kemna
parent
96406275f5
commit
d3e281700e
30
images.py
30
images.py
@ -1,30 +0,0 @@
|
||||
import os
|
||||
import requests
|
||||
import re
|
||||
import time
|
||||
|
||||
def image_set(save_path,word,epoch):
|
||||
q=0
|
||||
a=0
|
||||
while True:
|
||||
time.sleep(1)
|
||||
url="https://images.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=index&fr=&hs=0&xthttps=111110&sf=1&fmq=&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&word={}&oq={}&rsp=-1".format(word,word)
|
||||
headers={"User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET4.0C; .NET4.0E; rv:11.0) like Gecko"}
|
||||
response=requests.get(url,headers)
|
||||
html=response.text
|
||||
urls=re.findall('"objURL":"(.*?)"',html)
|
||||
for url in urls:
|
||||
print(a)
|
||||
response = requests.get(url,headers=headers)
|
||||
image = response.content
|
||||
with open(os.path.join(save_path,"{}.jpg".format(a))) as f:
|
||||
f.write(image)
|
||||
a=a+1
|
||||
q=q+20
|
||||
if(q/20)>=int(epoch):
|
||||
break
|
||||
if __name__=="__main__":
|
||||
save_path = "/kemna"
|
||||
word=input('输入你要的图片')
|
||||
epoch=input('下载几轮图片？')
|
||||
image_set(save_path,word,epoch)
|
||||
82
main.py
82
main.py
@ -1,49 +1,67 @@
|
||||
#导入模块
|
||||
import torch
|
||||
import torch.utils
|
||||
import torch.utils.data
|
||||
from torch.utils.data import DataLoader
|
||||
import torchvision
|
||||
from tqdm import tqdm
|
||||
import matplotlib
|
||||
|
||||
import random
|
||||
from enum import Enum
|
||||
import matplotlib as plt
|
||||
import torch.nn.functional as F
|
||||
device = 'cuda:0' if torch.cuda.is_available() else 'cpu'
|
||||
#使用torchvisiom.transform将图片转换为张量
|
||||
|
||||
transform =torchvision.transforms.Compose([torchvision.transforms.ToTensor(),torchvision.transforms.Normalize(mean=[0.5],std=[0.5])])
|
||||
#构建数据集（使用MINIST）
|
||||
path ='./MNIST'
|
||||
|
||||
EPOCH =10
|
||||
Batch_Size = 64
|
||||
#创建dataset
|
||||
class DataSet:
|
||||
def __init__(self,floder,data_name,label_name,transform=None):
|
||||
self.floder = floder
|
||||
self.transform = transform
|
||||
#创建dataloader
|
||||
class DataLoader:
|
||||
def __init__(self,type,batch_size,is_shuffle):
|
||||
data_name = 'train-images-idx3-ubyte.gz' if type=='train' else 't10k-images-idx3-ubyte.gz'
|
||||
label_name = 'train-labels-idx1-ubyte.gz' if type=='train' else 't10k-labels-idx1-ubyte.gz'
|
||||
|
||||
#下载数据集
|
||||
#下载训练集
|
||||
trainData=torchvision.datasets.MNIST(path,train=True,transform=transform,download=True)
|
||||
#下载测试集
|
||||
testData=torchvision.datasets.MNIST(path,train=False,transform=transform,download=False)
|
||||
Batch_Size = 300
|
||||
#shuffle=true是用来打乱数据集的
|
||||
train_Dataloader = DataLoader(trainData,batch_size = Batch_Size,shuffle = True)
|
||||
test_DataLoader = DataLoader(testData,batch_size=Batch_Size,shuffle=False)
|
||||
train_Dataloader = DataLoader(train,batch_size = Batch_Size,shuffle = True)
|
||||
test_DataLoader = DataLoader(test,batch_size=Batch_Size,shuffle=False)
|
||||
class Net(torch.nn.Module):
|
||||
#构造函数
|
||||
def __init__(self):
|
||||
#继承父类
|
||||
super(Net,self).__init__()
|
||||
self.conv1=torch.nn.Sequential(
|
||||
#torch.nn.Conv2d(in_channels,out_channels,卷积核大小,步长,填充)
