pytorch之inception_v3的实现案例

2020-12-16 20:35:12 阅读：285 来源： 互联网

标签：ft epoch num pytorch v3 inception model size

更多python教程请到：菜鸟教程www.piaodoo.com

人人影视www.sfkyty.com

16影视www.591319.com

星辰影院www.591319.com

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 &gt; 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菜鸟教程www.piaodoo.com。

标签：ft,epoch,num,pytorch,v3,inception,model,size
来源： https://www.cnblogs.com/piaodoo/p/14146021.html

本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享；
2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关；
3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关；
4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除；
5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。

ICode9

pytorch之inception_v3的实现案例

Top level data directory. Here we assume the format of the directory conforms

to the ImageFolder structure

Batch size for training (change depending on how much memory you have)

Number of epochs to train for

Flag for feature extracting. When False, we finetune the whole model,

when True we only update the reshaped layer params

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

load best model weights

是否更新参数

Initialize these variables which will be set in this if statement. Each of these

variables is model specific.

Initialize the model for this run

Print the model we just instantiated

print(model_ft)

准备数据

Create training and validation datasets

Create training and validation dataloaders

Detect if we have a GPU available

Send the model to GPU

Observe that all parameters are being optimized

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

Train and evaluate

随机初始化时的训练程序

Initialize the non-pretrained version of the model used for this run

Plot the training curves of validation accuracy vs. number

of training epochs for the transfer learning method and

the model trained from scratch