本小節使用torch搭建CNN模型，訓練和測試：
（1）定義模型超參數：輸出、疊代次數、批量大小、學習率。
（2）定義訓練資料，加餐部分是使用自己的資料集：（可參考：https://blog.csdn.net/u014365862/article/details/80506147）
（3）定義模型（定義卷積神經網絡）。
（4）定義損失函數，選用适合的損失函數。
（5）定義優化算法（SGD、Adam等）。
（6）儲存模型。
---------------------------------我是可愛的分割線---------------------------------
代碼部分：
# coding=utf-8
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
# 判定GPU是否存在
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
# 定義超參數
num_epochs = 5
num_classes = 10
batch_size = 100
learning_rate = 0.001
# 手寫體資料，（資料+标簽）
train_dataset = torchvision.datasets.MNIST(root='./data/',
train=True,
transform=transforms.ToTensor(),
download=True)
test_dataset = torchvision.datasets.MNIST(root='./data/',
train=False,
transform=transforms.ToTensor())
# # 建構資料管道， 使用自己的資料集請參考：https://blog.csdn.net/u014365862/article/details/80506147
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False)
# 定義自己的卷積神經網絡
class ConvNet(nn.Module):
def __init__(self, num_classes=10):
super(ConvNet, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(16),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.layer2 = nn.Sequential(
nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.layer3 = nn.Sequential(
nn.Conv2d(32, 64, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.fc = nn.Linear(3*3*64, num_classes)
def forward(self, x):
out = self.layer1(x)
out = self.layer2(out)
out = self.layer3(out)
out = out.reshape(out.size(0), -1)
out = self.fc(out)
return out
# 定義模型
model = ConvNet(num_classes).to(device)
# 定義損失函數+優化算法
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# 訓練模型
total_step = len(train_loader)
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
images = images.to(device)
labels = labels.to(device)
# 前向傳播+計算loss
outputs = model(images)
loss = criterion(outputs, labels)
# 後向傳播+調整參數
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 每100個batch列印一次資料
if (i+1) % 100 == 0:
print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
.format(epoch+1, num_epochs, i+1, total_step, loss.item()))
# 模型測試部分
# 測試階段不需要計算梯度，注意
model.eval() # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
with torch.no_grad():
correct = 0
total = 0
for images, labels in test_loader:
images = images.to(device)
labels = labels.to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))
# 儲存模型參數
torch.save(model.state_dict(), 'model.ckpt') 複制
加餐：在自己資料集上使用：
其中，train.txt中的資料格式：
gender/0male/0(2).jpg 1
gender/0male/0(3).jpeg 1
gender/0male/0(1).jpg 0
test.txt中的資料格式如下：
gender/0male/0(3).jpeg 1
gender/0male/0(1).jpg 0
gender/1female/1(6).jpg 1
代碼部分：
# coding=utf-8
import torch
import torch.nn as nn
import torchvision
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils
from PIL import Image
# 判定GPU是否存在
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
# 定義超參數
num_epochs = 5
num_classes = 10
batch_size = 16
learning_rate = 0.001
def default_loader(path):
# 注意要保證每個batch的tensor大小時候一樣的。
return Image.open(path).convert('RGB')
class MyDataset(Dataset):
def __init__(self, txt, transform=None, target_transform=None, loader=default_loader):
fh = open(txt, 'r')
imgs = []
for line in fh:
line = line.strip('\n')
# line = line.rstrip()
words = line.split(' ')
imgs.append((words[0],int(words[1])))
self.imgs = imgs
self.transform = transform
self.target_transform = target_transform
self.loader = loader
def __getitem__(self, index):
fn, label = self.imgs[index]
img = self.loader(fn)
if self.transform is not None:
img = self.transform(img)
return img,label
def __len__(self):
return len(self.imgs)
def get_loader(dataset='train.txt', crop_size=128, image_size=28, batch_size=2, mode='train', num_workers=1):
"""Build and return a data loader."""
transform = []
if mode == 'train':
transform.append(transforms.RandomHorizontalFlip())
transform.append(transforms.CenterCrop(crop_size))
transform.append(transforms.Resize(image_size))
transform.append(transforms.ToTensor())
transform.append(transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)))
transform = transforms.Compose(transform)
train_data=MyDataset(txt=dataset, transform=transform)
data_loader = DataLoader(dataset=train_data,
batch_size=batch_size,
shuffle=(mode=='train'),
num_workers=num_workers)
return data_loader
# 注意要保證每個batch的tensor大小時候一樣的。
# data_loader = DataLoader(train_data, batch_size=2,shuffle=True)
train_loader = get_loader('train.txt', batch_size=batch_size)
print(len(train_loader))
test_loader = get_loader('test.txt', batch_size=batch_size)
print(len(test_loader))
# 定義自己的卷積神經網絡
class ConvNet(nn.Module):
def __init__(self, num_classes=10):
super(ConvNet, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(3, 16, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(16),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.layer2 = nn.Sequential(
nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.layer3 = nn.Sequential(
nn.Conv2d(32, 64, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.fc = nn.Linear(3*3*64, num_classes)
def forward(self, x):
out = self.layer1(x)
out = self.layer2(out)
out = self.layer3(out)
out = out.reshape(out.size(0), -1)
out = self.fc(out)
return out
# 定義模型
model = ConvNet(num_classes).to(device)
# 定義損失函數+優化算法
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# 訓練模型
total_step = len(train_loader)
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
images = images.to(device)
labels = labels.to(device)
# 前向傳播+計算loss
outputs = model(images)
loss = criterion(outputs, labels)
# 後向傳播+調整參數
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 每100個batch列印一次資料
if (i+1) % 100 == 0:
print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
.format(epoch+1, num_epochs, i+1, total_step, loss.item()))
# 模型測試部分
# 測試階段不需要計算梯度，注意
model.eval() # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
with torch.no_grad():
correct = 0
total = 0
for images, labels in test_loader:
images = images.to(device)
labels = labels.to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))
# 儲存模型參數
torch.save(model.state_dict(), 'model.ckpt') 複制
總結：
本節使用CNN訓練MNIST識别、自己資料的識别。
上面加餐部分需要生成自己的txt檔案（資料+标簽），可以參考這個，自己以前調試用的：https://github.com/MachineLP/py_workSpace/blob/master/g_img_path.py
torch系列：
1. torch01：torch基礎
2. torch02：logistic regression--MNIST識别
3. torch03：linear_regression
4. torch04：全連接配接神經網絡--MNIST識别和自己資料集