label = 1 if ‘dog’ in img_path.split(‘/’)[-1] else 0
data = Image.open(img_path)
data = self.transforms(data)
return data, label
def len(self):
return len(self.imgs)
然后我们在train.py调用DogCat读取数据
dataset_train = DogCat(‘data/train’, transforms=transform, train=True)
dataset_test = DogCat(“data/train”, transforms=transform_test, train=False)
读取数据
print(dataset_train.imgs)
导入数据
train_loader = torch.utils.data.DataLoader(dataset_train, batch_size=BATCH_SIZE, shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset_test, batch_size=BATCH_SIZE, shuffle=False)
设置模型
====
使用CrossEntropyLoss作为loss，模型采用alexnet，选用预训练模型。更改全连接层，将最后一层类别设置为2，然后将模型放到DEVICE。优化器选用Adam。
实例化模型并且移动到GPU
criterion = nn.CrossEntropyLoss()
model_ft = alexnet(pretrained=True)
model_ft.classifier = nn.Sequential(
nn.Dropout(),
nn.Linear(256 * 6 * 6, 4096),
nn.ReLU(inplace=True),
nn.Dropout(),
nn.Linear(4096, 4096),
nn.ReLU(inplace=True),
nn.Linear(4096, 2),
)
model_ft.to(DEVICE)
选择简单暴力的Adam优化器，学习率调低
optimizer = optim.Adam(model_ft.parameters(), lr=modellr)
def adjust_learning_rate(optimizer, epoch):
“”“Sets the learning rate to the initial LR decayed by 10 every 30 epochs”“”
modellrnew = modellr * (0.1 ** (epoch // 50))
print(“lr:”, modellrnew)
for param_group in optimizer.param_groups:
param_group[‘lr’] = modellrnew
设置训练和验证
=======
定义训练过程
def train(model, device, train_loader, optimizer, epoch):
model.train()
sum_loss = 0
total_num = len(train_loader.dataset)
print(total_num, len(train_loader))
for batch_idx, (data, target) in enumerate(train_loader):
data, target = Variable(data).to(device), Variable(target).to(device)
output = model(data)
loss = criterion(output, target)
optimizer.zero_grad()
loss.backward()
optimizer.step()
print_loss = loss.data.item()
sum_loss += print_loss
if (batch_idx + 1) % 50 == 0:
print(‘Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}’.format(
epoch, (batch_idx + 1) * len(data), len(train_loader.dataset),
-
- (batch_idx + 1) / len(train_loader), loss.item()))
ave_loss = sum_loss / len(train_loader)
print(‘epoch:{},loss:{}’.format(epoch, ave_loss))
验证过程
def val(model, device, test_loader):
model.eval()
test_loss = 0
correct = 0
total_num = len(test_loader.dataset)
print(total_num, len(test_loader))
with torch.no_grad():
for data, target in test_loader:
data, target = Variable(data).to(device), Variable(target).to(device)
output = model(data)
loss = criterion(output, target)
_, pred = torch.max(output.data, 1)
correct += torch.sum(pred == target)
print_loss = loss.data.item()
test_loss += print_loss
correct = correct.data.item()
acc = correct / total_num
avgloss = test_loss / len(test_loader)
print(‘\nVal set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n’.format(
avgloss, correct, len(test_loader.dataset), 100 * acc))
训练
for epoch in range(1, EPOCHS + 1):
adjust_learning_rate(optimizer, epoch)
train(model_ft, DEVICE, train_loader, optimizer, epoch)
val(model_ft, DEVICE, test_loader)
torch.save(model_ft, ‘model.pth’)
完成上面的代码后就可以开始训练，点击run开始训练，如下图：
由于我们使用了预训练模型，所以收敛速度很快。
测试
==
我介绍两种常用的测试方式，第一种是通用的，通过自己手动加载数据集然后做预测，具体操作如下：
测试集存放的目录如下图：
第一步 定义类别，这个类别的顺序和训练时的类别顺序对应，一定不要改变顺序！！！！我们在训练时，cat类别是0，dog类别是1，所以我定义classes为(cat,dog)。
第二步 定义transforms，transforms和验证集的transforms一样即可，别做数据增强。