|
||||
torch.nn.Conv2d(1,10,kernel_size=5),
|
||||
#torch.nn.RelU()激活函数
|
||||
self.conv1 = torch.nn.Sequential(
|
||||
torch.nn.Conv2d(1, 10, kernel_size=5),
|
||||
torch.nn.ReLU(),
|
||||
torch.nn.MaxPool2d(kernel_size=2)
|
||||
torch.nn.MaxPool2d(kernel_size=2),
|
||||
)
|
||||
self.fc=torch.nn.Sequential(
|
||||
torch.nn.Linear(64,10)
|
||||
self.conv2 = torch.nn.Sequential(
|
||||
torch.nn.Conv2d(10, 20, kernel_size=5),
|
||||
torch.nn.ReLU(),
|
||||
torch.nn.MaxPool2d(kernel_size=2),
|
||||
)
|
||||
self.fc = torch.nn.Sequential(
|
||||
torch.nn.Linear(320, 50),
|
||||
torch.nn.Linear(50, 10),
|
||||
)
|
||||
|
||||
def forward(self,x):
|
||||
x=self.conv1(x)
|
||||
x=x.view(Batch_Size,-1)
|
||||
x=self.fc(x)
|
||||
batch_size = x.size(0)
|
||||
x = self.conv1(x) # 一层卷积层,一层池化层,一层激活层(图是先卷积后激活再池化，差别不大)
|
||||
x = self.conv2(x) # 再来一次
|
||||
x = x.view(batch_size, -1) # flatten 变成全连接网络需要的输入 (batch, 20,4,4) ==> (batch,320), -1 此处自动算出的是320
|
||||
x = self.fc(x)
|
||||
return x
|
||||
|
||||
model = Net()
|
||||
|
||||
model = Net().to(device)
|
||||
#使用交叉墒损失做损失函数
|
||||
sunshi = torch.nn.CrossEntropyLoss()
|
||||
#优化器：随机梯度下降
|
||||
@ -55,27 +73,28 @@ def train(epoch):
|
||||
running_total=0
|
||||
running_correct = 0
|
||||
for batch_idx,data in enumerate(train_Dataloader,0):
|
||||
inputs,target = data
|
||||
inputs, target = data
|
||||
inputs = inputs.to(device)
|
||||
target = target.to(device)
|
||||
#梯度归零
|
||||
optimizer.zero_grad()
|
||||
|
||||
outputs = model(inputs)
|
||||
loss = criterion(outputs,target)
|
||||
loss = sunshi(outputs,target)
|
||||
#反向传播
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
|
||||
running_loss += loss.item()
|
||||
#准确率
|
||||
predicted = torch.max(outputs.data,dim=1)
|
||||
_,predicted = torch.max(outputs,dim=1)
|
||||
running_total+=inputs.shape[0]
|
||||
running_correct +=(predicted == target).sum().item()
|
||||
running_correct += (predicted == target).sum().item()
|
||||
print('[%d,%5d]:loss:%.3f,acc:%.2f',epoch+1,batch_idx+1,running_loss,running_correct/running_total)
|
||||
#测试
|
||||
def test():
|
||||
correct =0
|
||||
total = 0
|
||||
#
|
||||
with torch.no_grad():
|
||||
for data in test_DataLoader:
|
||||
images,labels = data
|
||||
@ -87,14 +106,17 @@ def test():
|
||||
print('[%d/%d]Accuracy: %.lf %%', epoch+1,EPOCH,accuracy)
|
||||
return accuracy
|
||||
|
||||
#
|
||||
EPOCH =10
|
||||
|
||||
if __name__ ==' __main__':
|
||||
|
||||
if __name__ =='__main__':
|
||||
acc_list_test =[]
|
||||
for epoch in range(EPOCH):
|
||||
train(epoch)
|
||||
#每训练10轮测试一次
|
||||
if epoch % 10 ==9:
|
||||
acc_test = test()
|
||||
acc_list_test.append(acc_test)
|
||||
acc_list_test.append(acc_test)
|
||||
plt.plot(acc_list_test)
|
||||
plt.xlabel('Epoch')
|
||||
plt.ylabel('Accuracy On TestSet')
|
||||
plt.show()
|
||||
103
test.py
103
test.py
@ -1,103 +0,0 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import torch.optim as optim
|
||||
from torchvision import datasets, transforms
|
||||
from torch.utils.data import DataLoader
|
||||
|
||||
# 定义超参数
|
||||
BATCH_SIZE =64 # 每批处理的数据
|
||||
DEVICE = torch.device('cpu') # 用 cpu 还是 gpu
|
||||
EPOCHS = 300 # 训练次数
|
||||
|
||||
