【图像分类】实战——使用VGG16实现对植物幼苗的分类（pytroch

nn.ReLU(True),

nn.Dropout(),

nn.Linear(4096, 4096),

nn.ReLU(True),

nn.Dropout(),

nn.Linear(4096, 12),

)

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) % 10 == 0:

print(‘Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}’.format(

epoch, (batch_idx + 1) * len(data), len(train_loader.dataset),

100. • (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’)

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！！！！

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()]))

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)

dataset_test =SeedlingData(‘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

完整代码

====

train.py

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

from torchvision.models import vgg16

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 = 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)

实例化模型并且移动到GPU

criterion = nn.CrossEntropyLoss()

model_ft = vgg16(pretrained=True)

model_ft.classifier = classifier = nn.Sequential(

nn.Linear(512 * 7 * 7, 4096),

nn.ReLU(True),

nn.Dropout(),

nn.Linear(4096, 4096),

nn.ReLU(True),

nn.Dropout(),

nn.Linear(4096, 12),

)

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) % 10 == 0:

print(‘Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}’.format(

epoch, (batch_idx + 1) * len(data), len(train_loader.dataset),

100. • (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’)

vgg实现植物幼苗分类.rar-深度学习文档类资源-CSDN下载

[

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。

需要这份系统化学习资料的朋友，可以戳这里无偿获取

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！