关于关于ResNeXt网络的网络的pytorch实现实现
今天小编就为大家分享一篇关于ResNeXt网络的pytorch实现,具有很好的参考价值,希望对大家有所帮助。一
起跟随小编过来看看吧
此处需要此处需要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
# 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 seresnet')
parser.add_argument('--outf', default='/home/dell/Desktop/zhou/train7', help='folder to output images and model checkpoints') #输出结果保存路径
parser.add_argument('--net', default='/home/dell/Desktop/zhou/train7/resnext.pth', help="path to net (to continue training)") #恢复训练时的模型路径
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!") # 定义遍历数据集的次数
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