# 构建 pipeline，对图像做处理
|
||||
pipeline = transforms.Compose([
|
||||
transforms.ToTensor(), # 将图片转化成 tensor
|
||||
transforms.Normalize((0.1307,), (0.3081,)) # 正则化，降低模型复杂度
|
||||
])
|
||||
|
||||
# 下载数据集
|
||||
train_set = datasets.MNIST('data', train=True, download=True, transform=pipeline)
|
||||
test_set = datasets.MNIST('data', train=False, download=False, transform=pipeline)
|
||||
# 加载数据
|
||||
train_loader = DataLoader(train_set, batch_size=BATCH_SIZE, shuffle=True)
|
||||
test_loader = DataLoader(test_set, batch_size=BATCH_SIZE, shuffle=True)
|
||||
|
||||
# 构建模型
|
||||
class Dight(nn.Module):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.conv1 = nn.Conv2d(1, 10, 5)
|
||||
self.conv2 = nn.Conv2d(10, 20, 3)
|
||||
self.fc1 = nn.Linear(20 * 10 * 10, 500)
|
||||
self.fc2 = nn.Linear(500, 10)
|
||||
|
||||
def forward(self, x):
|
||||
input_size = x.size(0) # batch_size ×1×28×28
|
||||
x = self.conv1(x) # s\输出 batch*1*28*28,输出×10×24×24(28-5+1=24)
|
||||
x = F.relu(x) # 保持 shape 不变
|
||||
x = F.max_pool2d(x, 2, 2) # 输入：10×24×24 输出：batch×10×12×12
|
||||
x = self.conv2(x) # 10*12*12 20*10*10
|
||||
x = F.relu(x)
|
||||
x = x.view(input_size, -1) # 拉平，自动计算维度 20×10×10=2000
|
||||
x = self.fc1(x) # 2000 500
|
||||
x = F.relu(x)
|
||||
x = self.fc2(x)
|
||||
output = F.log_softmax(x, dim=1) # 数字概率找最大的
|
||||
return output
|
||||
|
||||
# 定义优化器
|
||||
model = Dight().to(DEVICE)
|
||||
optimizer = optim.Adam(model.parameters())
|
||||
|
||||
# 定义训练方法
|
||||
def train_model(model, device, train_loader, optimizer, epoch):
|
||||
# 模型训练
|
||||
model.train()
|
||||
for batch_index, (data, target) in enumerate(train_loader):
|
||||
# 部署到 GPU
|
||||
data = data.to(device)
|
||||
target = target.to(device)
|
||||
# 梯度初始化为 0
|
||||
optimizer.zero_grad()
|
||||
# 预测结果
|
||||
output = model(data)
|
||||
# 计算损失
|
||||
loss = F.cross_entropy(output, target)
|
||||
# 损失函数
|
||||
loss.backward()
|
||||
# 反向传播
|
||||
optimizer.step()
|
||||
# 参数优化
|
||||
optimizer.step()
|
||||
if batch_index % 3000 == 0:
|
||||
print('Traib Epoch : {} \t Loss : {:.6f}'.format(epoch,loss.item()))
|
||||
# 定义测试方法
|
||||
def test_model(model, device, test_loader):
|
||||
# 模型验证
|
||||
model.eval()
|
||||
# 正确率
|
||||
correct = 0.0
|
||||
# 测试损失
|
||||
test_loss = 0.0
|
||||
with torch.no_grad():
|
||||
for data, target in test_loader:
|
||||
# 部署到 device 上
|
||||
data = data.to(device)
|
||||
target = target.to(device)
|
||||
# 测试数据
|
||||
output = model(data)
|
||||
# 计算测试损失
|
||||
test_loss += F.cross_entropy(output, target).item()
|
||||
# 获取预测结果
|
||||
_, pred = output.max(1, keepdim=True)
|
||||
# 累计正确率
|
||||
correct += (pred == target.view_as(pred)).sum().item()
|
||||
test_loss /= len(test_loader.dataset)
|
||||
print('Test - Average loss : (:.4f),Accuracy:{:.3f}\n'.format(
|
||||
test_loss, 100.0 * correct / len(test_loader.dataset)))
|
||||
|
||||
# 调用，输出
|
||||
for epoch in range(1, EPOCHS + 1):
|
||||
train_model(model, DEVICE, train_loader, optimizer, epoch)
|
||||
test_model(model, DEVICE, test_loader)
|
||||
BIN
yolo11n.pt
BIN
yolo11n.pt
Binary file not shown.
BIN
yolov8n.pt
BIN
yolov8n.pt
Binary file not shown.
BIN
yolov8x.pt
BIN
yolov8x.pt
Binary file not shown.
