SE-Resnext网络搭建及预训练模型
SE-Resnext预训练
完整代码
# -*- coding: utf-8 -*-
import os, torch, glob, time, copy
import numpy as np
from torch.autograd import Variable
from PIL import Image
from torchvision import models, transforms
import torch.nn as nn
from torch.utils.data import DataLoader, Dataset
import torch.optim as optim
from torch.optim import lr_scheduler
import pretrainedmodels
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "0,1"
train_data_dir = '/home/train/'
test_data_dir = '/home/test/'
def get_lists(data_dir):
files_list = []
labels_list = []
sub_dirs = [x[0] for x in os.walk(data_dir) ]
sub_dirs = sub_dirs[1:]
extentions = ['jpg', 'jpeg', 'JPG', 'JPEG']
for sub_dir in sub_dirs:
if os.path.basename(sub_dir) == '0':
label = [0]
elif os.path.basename(sub_dir) == '1':
label = [1]
elif os.path.basename(sub_dir) == '2':
label = [2]
elif os.path.basename(sub_dir) == '3':
label = [3]
elif os.path.basename(sub_dir) == '4':
label = [4]
elif os.path.basename(sub_dir) == '5':
label = [5]
elif os.path.basename(sub_dir) == '6':
label = [6]
elif os.path.basename(sub_dir) == '7':
label = [7]
elif os.path.basename(sub_dir) == '8':
label = [8]
elif os.path.basename(sub_dir) == '9':
label = [9]
elif os.path.basename(sub_dir) == '10':
label = [10]
elif os.path.basename(sub_dir) == '11':
label = [11]
elif os.path.basename(sub_dir) == '12':
label = [12]
elif os.path.basename(sub_dir) == '13':
label = [13]
elif os.path.basename(sub_dir) == '14':
label = [14]
elif os.path.basename(sub_dir) == '15':
label = [15]
elif os.path.basename(sub_dir) == '16':
label = [16]
elif os.path.basename(sub_dir) == '17':
label = [17]
for extention in extentions:
file_glob = os.path.join(sub_dir, '*.' + extention)
new_files = glob.glob(file_glob)
files_list.extend(new_files)
labels_list = labels_list + label * len(new_files)
return files_list, labels_list
class myDataset(Dataset):
# TensorDataset继承Dataset, 重载了__init__, __getitem__, __len__
# 实现将一组Tensor数据对封装成Tensor数据集
# 能够通过index得到数据集的数据，能够通过len，得到数据集大小
def __init__(self, files_list, labels_list, transform):
self.files_list = files_list
self.labels_list = labels_list
self.transform = transform
def __getitem__(self, index):
img = Image.open(self.files_list[index])
img = self.transform(img)
return img, self.labels_list[index]
def __len__(self):
return len(self.labels_list)
def make_save_dir(dirname,epoch):
save_dir = os.path.join(dirname,epoch)
if not os.path.exists(save_dir):
os.makedirs(save_dir)
return save_dir
def get_filename_for_saving(save_dir):
return os.path.join(save_dir,"torh.pth")
def train_model(model, criterion, optimizer, scheduler, num_epochs=15):
since1 = time.time()
best_model_wts = copy.deepcopy(model.state_dict())
best_acc = 0.0
for epoch in range(num_epochs):
since2 = time.time()
print('Epoch {}/{}'.format(epoch, num_epochs - 1))
print('-' * 10)
# Each epoch has a training and validation phase
for phase in ['train', 'val']:
if phase == 'train':
scheduler.step()
model.train(True) # Set model to training mode
else:
