from torchtoolbox.transform import Cutout
=================================================================
设置学习率、BatchSize、epoch等参数,判断环境中是否存在GPU,如果没有则使用CPU。建议使用GPU,CPU太慢了。
设置全局参数
modellr = 1e-4
BATCH_SIZE = 16
EPOCHS = 300
DEVICE = torch.device(‘cuda’ if torch.cuda.is_available() else ‘cpu’)
===================================================================
数据处理比较简单,加入了Cutout、做了Resize和归一化。
数据预处理
transform = transforms.Compose([
transforms.Resize((224, 224)),
Cutout(),
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])
])
===============================================================
将数据集解压后放到data文件夹下面,如图:
然后我们在dataset文件夹下面新建 init.py和dataset.py,在datasets.py文件夹写入下面的代码:
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)
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。
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 dataset.dataset import SeedlingData)
dataset_train = SeedlingData(‘data/train’, transforms=transform, train=True)
dataset_test = SeedlingData(“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loss函数为nn.CrossEntropyLoss()。
-
设置模型为mobilenet_v3_large,预训练设置为true,num_classes设置为12。
-
优化器设置为adam。
-
学习率调整策略选择为余弦退火。
实例化模型并且移动到GPU
criterion = nn.CrossEntropyLoss()
model_ft = mobilenet_v3_large(pretrained=True)
print(model_ft)
num_ftrs = model_ft.classifier[3].in_features
model_ft.classifier[3] = nn.Linear(num_ftrs, 12)
model_ft.to(DEVICE)
print(model_ft)
选择简单暴力的Adam优化器,学习率调低
optimizer = optim.Adam(model_ft.parameters(), lr=modellr)
cosine_schedule = optim.lr_scheduler.CosineAnnealingLR(optimizer=optimizer,T_max=20,eta_min=1e-9)
====================================================================
定义训练过程
alpha=0.2
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 = data.to(device, non_blocking=True), target.to(device, non_blocking=True)
data, labels_a, labels_b, lam = mixup_data(data, target, alpha)
optimizer.zero_grad()
output = model(data)
loss = mixup_criterion(criterion, output, labels_a, labels_b, lam)
loss.backward()
optimizer.step()
lr = optimizer.state_dict()[‘param_groups’][0][‘lr’]
print_loss = loss.data.item()
sum_loss += print_loss
if (batch_idx + 1) % 10 == 0:
print(‘Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}\tLR:{:.9f}’.format(
epoch, (batch_idx + 1) * len(data), len(train_loader.dataset),
-
- (batch_idx + 1) / len(train_loader), loss.item(),lr))
ave_loss = sum_loss / len(train_loader)
print(‘epoch:{},loss:{}’.format(epoch, ave_loss))
ACC=0
验证过程
def val(model, device, test_loader):
global ACC
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))
if acc > ACC:
torch.save(model_ft, ‘model_’ + str(epoch) + ‘_’ + str(round(acc, 3)) + ‘.pth’)
ACC = acc
训练
for epoch in range(1, EPOCHS + 1):
train(model_ft, DEVICE, train_loader, optimizer, epoch)
cosine_schedule.step()
val(model_ft, DEVICE, test_loader)
运行结果:
=============================================================
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!!!!
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 PIL import Image
from torch.autograd import Variable
import os
classes = (‘Black-grass’, ‘Charlock’, ‘Cleavers’, ‘Common Chickweed’,
‘Common wheat’,‘Fat Hen’, ‘Loose Silky-bent’,
‘Maize’,‘Scentless Mayweed’,‘Shepherds Purse’,‘Small-flowered Cranesbill’,‘Sugar beet’)
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 使用自定义的Dataset读取图片
import torch.utils.data.distributed
import torchvision.transforms as transforms
from dataset.dataset import SeedlingData
from torch.autograd import Variable
classes = (‘Black-grass’, ‘Charlock’, ‘Cleavers’, ‘Common Chickweed’,
‘Common wheat’,‘Fat Hen’, ‘Loose Silky-bent’,
‘Maize’,‘Scentless Mayweed’,‘Shepherds Purse’,‘Small-flowered Cranesbill’,‘Sugar beet’)
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)
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)
img-hrC8haY2-1712484273720)]
[外链图片转存中…(img-IG4sEZs0-1712484273721)]
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)
![img](https://img-blog.csdnimg.cn/img_convert/a510ff6e4e62eb29a89e397013b433bc.jpeg)