pip install pretrainedmodels
安装完成后,导入到项目中。
import torch.optim as optim
import torch
import torch.nn as nn
import torch.nn.parallel
import torch.utils.data
import torch.utils.data.distributed
import torchvision.transforms as transforms
from dataset.dataset import SeedlingData
from torch.autograd import Variable
import pretrainedmodels
设置使用GPU,设置学习率、BatchSize、epoch等参数
设置全局参数
modellr = 1e-4
BATCH_SIZE = 16
EPOCHS = 50
DEVICE = torch.device(‘cuda’ if torch.cuda.is_available() else ‘cpu’)
数据处理比较简单,没有做复杂的尝试,有兴趣的可以加入一些处理。
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])
])
然后我们在dataset文件夹下面新建 init.py和dataset.py,在mydatasets.py文件夹写入下面的代码:
说一下代码的核心逻辑。
第一步 建立字典,定义类别对应的ID,用数字代替类别。
第二步 在__init__里面编写获取图片路径的方法。测试集只有一层路径直接读取,训练集在train文件夹下面是类别文件夹,先获取到类别,再获取到具体的图片路径。然后使用sklearn中切分数据集的方法,按照7:3的比例切分训练集和验证集。
第三步 在__getitem__方法中定义读取单个图片和类别的方法,由于图像中有位深度32位的,所以我在读取图像的时候做了转换。
代码如下:
coding:utf8
import os
from PIL import Image
from torch.utils import data
from torchvision import transforms as T
from sklearn.model_selection import train_test_split
Labels = {‘Black-grass’: 0, ‘Charlock’: 1, ‘Cleavers’: 2, ‘Common Chickweed’: 3,
‘Common wheat’: 4, ‘Fat Hen’: 5, ‘Loose Silky-bent’: 6, ‘Maize’: 7, ‘Scentless Mayweed’: 8,
‘Shepherds Purse’: 9, ‘Small-flowered Cranesbill’: 10, ‘Sugar beet’: 11}
class SeedlingData (data.Dataset):
def init(self, root, transforms=None, train=True, test=False):
“”"
主要目标: 获取所有图片的地址,并根据训练,验证,测试划分数据
“”"
self.test = test
self.transforms = transforms
if self.test:
imgs = [os.path.join(root, img) for img in os.listdir(root)]
self.imgs = imgs
else:
imgs_labels = [os.path.join(root, img) for img in os.listdir(root)]
imgs = []
for imglable in imgs_labels:
for imgname in os.listdir(imglable):
imgpath = os.path.join(imglable, imgname)
imgs.append(imgpath)
trainval_files, val_files = train_test_split(imgs, test_size=0.3, random_state=42)
if train:
self.imgs = trainval_files
else:
self.imgs = val_files
def getitem(self, index):
“”"
一次返回一张图片的数据
“”"
img_path = self.imgs[index]
img_path=img_path.replace(“\”,‘/’)
if self.test:
label = -1
else:
labelname = img_path.split(‘/’)[-2]
label = Labels[labelname]
data = Image.open(img_path).convert(‘RGB’)
data = self.transforms(data)
return data, label
def len(self):
return len(self.imgs)
然后我们在train.py调用SeedlingData读取数据 ,记着导入刚才写的dataset.py(from mydatasets import SeedlingData)
读取数据
dataset_train = SeedlingData(‘data/train’, transforms=transform, train=True)
dataset_test = SeedlingData(“data/train”, transforms=transform_test, train=False)
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loss函数为nn.CrossEntropyLoss()。
-
设置模型为se_resnet50,修改最后一层全连接输出改为12。
-
优化器设置为adamw。
实例化模型并且移动到GPU
criterion = nn.CrossEntropyLoss()
model_ft = pretrainedmodels.dict[‘se_resnet50’](num_classes=1000, pretrained=‘imagenet’)
model_ft.fc = classifier = nn.Sequential(
nn.Linear(2048, 512),
nn.LeakyReLU(True),
nn.Dropout(0.5),
nn.Linear(512, 12),
)
model_ft.to(DEVICE)
选择简单暴力的Adam优化器,学习率调低
optimizer = optim.AdamW(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) % 10 == 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’)
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:
最后
🍅 硬核资料:关注即可领取PPT模板、简历模板、行业经典书籍PDF。
🍅 技术互助:技术群大佬指点迷津,你的问题可能不是问题,求资源在群里喊一声。
🍅 面试题库:由技术群里的小伙伴们共同投稿,热乎的大厂面试真题,持续更新中。
🍅 知识体系:含编程语言、算法、大数据生态圈组件(Mysql、Hive、Spark、Flink)、数据仓库、Python、前端等等。
网上学习资料一大堆,但如果学到的知识不成体系,遇到问题时只是浅尝辄止,不再深入研究,那么很难做到真正的技术提升。
一个人可以走的很快,但一群人才能走的更远!不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人,都欢迎加入我们的的圈子(技术交流、学习资源、职场吐槽、大厂内推、面试辅导),让我们一起学习成长!