103
啊.py
103
啊.py
@ -1,103 +0,0 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import torch.optim as optim
|
||||
from torchvision import datasets, transforms
|
||||
from torch.utils.data import DataLoader
|
||||
|
||||
# 定义超参数
|
||||
BATCH_SIZE =64 # 每批处理的数据
|
||||
DEVICE = torch.device('cpu') # 用 cpu 还是 gpu
|
||||
EPOCHS = 300 # 训练次数
|
||||
|
||||
# 构建 pipeline，对图像做处理
|
||||
pipeline = transforms.Compose([
|
||||
transforms.ToTensor(), # 将图片转化成 tensor
|
||||
transforms.Normalize((0.1307,), (0.3081,)) # 正则化，降低模型复杂度
|
||||
])
|
||||
|
||||
# 下载数据集
|
||||
train_set = datasets.MNIST('data', train=True, download=True, transform=pipeline)
|
||||
test_set = datasets.MNIST('data', train=False, download=False, transform=pipeline)
|
||||
# 加载数据
|
||||
train_loader = DataLoader(train_set, batch_size=BATCH_SIZE, shuffle=True)
|
||||
test_loader = DataLoader(test_set, batch_size=BATCH_SIZE, shuffle=True)
|
||||
|
||||
# 构建模型
|
||||
class Dight(nn.Module):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.conv1 = nn.Conv2d(1, 10, 5)
|
||||
self.conv2 = nn.Conv2d(10, 20, 3)
|
||||
self.fc1 = nn.Linear(20 * 10 * 10, 500)
|
||||
self.fc2 = nn.Linear(500, 10)
|
||||
|
||||
def forward(self, x):
|
||||
input_size = x.size(0) # batch_size ×1×28×28
|
||||
x = self.conv1(x) # s\输出 batch*1*28*28,输出×10×24×24(28-5+1=24)
|
||||
x = F.relu(x) # 保持 shape 不变
|
||||
x = F.max_pool2d(x, 2, 2) # 输入：10×24×24 输出：batch×10×12×12
|
||||
x = self.conv2(x) # 10*12*12 20*10*10
|
||||
x = F.relu(x)
|
||||
x = x.view(input_size, -1) # 拉平，自动计算维度 20×10×10=2000
|
||||
x = self.fc1(x) # 2000 500
|
||||
x = F.relu(x)
|
||||
x = self.fc2(x)
|
||||
output = F.log_softmax(x, dim=1) # 数字概率找最大的
|
||||
return output
|
||||
|
||||
# 定义优化器
|
||||
model = Dight().to(DEVICE)
|
||||
optimizer = optim.Adam(model.parameters())
|
||||
|
||||
# 定义训练方法
|
||||
def train_model(model, device, train_loader, optimizer, epoch):
|
||||
# 模型训练
|
||||
model.train()
|
||||
for batch_index, (data, target) in enumerate(train_loader):
|
||||
# 部署到 GPU
|
||||
data = data.to(device)
|
||||
target = target.to(device)
|
||||
# 梯度初始化为 0
|
||||
optimizer.zero_grad()
|
||||
# 预测结果
|
||||
output = model(data)
|
||||
# 计算损失
|
||||
loss = F.cross_entropy(output, target)
|
||||
# 损失函数
|
||||
loss.backward()
|
||||
# 反向传播
|
||||
optimizer.step()
|
||||
# 参数优化
|
||||
optimizer.step()
|
||||
if batch_index % 3000 == 0:
|
||||
print('Traib Epoch : {} \t Loss : {:.6f}'.format(epoch,loss.item()))
|
||||
# 定义测试方法
|
||||
def test_model(model, device, test_loader):
|
||||
# 模型验证
|
||||
model.eval()
|
||||
# 正确率
|
||||
correct = 0.0
|
||||
# 测试损失
|
||||
test_loss = 0.0
|
||||
with torch.no_grad():
|
||||
for data, target in test_loader:
|
||||
# 部署到 device 上
|
||||
data = data.to(device)
|
||||
target = target.to(device)
|
||||
# 测试数据
|
||||
output = model(data)
|
||||
# 计算测试损失
|
||||
test_loss += F.cross_entropy(output, target).item()
|
||||
# 获取预测结果
|
||||
_, pred = output.max(1, keepdim=True)
|
||||
# 累计正确率
|
||||
correct += (pred == target.view_as(pred)).sum().item()
|
||||
test_loss /= len(test_loader.dataset)
|
||||
print('Test - Average loss : (:.4f),Accuracy:{:.3f}\n'.format(
|
||||
test_loss, 100.0 * correct / len(test_loader.dataset)))
|
||||
|
||||
# 调用，输出
|
||||
for epoch in range(1, EPOCHS + 1):
|
||||
train_model(model, DEVICE, train_loader, optimizer, epoch)
|
||||
test_model(model, DEVICE, test_loader)
|
||||
Loading…
x
Reference in New Issue
Block a user