集上的loss:{}".format(total_test_loss))
print("整体测试集的正确率：{}".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=total_test_step+1
torch.save(tudui,"tudui_{}.pth".format(i))
print("模型已保存")
writer.close()
18 利用gpu训练
# 创建网络模型
tudui=Tudui()
# 这种判断方法全部都要加
if torch.cuda.is_available():
tudui = tudui.cuda()
# 损失函数
loss_fn=nn.CrossEntropyLoss()
loss_fn = loss_fn.cuda()
# 训练步骤开始
tudui.train()
for data in train_dataloader:
imgs,targets=data
imgs = imgs.cuda()
targets=targets.cuda()
利用gpu方式二：
device=torch.device("cuda")
# 创建网络模型
tudui=Tudui()
tudui=tudui.to(device)
loss_fn = loss_fn.to(device)
19 完整的模型验证套路
img_path="img_1.png"
img=Image.open(img_path)
print(img)
img = img.convert('RGB')
transform=torchvision.transforms.Compose([torchvision.transforms.Resize((32,32)),
torchvision.transforms.ToTensor()])
img=transform(img)
print(img.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(1024,64),
nn.Linear(64,10)
)
def forward(self,x):
x=self.model(x)
return x
# model = torch.load("tudui_2.pth",map_location=torch.device('cpu'))
model = torch.load("tudui_1.pth")
print(model)
image=torch.reshape(img,(1,3,32,32))
model.eval()
with torch.no_grad():
output=model(image)
print(output)
print(output.argmax(1))
参考视频：PyTorch深度学习快速入门教程（绝对通俗易懂！）【小土堆】