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])
])
读取数据
====
使用Pytorch的默认方式读取数据。数据的目录如下图：
训练集，取了猫狗大战数据集中，猫狗图像各一万张，剩余的放到验证集中。
读取数据
dataset_train = datasets.ImageFolder('data/train', transform)
print(dataset_train.imgs)
对应文件夹的label
print(dataset_train.class_to_idx)
dataset_test = datasets.ImageFolder('data/val', transform_test)
对应文件夹的label
print(dataset_test.class_to_idx)
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efficientnetv2_s，由于没有Pytorch的预训练模型，我们只能从头开始训练。更改最后一层的全连接，将类别设置为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 = efficientnetv2_s()
num_ftrs = model.classifier.in_features
model.classifier = nn.Linear(num_ftrs, 2)
model.to(DEVICE)
选择简单暴力的Adam优化器，学习率调低
optimizer = optim.Adam(model.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, DEVICE, train_loader, optimizer, epoch)
val(model, DEVICE, test_loader)
torch.save(model, '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：
验证
==
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
from torch.autograd import Variable
import os
from PIL import Image
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：
其实在读取数据，也可以巧妙的用datasets.ImageFolder，下面我们就用datasets.ImageFolder实现对图片的预测。改一下test数据集的路径，在test文件夹外面再加一层文件件，取名为dataset，如下图所示：
然后修改读取图片的方式。代码如下：
import torch.utils.data.distributed
import torchvision.transforms as transforms
import torchvision.datasets as datasets
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 = datasets.ImageFolder('data/datatest', transform_test)
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][0], classes[pred.data.item()]))
index += 1
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
import torchvision.datasets as datasets
from torch.autograd import Variable
from model.EfficientNetv2 import efficientnetv2_s
设置全局参数
modellr = 1e-4
BATCH_SIZE = 32
EPOCHS = 50
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])
])
读取数据
dataset_train = datasets.ImageFolder('data/train', transform)
print(dataset_train.imgs)
对应文件夹的label
print(dataset_train.class_to_idx)
dataset_test = datasets.ImageFolder('data/val', transform_test)
对应文件夹的label
print(dataset_test.class_to_idx)
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 = efficientnetv2_s()
num_ftrs = model.classifier.in_features
model.classifier = nn.Linear(num_ftrs, 2)
model.to(DEVICE)
选择简单暴力的Adam优化器，学习率调低
optimizer = optim.Adam(model.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, DEVICE, train_loader, optimizer, epoch)
val(model, DEVICE, test_loader)
torch.save(model, 'model.pth')
test1.py
import torch.utils.data.distributed
最后
不知道你们用的什么环境，我一般都是用的Python3.6环境和pycharm解释器，没有软件，或者没有资料，没人解答问题，都可以免费领取（包括今天的代码），过几天我还会做个视频教程出来，有需要也可以领取~
给大家准备的学习资料包括但不限于：
Python 环境、pycharm编辑器/永久激活/翻译插件
python 零基础视频教程
Python 界面开发实战教程
Python 爬虫实战教程
Python 数据分析实战教程
python 游戏开发实战教程
Python 电子书100本
Python 学习路线规划
