pytorch之inception_v3的实现案例


Posted in Python onJanuary 06, 2020

如下所示:

from __future__ import print_function 
from __future__ import division
import torch
import torch.nn as nn
import torch.optim as optim
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy
import argparse
print("PyTorch Version: ",torch.__version__)
print("Torchvision Version: ",torchvision.__version__)


# Top level data directory. Here we assume the format of the directory conforms 
#  to the ImageFolder structure

数据集路径,路径下的数据集分为训练集和测试集,也就是train 以及val,train下分为两类数据1,2,val集同理

data_dir = "/home/dell/Desktop/data/切割图像"
# Models to choose from [resnet, alexnet, vgg, squeezenet, densenet, inception]
model_name = "inception" 
# Number of classes in the dataset
num_classes = 2#两类数据1,2

# Batch size for training (change depending on how much memory you have)
batch_size = 32#batchsize尽量选取合适,否则训练时会内存溢出

# Number of epochs to train for 
num_epochs = 1000

# Flag for feature extracting. When False, we finetune the whole model, 
#  when True we only update the reshaped layer params
feature_extract = True

# 参数设置,使得我们能够手动输入命令行参数,就是让风格变得和Linux命令行差不多
parser = argparse.ArgumentParser(description='PyTorch inception')
parser.add_argument('--outf', default='/home/dell/Desktop/dj/inception/', help='folder to output images and model checkpoints') #输出结果保存路径
parser.add_argument('--net', default='/home/dell/Desktop/dj/inception/inception.pth', help="path to net (to continue training)") #恢复训练时的模型路径
args = parser.parse_args()

训练函数

def train_model(model, dataloaders, criterion, optimizer, num_epochs=25,is_inception=False):

  since = time.time()

  val_acc_history = []
  
  best_model_wts = copy.deepcopy(model.state_dict())
  best_acc = 0.0
  print("Start Training, InceptionV3!") 
  with open("acc.txt", "w") as f1:
    with open("log.txt", "w")as f2:
      for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch+1, num_epochs))
        print('*' * 10)
        # Each epoch has a training and validation phase
        for phase in ['train', 'val']:
          if phase == 'train':
            model.train() # Set model to training mode
          else:
            model.eval()  # Set model to evaluate mode
    
          running_loss = 0.0
          running_corrects = 0
    
          # Iterate over data.
          for inputs, labels in dataloaders[phase]:
            inputs = inputs.to(device)
            labels = labels.to(device)
    
            # zero the parameter gradients
            optimizer.zero_grad()
    
            # forward
            # track history if only in train
            with torch.set_grad_enabled(phase == 'train'):
              
              if is_inception and phase == 'train':
                # From https://discuss.pytorch.org/t/how-to-optimize-inception-model-with-auxiliary-classifiers/7958
                outputs, aux_outputs = model(inputs)
                loss1 = criterion(outputs, labels)
                loss2 = criterion(aux_outputs, labels)
                loss = loss1 + 0.4*loss2
              else:
                outputs = model(inputs)
                loss = criterion(outputs, labels)
    
              _, preds = torch.max(outputs, 1)
    
              # backward + optimize only if in training phase
              if phase == 'train':
                loss.backward()
                optimizer.step()
    
            # statistics
            running_loss += loss.item() * inputs.size(0)
            running_corrects += torch.sum(preds == labels.data)
          epoch_loss = running_loss / len(dataloaders[phase].dataset)
          epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)
    
          print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))
          f2.write('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))
          f2.write('\n')
          f2.flush()           
          # deep copy the model
          if phase == 'val':
            if (epoch+1)%50==0:
              #print('Saving model......')
              torch.save(model.state_dict(), '%s/inception_%03d.pth' % (args.outf, epoch + 1))
            f1.write("EPOCH=%03d,Accuracy= %.3f%%" % (epoch + 1, epoch_acc))
            f1.write('\n')
            f1.flush()
          if phase == 'val' and epoch_acc > best_acc:
            f3 = open("best_acc.txt", "w")
            f3.write("EPOCH=%d,best_acc= %.3f%%" % (epoch + 1,epoch_acc))
            f3.close()
            best_acc = epoch_acc
            best_model_wts = copy.deepcopy(model.state_dict())
          if phase == 'val':
            val_acc_history.append(epoch_acc)

  time_elapsed = time.time() - since
  print('Training complete in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
  print('Best val Acc: {:4f}'.format(best_acc))
  # load best model weights
  model.load_state_dict(best_model_wts)
  return model, val_acc_history