第三步 加载model，并将模型放在DEVICE里，
第四步 读取图片并预测图片的类别，在这里注意，读取图片用PIL库的Image。不要用cv2，transforms不支持。
import torch.utils.data.distributed
import torchvision.transforms as transforms
import torchvision.datasets as datasets
from PIL import Image
from torch.autograd import Variable
import os
classes = (‘cat’, ‘dog’)
transform_test = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
])
DEVICE = torch.device(“cuda:0” if torch.cuda.is_available() else “cpu”)
model = torch.load(“model.pth”)
model.eval()
model.to(DEVICE)
path=‘data/test/’
testList=os.listdir(path)
for file in testList:
img=Image.open(path+file)
img=transform_test(img)
img.unsqueeze_(0)
img = Variable(img).to(DEVICE)
out=model(img)
Predict
_, pred = torch.max(out.data, 1)
print(‘Image Name:{},predict:{}’.format(file,classes[pred.data.item()]))
运行结果：
第二种使用我们刚才定义的dataset.py加载测试集。代码如下：
import torch.utils.data.distributed
import torchvision.transforms as transforms
from dataset.dataset import DogCat
from torch.autograd import Variable
classes = (‘cat’, ‘dog’)
transform_test = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
])
DEVICE = torch.device(“cuda:0” if torch.cuda.is_available() else “cpu”)
model = torch.load(“model.pth”)
model.eval()
model.to(DEVICE)
dataset_test =DogCat(‘data/test/’, transform_test,test=True)
print(len(dataset_test))
对应文件夹的label
for index in range(len(dataset_test)):
item = dataset_test[index]
img, label = item
img.unsqueeze_(0)
data = Variable(img).to(DEVICE)
output = model(data)
_, pred = torch.max(output.data, 1)
print(‘Image Name:{},predict:{}’.format(dataset_test.imgs[index], classes[pred.data.item()]))
index += 1
运行结果：
完整代码
==========================================================================================================================================================================================================================
train.py
import torch.optim as optim
import torch
import torch.nn as nn
import torch.nn.parallel
import torch.optim
import torch.utils.data
import torch.utils.data.distributed
import torchvision.transforms as transforms
from dataset.dataset import DogCat
from torch.autograd import Variable
from torchvision.models import alexnet
设置全局参数
modellr = 1e-4
BATCH_SIZE = 32
EPOCHS = 10
DEVICE = torch.device(‘cuda’ if torch.cuda.is_available() else ‘cpu’)
数据预处理
transform = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
])
transform_test = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
])
dataset_train = DogCat(‘data/train’, transforms=transform, train=True)
dataset_test = DogCat(“data/train”, transforms=transform_test, train=False)
读取数据
print(dataset_train.imgs)
导入数据
train_loader = torch.utils.data.DataLoader(dataset_train, batch_size=BATCH_SIZE, shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset_test, batch_size=BATCH_SIZE, shuffle=False)
实例化模型并且移动到GPU
criterion = nn.CrossEntropyLoss()
model_ft = alexnet(pretrained=True)
model_ft.classifier = nn.Sequential(
nn.Dropout(),
nn.Linear(256 * 6 * 6, 4096),
nn.ReLU(inplace=True),
nn.Dropout(),
nn.Linear(4096, 4096),
nn.ReLU(inplace=True),
nn.Linear(4096, 2),
)
model_ft.to(DEVICE)
选择简单暴力的Adam优化器，学习率调低
optimizer = optim.Adam(model_ft.parameters(), lr=modellr)
