pytorch和keras默认加载方式是ImageNet数据集格式,格式是
├─data
│ ├─val
│ │ ├─Black-grass
│ │ ├─Charlock
│ │ ├─Cleavers
│ │ ├─Common Chickweed
│ │ ├─Common wheat
│ │ ├─Fat Hen
│ │ ├─Loose Silky-bent
│ │ ├─Maize
│ │ ├─Scentless Mayweed
│ │ ├─Shepherds Purse
│ │ ├─Small-flowered Cranesbill
│ │ └─Sugar beet
│ └─train
│ ├─Black-grass
│ ├─Charlock
│ ├─Cleavers
│ ├─Common Chickweed
│ ├─Common wheat
│ ├─Fat Hen
│ ├─Loose Silky-bent
│ ├─Maize
│ ├─Scentless Mayweed
│ ├─Shepherds Purse
│ ├─Small-flowered Cranesbill
│ └─Sugar beet
新增格式转化脚本makedata.py,插入代码:
import glob
import os
import shutil
image_list=glob.glob(‘data1//.png’)
print(image_list)
file_dir=‘data’
if os.path.exists(file_dir):
print(‘true’)
#os.rmdir(file_dir)
shutil.rmtree(file_dir)#删除再建立
os.makedirs(file_dir)
else:
os.makedirs(file_dir)
from sklearn.model_selection import train_test_split
trainval_files, val_files = train_test_split(image_list, test_size=0.3, random_state=42)
train_dir=‘train’
val_dir=‘val’
train_root=os.path.join(file_dir,train_dir)
val_root=os.path.join(file_dir,val_dir)
for file in trainval_files:
file_class=file.replace(“\”,“/”).split(‘/’)[-2]
file_name=file.replace(“\”,“/”).split(‘/’)[-1]
file_class=os.path.join(train_root,file_class)
if not os.path.isdir(file_class):
os.makedirs(file_class)
shutil.copy(file, file_class + ‘/’ + file_name)
for file in val_files:
file_class=file.replace(“\”,“/”).split(‘/’)[-2]
file_name=file.replace(“\”,“/”).split(‘/’)[-1]
file_class=os.path.join(val_root,file_class)
if not os.path.isdir(file_class):
os.makedirs(file_class)
shutil.copy(file, file_class + ‘/’ + file_name)
===========================================================================
为了提高成绩我在代码中加入Cutout和Mixup这两种增强方式。实现这两种增强需要安装torchtoolbox。安装命令:
pip install torchtoolbox
Cutout实现,在transforms中。
from torchtoolbox.transform import Cutout
数据预处理
transform = transforms.Compose([
transforms.Resize((224, 224)),
Cutout()
])
Mixup实现,在train方法中。需要导入包:from torchtoolbox.tools import mixup_data, mixup_criterion
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()
print_loss = loss.data.item()
===================================================================
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
import torchvision.datasets as datasets
from models.vision_transformer import deit_tiny_patch16_224
from torchtoolbox.tools import mixup_data, mixup_criterion
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。在transforms.Normalize中写入上面求得的mean和std的值。
数据预处理
transform = transforms.Compose([
transforms.Resize((224, 224)),
Cutout(),
transforms.ToTensor(),
transforms.Normalize([0.3281186, 0.28937867, 0.20702125], [0.09407319, 0.09732835, 0.106712654])
])
transform_test = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize([0.3281186, 0.28937867, 0.20702125], [0.09407319, 0.09732835, 0.106712654])
])
===============================================================
使用pytorch默认读取数据的方式,然后将dataset_train.class_to_idx打印出来,预测的时候要用到。
读取数据
dataset_train = datasets.ImageFolder(‘data/train’, transform=transform)
dataset_test = datasets.ImageFolder(“data/val”, transform=transform_test)
print(dataset_train.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)
class_to_idx的结果:
{‘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}
===============================================================
-
设置loss函数为nn.CrossEntropyLoss()。
-
设置模型为deit_tiny_patch16_224,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。
模型文件来自:https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/vision_transformer.py
我在这个脚本的基础上做了更改,目前可以加载.pth的预训练模型,不能加载.npz的预训练模型。
实例化模型并且移动到GPU
criterion = nn.CrossEntropyLoss()
model_ft = deit_tiny_patch16_224(pretrained=True)
print(model_ft)
num_ftrs = model_ft.head.in_features
model_ft.head = nn.Linear(num_ftrs, 12,bias=True)
nn.init.xavier_uniform_(model_ft.head.weight)
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)
文末有福利领取哦~
👉一、Python所有方向的学习路线
Python所有方向的技术点做的整理,形成各个领域的知识点汇总,它的用处就在于,你可以按照上面的知识点去找对应的学习资源,保证自己学得较为全面。
👉二、Python必备开发工具
👉三、Python视频合集
观看零基础学习视频,看视频学习是最快捷也是最有效果的方式,跟着视频中老师的思路,从基础到深入,还是很容易入门的。
👉 四、实战案例
光学理论是没用的,要学会跟着一起敲,要动手实操,才能将自己的所学运用到实际当中去,这时候可以搞点实战案例来学习。(文末领读者福利)
👉五、Python练习题
检查学习结果。
👉六、面试资料
我们学习Python必然是为了找到高薪的工作,下面这些面试题是来自阿里、腾讯、字节等一线互联网大厂最新的面试资料,并且有阿里大佬给出了权威的解答,刷完这一套面试资料相信大家都能找到满意的工作。
👉因篇幅有限,仅展示部分资料,这份完整版的Python全套学习资料已经上传
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!