 #是否更新参数
def set_parameter_requires_grad(model, feature_extracting):
  if feature_extracting:
    for param in model.parameters():
      param.requires_grad = False



def initialize_model(model_name, num_classes, feature_extract, use_pretrained=True):
  # Initialize these variables which will be set in this if statement. Each of these
  #  variables is model specific.
  model_ft = None
  input_size = 0

  if model_name == "resnet":
    """ Resnet18
    """
    model_ft = models.resnet18(pretrained=use_pretrained)
    set_parameter_requires_grad(model_ft, feature_extract)
    num_ftrs = model_ft.fc.in_features
    model_ft.fc = nn.Linear(num_ftrs, num_classes)
    input_size = 224

  elif model_name == "alexnet":
    """ Alexnet
    """
    model_ft = models.alexnet(pretrained=use_pretrained)
    set_parameter_requires_grad(model_ft, feature_extract)
    num_ftrs = model_ft.classifier[6].in_features
    model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
    input_size = 224

  elif model_name == "vgg":
    """ VGG11_bn
    """
    model_ft = models.vgg11_bn(pretrained=use_pretrained)
    set_parameter_requires_grad(model_ft, feature_extract)
    num_ftrs = model_ft.classifier[6].in_features
    model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
    input_size = 224

  elif model_name == "squeezenet":
    """ Squeezenet
    """
    model_ft = models.squeezenet1_0(pretrained=use_pretrained)
    set_parameter_requires_grad(model_ft, feature_extract)
    model_ft.classifier[1] = nn.Conv2d(512, num_classes, kernel_size=(1,1), stride=(1,1))
    model_ft.num_classes = num_classes
    input_size = 224

  elif model_name == "densenet":
    """ Densenet
    """
    model_ft = models.densenet121(pretrained=use_pretrained)
    set_parameter_requires_grad(model_ft, feature_extract)
    num_ftrs = model_ft.classifier.in_features
    model_ft.classifier = nn.Linear(num_ftrs, num_classes) 
    input_size = 224

  elif model_name == "inception":
    """ Inception v3 
    Be careful, expects (299,299) sized images and has auxiliary output
    """
    model_ft = models.inception_v3(pretrained=use_pretrained)
    set_parameter_requires_grad(model_ft, feature_extract)
    # Handle the auxilary net
    num_ftrs = model_ft.AuxLogits.fc.in_features
    model_ft.AuxLogits.fc = nn.Linear(num_ftrs, num_classes)
    # Handle the primary net
    num_ftrs = model_ft.fc.in_features
    model_ft.fc = nn.Linear(num_ftrs,num_classes)
    input_size = 299

  else:
    print("Invalid model name, exiting...")
    exit()
  
  return model_ft, input_size

# Initialize the model for this run
model_ft, input_size = initialize_model(model_name, num_classes, feature_extract, use_pretrained=True)

# Print the model we just instantiated
#print(model_ft) 


#准备数据
data_transforms = {
  'train': transforms.Compose([
    transforms.RandomResizedCrop(input_size),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
  ]),
  'val': transforms.Compose([
    transforms.Resize(input_size),
    transforms.CenterCrop(input_size),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
  ]),
}

print("Initializing Datasets and Dataloaders...")


# Create training and validation datasets
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'val']}
# Create training and validation dataloaders
dataloaders_dict = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=batch_size, shuffle=True, num_workers=0) for x in ['train', 'val']}

# Detect if we have a GPU available
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
'''
是否加载之前训练过的模型
we='/home/dell/Desktop/dj/inception_050.pth'
model_ft.load_state_dict(torch.load(we))
'''
# Send the model to GPU
model_ft = model_ft.to(device)

params_to_update = model_ft.parameters()
print("Params to learn:")
if feature_extract:
  params_to_update = []
  for name,param in model_ft.named_parameters():
    if param.requires_grad == True:
      params_to_update.append(param)
      print("\t",name)
else:
  for name,param in model_ft.named_parameters():
    if param.requires_grad == True:
      print("\t",name)

# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(params_to_update, lr=0.001, momentum=0.9)
# Decay LR by a factor of 0.1 every 7 epochs
#exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=30, gamma=0.95)

# Setup the loss fxn
criterion = nn.CrossEntropyLoss()

# Train and evaluate
model_ft, hist = train_model(model_ft, dataloaders_dict, criterion, optimizer_ft, num_epochs=num_epochs, is_inception=(model_name=="inception"))

'''
#随机初始化时的训练程序
# Initialize the non-pretrained version of the model used for this run
scratch_model,_ = initialize_model(model_name, num_classes, feature_extract=False, use_pretrained=False)
scratch_model = scratch_model.to(device)
scratch_optimizer = optim.SGD(scratch_model.parameters(), lr=0.001, momentum=0.9)
scratch_criterion = nn.CrossEntropyLoss()
_,scratch_hist = train_model(scratch_model, dataloaders_dict, scratch_criterion, scratch_optimizer, num_epochs=num_epochs, is_inception=(model_name=="inception"))