def adjust_learning_rate(optimizer, epoch):
“”“Sets the learning rate to the initial LR decayed by 10 every 30 epochs”“”
modellrnew = modellr * (0.1 ** (epoch // 50))
print(“lr:”, modellrnew)
for param_group in optimizer.param_groups:
param_group[‘lr’] = modellrnew
定义训练过程
def train(model, device, train_loader, optimizer, epoch):
model.train()
sum_loss = 0
total_num = len(train_loader.dataset)
print(total_num, len(train_loader))
for batch_idx, (data, target) in enumerate(train_loader):
data, target = Variable(data).to(device), Variable(target).to(device)
output = model(data)
loss = criterion(output, target)
optimizer.zero_grad()
loss.backward()
optimizer.step()
print_loss = loss.data.item()
sum_loss += print_loss
if (batch_idx + 1) % 50 == 0:
print(‘Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}’.format(
epoch, (batch_idx + 1) * len(data), len(train_loader.dataset),
-
- (batch_idx + 1) / len(train_loader), loss.item()))
ave_loss = sum_loss / len(train_loader)
print(‘epoch:{},loss:{}’.format(epoch, ave_loss))
验证过程
def val(model, device, test_loader):
model.eval()
test_loss = 0
correct = 0
total_num = len(test_loader.dataset)
print(total_num, len(test_loader))
with torch.no_grad():
for data, target in test_loader:
data, target = Variable(data).to(device), Variable(target).to(device)
output = model(data)
loss = criterion(output, target)
_, pred = torch.max(output.data, 1)
correct += torch.sum(pred == target)
print_loss = loss.data.item()
test_loss += print_loss
correct = correct.data.item()
acc = correct / total_num
avgloss = test_loss / len(test_loader)
print(‘\nVal set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n’.format(
avgloss, correct, len(test_loader.dataset), 100 * acc))
训练
for epoch in range(1, EPOCHS + 1):
adjust_learning_rate(optimizer, epoch)
train(model_ft, DEVICE, train_loader, optimizer, epoch)
val(model_ft, DEVICE, test_loader)
torch.save(model_ft, ‘model.pth’)
test1.py
import torch.utils.data.distributed
import torchvision.transforms as transforms
import torchvision.datasets as datasets
from PIL import Image
from torch.autograd import Variable
import os
classes = (‘cat’, ‘dog’)
transform_test = transforms.Compose([
自我介绍一下，小编13年上海交大毕业，曾经在小公司待过，也去过华为、OPPO等大厂，18年进入阿里一直到现在。
深知大多数Python工程师，想要提升技能，往往是自己摸索成长或者是报班学习，但对于培训机构动则几千的学费，着实压力不小。自己不成体系的自学效果低效又漫长，而且极易碰到天花板技术停滞不前！
因此收集整理了一份《2024年Python开发全套学习资料》，初衷也很简单，就是希望能够帮助到想自学提升又不知道该从何学起的朋友，同时减轻大家的负担。
既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，基本涵盖了95%以上前端开发知识点，真正体系化！
由于文件比较大，这里只是将部分目录大纲截图出来，每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频，并且后续会持续更新
如果你觉得这些内容对你有帮助，可以扫码获取！！！（备注Python）
**
深知大多数Python工程师，想要提升技能，往往是自己摸索成长或者是报班学习，但对于培训机构动则几千的学费，着实压力不小。自己不成体系的自学效果低效又漫长，而且极易碰到天花板技术停滞不前！
因此收集整理了一份《2024年Python开发全套学习资料》，初衷也很简单，就是希望能够帮助到想自学提升又不知道该从何学起的朋友，同时减轻大家的负担。
[外链图片转存中…(img-YarOtCUd-1712969563773)]
[外链图片转存中…(img-Zer6I1hG-1712969563773)]
[外链图片转存中…(img-66cqlCb8-1712969563774)]
[外链图片转存中…(img-x7lT7JXe-1712969563774)]
既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，基本涵盖了95%以上前端开发知识点，真正体系化！
由于文件比较大，这里只是将部分目录大纲截图出来，每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频，并且后续会持续更新
如果你觉得这些内容对你有帮助，可以扫码获取！！！（备注Python）
560
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
