欧美bbbwbbbw肥妇,免费乱码人妻系列日韩,一级黄片

關(guān)于ResNeXt網(wǎng)絡(luò)的pytorch實(shí)現(xiàn)

 更新時(shí)間:2020年01月14日 09:04:00   作者:樸素.無(wú)恙  
今天小編就為大家分享一篇關(guān)于ResNeXt網(wǎng)絡(luò)的pytorch實(shí)現(xiàn),具有很好的參考價(jià)值,希望對(duì)大家有所幫助。一起跟隨小編過(guò)來(lái)看看吧

此處需要pip install pretrainedmodels

"""
Finetuning Torchvision Models

"""

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
import pretrainedmodels.models.resnext as resnext

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
#data_dir = "./data/hymenoptera_data"
data_dir = "/media/dell/dell/data/13/"
# Models to choose from [resnet, alexnet, vgg, squeezenet, densenet, inception]
model_name = "resnext"

# Number of classes in the dataset
num_classes = 171

# Batch size for training (change depending on how much memory you have)
batch_size = 16

# 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 = False

# 參數(shù)設(shè)置,使得我們能夠手動(dòng)輸入命令行參數(shù),就是讓風(fēng)格變得和Linux命令行差不多
parser = argparse.ArgumentParser(description='PyTorch seresnet')
parser.add_argument('--outf', default='/home/dell/Desktop/zhou/train7', help='folder to output images and model checkpoints') #輸出結(jié)果保存路徑
parser.add_argument('--net', default='/home/dell/Desktop/zhou/train7/resnext.pth', help="path to net (to continue training)") #恢復(fù)訓(xùn)練時(shí)的模型路徑
args = parser.parse_args()


def train_model(model, dataloaders, criterion, optimizer, num_epochs=25,is_inception=False):
#def train_model(model, dataloaders, criterion, optimizer, num_epochs=25,scheduler, is_inception=False):
  since = time.time()

  val_acc_history = []
  
  best_model_wts = copy.deepcopy(model.state_dict())
  best_acc = 0.0
  print("Start Training, resnext!") # 定義遍歷數(shù)據(jù)集的次數(shù)
  with open("/home/dell/Desktop/zhou/train7/acc.txt", "w") as f1:
    with open("/home/dell/Desktop/zhou/train7/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':
            #scheduler.step()
            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'):
              # Get model outputs and calculate loss
              # Special case for inception because in training it has an auxiliary output. In train
              #  mode we calculate the loss by summing the final output and the auxiliary output
              #  but in testing we only consider the final output.
              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)%5==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, 100*epoch_acc))
            f1.write('\n')
            f1.flush()
          if phase == 'val' and epoch_acc > best_acc:
            f3 = open("/home/dell/Desktop/zhou/train7/best_acc.txt", "w")
            f3.write("EPOCH=%d,best_acc= %.3f%%" % (epoch + 1,100*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


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 == "resnext":
    """ resnext
    Be careful, expects (3,224,224) sized images 
    """
    model_ft = resnext.resnext101_64x4d(num_classes=1000, pretrained='imagenet')
    set_parameter_requires_grad(model_ft, feature_extract)
    model_ft.last_linear = nn.Linear(2048, num_classes)   
    #pre='/home/dell/Desktop/zhou/train6/inception_009.pth'
    #model_ft.load_state_dict(torch.load(pre))
    input_size = 224

  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) 



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=4) for x in ['train', 'val']}

# Detect if we have a GPU available
device = torch.device("cuda:1" if torch.cuda.is_available() else "cpu")

#we='/home/dell/Desktop/dj/inception_050.pth'
#model_ft.load_state_dict(torch.load(we))#diaoyong
# 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=0.01, 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()
print(model_ft)
# Train and evaluate
model_ft, hist = train_model(model_ft, dataloaders_dict, criterion, optimizer_ft, num_epochs=num_epochs, is_inception=False)

以上這篇關(guān)于ResNeXt網(wǎng)絡(luò)的pytorch實(shí)現(xiàn)就是小編分享給大家的全部?jī)?nèi)容了,希望能給大家一個(gè)參考,也希望大家多多支持腳本之家。

相關(guān)文章

  • python 錄制系統(tǒng)聲音的示例

    python 錄制系統(tǒng)聲音的示例

    這篇文章主要介紹了python 錄制系統(tǒng)聲音的示例,幫助大家更好的理解和使用python,感興趣的朋友可以了解下
    2020-12-12
  • 使用wxPython獲取系統(tǒng)剪貼板中的數(shù)據(jù)的教程