# Plot the training curves of validation accuracy vs. number 
# of training epochs for the transfer learning method and
# the model trained from scratch
ohist = []
shist = []

ohist = [h.cpu().numpy() for h in hist]
shist = [h.cpu().numpy() for h in scratch_hist]

plt.title("Validation Accuracy vs. Number of Training Epochs")
plt.xlabel("Training Epochs")
plt.ylabel("Validation Accuracy")
plt.plot(range(1,num_epochs+1),ohist,label="Pretrained")
plt.plot(range(1,num_epochs+1),shist,label="Scratch")
plt.ylim((0,1.))
plt.xticks(np.arange(1, num_epochs+1, 1.0))
plt.legend()
plt.show()
'''

以上这篇pytorch之inception_v3的实现案例就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持三水点靠木。

Python 相关文章推荐
浅析Python中的for 循环
Jun 09 Python
Python编程实现正则删除命令功能
Aug 30 Python
Python中矩阵库Numpy基本操作详解
Nov 21 Python
Python利用字典将两个通讯录文本合并为一个文本实例
Jan 16 Python
Pandas读取MySQL数据到DataFrame的方法
Jul 25 Python
解决pycharm下os.system执行命令返回有中文乱码的问题
Jul 07 Python
Python中zip函数如何使用
Jun 04 Python
python有几个版本
Jun 17 Python
pandas按照列的值排序(某一列或者多列)
Dec 13 Python
解决pytorch 的state_dict()拷贝问题
Mar 03 Python
python opencv通过4坐标剪裁图片
Jun 05 Python
Python时间操作之pytz模块使用详解
Jun 14 Python
pytorch之添加BN的实现
Jan 06 #Python
PyTorch学习:动态图和静态图的例子
Jan 06 #Python
pytorch动态网络以及权重共享实例
Jan 06 #Python
selenium中get_cookies()和add_cookie()的用法详解
Jan 06 #Python
pytorch中的自定义反向传播,求导实例
Jan 06 #Python
PyTorch中 tensor.detach() 和 tensor.data 的区别详解
Jan 06 #Python
6行Python代码实现进度条效果(Progress、tqdm、alive-progress​​​​​​​和PySimpleGUI库)
Jan 06 #Python
You might like
PHP中的一些常用函数收集
2015/05/26 PHP
php实现搜索一维数组元素并删除二维数组对应元素的方法
2015/07/06 PHP
详解PHP的Yii框架中日志的相关配置及使用
2015/12/08 PHP
PHP使用内置函数生成图片的方法详解
2016/05/09 PHP
如何用javascript去掉字符串里的所有空格
2007/02/08 Javascript
jQuery 解析xml文件
2009/08/09 Javascript
javascript定义函数的方法
2010/12/06 Javascript
jquery实现的下拉和收缩效果示例
2014/08/21 Javascript
快速学习jQuery插件 Cookie插件使用方法
2015/12/01 Javascript
vue.js异步上传文件前后端实现代码
2017/08/22 Javascript
vue.js分页中单击页码更换页面内容的方法(配合spring springmvc)
2018/02/10 Javascript
解决layer弹出层msg的文字不显示的问题
2019/09/11 Javascript
vue路由传参页面刷新参数丢失问题解决方案
2019/10/08 Javascript
基于Cesium绘制抛物弧线
2020/11/18 Javascript
[04:45]上海特级锦标赛主赛事第三日TOP10
2016/03/05 DOTA
[01:01:52]DOTA2-DPC中国联赛定级赛 SAG vs iG BO3第二场 1月9日
2021/03/11 DOTA
Linux下使用python调用top命令获得CPU利用率
2015/03/10 Python
Python爬虫:通过关键字爬取百度图片
2017/02/17 Python
python好玩的项目—色情图片识别代码分享
2017/11/07 Python
python爬虫爬取网页表格数据
2018/03/07 Python
python线程的几种创建方式详解
2019/08/29 Python
Python调用scp向服务器上传文件示例
2019/12/22 Python
html5 video标签屏蔽右键视频另存为的js代码
2013/11/12 HTML / CSS
Belvilla德国:在线预订度假屋
2018/04/10 全球购物
会计专业自荐信
2013/12/02 职场文书
自行车租赁公司创业计划书
2014/01/28 职场文书
毕业生如何写自我鉴定
2014/03/15 职场文书
勤俭节约演讲稿
2014/05/08 职场文书
多媒体编辑专业毕业生求职信
2014/06/13 职场文书
村级个人对照检查材料
2014/08/22 职场文书
高中军训的心得体会
2014/09/01 职场文书
党的群众路线教育实践活动个人整改落实情况汇报
2014/10/28 职场文书
淘宝客服专员岗位职责
2015/04/07 职场文书
银行资信证明
2015/06/17 职场文书
导游词之香港-太平山顶
2019/10/18 职场文书
Python 实现绘制子图及子图刻度的变换等问题
2021/05/31 Python