    使用wxPython獲取系統(tǒng)剪貼板中的數(shù)據(jù)的教程

    這篇文章主要介紹了使用wxPython獲取系統(tǒng)剪貼板中的數(shù)據(jù)的教程,wxPython是一個(gè)非常受歡迎的Python圖形庫(kù),需要的朋友可以參考下
    2015-05-05
  • python如何進(jìn)行矩陣運(yùn)算

    python如何進(jìn)行矩陣運(yùn)算

    在本篇文章里小編給大家分享的是關(guān)于python進(jìn)行矩陣運(yùn)算的方法及實(shí)例代碼,需要的朋友們可以學(xué)習(xí)下。
    2020-06-06
  • pytorch 數(shù)據(jù)集圖片顯示方法

    pytorch 數(shù)據(jù)集圖片顯示方法

    今天小編就為大家分享一篇pytorch 數(shù)據(jù)集圖片顯示方法,具有很好的參考價(jià)值,希望對(duì)大家有所幫助。一起跟隨小編過(guò)來(lái)看看吧
    2018-07-07
  • Python subprocess庫(kù)六個(gè)實(shí)例快速掌握

    Python subprocess庫(kù)六個(gè)實(shí)例快速掌握

    這次來(lái)說(shuō)Python的第三方庫(kù)subprocess庫(kù),在python2.4以上的版本commands模塊被subprocess取代了。一般當(dāng)我們?cè)谟肞ython寫(xiě)運(yùn)維腳本時(shí),需要履行一些Linux shell的命令,Python中subprocess模塊就是專(zhuān)門(mén)用于調(diào)用Linux shell命令,并返回狀態(tài)和結(jié)果,可以完美的解決這個(gè)問(wèn)題
    2022-10-10
  • 深入理解Python密碼學(xué)之使用PyCrypto庫(kù)進(jìn)行加密和解密

    深入理解Python密碼學(xué)之使用PyCrypto庫(kù)進(jìn)行加密和解密

    Python中的Pycrypto庫(kù)是一個(gè)廣泛使用的密碼學(xué)工具包,它為開(kāi)發(fā)者提供了多種加密算法,包括著名的RSA加密算法,這篇文章主要給大家介紹了關(guān)于Python密碼學(xué)之使用PyCrypto庫(kù)進(jìn)行加密和解密的相關(guān)資料,需要的朋友可以參考下
    2024-07-07
  • pip命令無(wú)法使用的解決方法

    pip命令無(wú)法使用的解決方法

    今天小編就為大家分享一篇pip命令無(wú)法使用的解決方法,具有很好的參考價(jià)值,希望對(duì)大家有所幫助。一起跟隨小編過(guò)來(lái)看看吧
    2018-06-06
  • python根據(jù)文章標(biāo)題內(nèi)容自動(dòng)生成摘要的實(shí)例

    python根據(jù)文章標(biāo)題內(nèi)容自動(dòng)生成摘要的實(shí)例

    今天小編就為大家分享一篇python根據(jù)文章標(biāo)題內(nèi)容自動(dòng)生成摘要的實(shí)例,具有很好的參考價(jià)值,希望對(duì)大家有所幫助。一起跟隨小編過(guò)來(lái)看看吧
    2019-02-02
  • 從零開(kāi)始的TensorFlow+VScode開(kāi)發(fā)環(huán)境搭建的步驟(圖文)

    從零開(kāi)始的TensorFlow+VScode開(kāi)發(fā)環(huán)境搭建的步驟(圖文)

    這篇文章主要介紹了從零開(kāi)始的TensorFlow+VScode開(kāi)發(fā)環(huán)境搭建的步驟(圖文),文中通過(guò)示例代碼介紹的非常詳細(xì),對(duì)大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價(jià)值,需要的朋友們下面隨著小編來(lái)一起學(xué)習(xí)學(xué)習(xí)吧
    2020-08-08
  • selenium+python自動(dòng)化測(cè)試環(huán)境搭建步驟

    selenium+python自動(dòng)化測(cè)試環(huán)境搭建步驟

    在本文中小編給大家分享了關(guān)于selenium+python自動(dòng)化測(cè)試環(huán)境搭建的相關(guān)步驟以及知識(shí)點(diǎn)內(nèi)容,需要的朋友們參考學(xué)習(xí)下。
    2019-06-06

最新評(píng)論