model.train(False) # Set model to evaluate mode
running_loss = 0.0
running_corrects = 0
# Iterate over data.
for data in (dataloaders[phase]):
# get the inputs
inputs, labels = data
# wrap them in Variable
if use_gpu:
inputs = Variable(inputs.cuda())
labels = Variable(labels.cuda())
else:
inputs, labels = Variable(inputs), Variable(labels)
# zero the parameter gradients
optimizer.zero_grad()
# forward
outputs = model(inputs)
_, preds = torch.max(outputs.data, 1)
loss = criterion(outputs, labels)
# 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 / dataset_sizes[phase]
epoch_acc = running_corrects.double() / dataset_sizes[phase]
print('{} Loss: {:.4f} Acc: {:.4f}'.format(
phase, epoch_loss, epoch_acc))
# deep copy the model
if phase == 'val' and epoch_acc > best_acc:
best_acc = epoch_acc
best_model_wts = copy.deepcopy(model.state_dict())
print(time.time() - since2)
save_dir="/home/"+str(epoch)+".pth"
torch.save(model,save_dir)
time_elapsed = time.time() - since1
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)
torch.save(model.state_dict(),'/home/11.13_resnet50_no.pth')
return model
if __name__ == '__main__':
BATCH_SIZE =32
use_gpu = torch.cuda.is_available()
transform = transforms.Compose([
transforms.Scale(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485,0.456,0.406],
std=[0.229,0.224,0.225])]
)
train_images, train_labels = get_lists(train_data_dir)
test_images, test_labels = get_lists(test_data_dir)
train_dataset = myDataset(train_images, train_labels, transform)
test_dataset = myDataset(test_images, test_labels, transform)
train_loader = DataLoader(dataset=train_dataset, batch_size=BATCH_SIZE,
shuffle=True, num_workers=0)
test_loader = DataLoader(dataset=test_dataset, batch_size=BATCH_SIZE,
shuffle=False, num_workers=0)
dataloaders = {}
dataloaders['train'] = train_loader
dataloaders['val'] = test_loader
dataset_sizes = {}
dataset_sizes['train'] = len(train_labels)
dataset_sizes['val'] = len(test_labels)
# model_ft = models.resnet50(pretrained=True)
# # for param in model_ft.parameters():
# # param.requires_grad = False
# num_ftrs = model_ft.fc.in_features
# model_ft.fc = nn.Linear(num_ftrs, 18)
model_name = 'se_resnext101_32x4d' # could be fbresnet152 or inceptionresnetv2
model_ft = pretrainedmodels.__dict__[model_name](num_classes=1000, pretrained='imagenet')
# num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(2048, 18)
model_ft.eval()
if use_gpu:
model_ft = model_ft.cuda()
model_ft = torch.nn.DataParallel(model_ft, device_ids=[0,1])
criterion = nn.CrossEntropyLoss()
# Observe that all parameters are being optimized
# optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)
optimizer_ft = optim.Adam(model_ft.parameters(), lr=0.001, betas=(0.9,0.999),eps=1e-08,weight_decay=0,amsgrad=False)
# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
num_epochs=25)
# for (batch_x, batch_y) in enumerate(train_loader):
# print(batch_x, batch_y)
1、预训练模型下载
点击这里下载
2、pytorch每训练一轮保存一次模型
def train_model(model, criterion, optimizer, scheduler, num_epochs=15):
since1 = time.time()
best_model_wts = copy.deepcopy(model.state_dict())
best_acc = 0.0
for epoch in range(num_epochs):
since2 = time.time()
print('Epoch {}/{}'.format(epoch, num_epochs - 1))
print('-' * 10)
# Each epoch has a training and validation phase
for phase in ['train', 'val']:
if phase == 'train':
scheduler.step()
model.train(True) # Set model to training mode
else:
model.train(False) # Set model to evaluate mode
running_loss = 0.0
running_corrects = 0
# Iterate over data.
for data in (dataloaders[phase]):
# get the inputs
inputs, labels = data
# wrap them in Variable
if use_gpu:
inputs = Variable(inputs.cuda())
labels = Variable(labels.cuda())
else:
inputs, labels = Variable(inputs), Variable(labels)
# zero the parameter gradients
optimizer.zero_grad()
# forward
outputs = model(inputs)
_, preds = torch.max(outputs.data, 1)
loss = criterion(outputs, labels)
# 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 / dataset_sizes[phase]
epoch_acc = running_corrects.double() / dataset_sizes[phase]
print('{} Loss: {:.4f} Acc: {:.4f}'.format(
phase, epoch_loss, epoch_acc))
# deep copy the model
if phase == 'val' and epoch_acc > best_acc:
best_acc = epoch_acc
best_model_wts = copy.deepcopy(model.state_dict())
print(time.time() - since2)
save_dir="/home/vivo3/11.14se_resnext101_32x4d/"+str(epoch)+".pth"//每训练一轮保存一次模型
torch.save(model,save_dir)
time_elapsed = time.time() - since1
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)
torch.save(model.state_dict(),'/home/11.13_resnet50_no.pth')//保存最佳模型
return model
3、
SE-Resnext网络搭建完整代码
'''
New for ResNeXt:
1. Wider bottleneck
2. Add group for conv2
'''
import torch.nn as nn
import math
__all__ = ['SE_ResNeXt', 'se_resnext_50', 'se_resnext_101', 'se_resnext_152']
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None, num_group=32):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes*2, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes*2)
self.conv2 = nn.Conv2d(planes*2, planes*2, kernel_size=3, stride=stride,
padding=1, bias=False, groups=num_group)
self.bn2 = nn.BatchNorm2d(planes*2)
self.conv3 = nn.Conv2d(planes*2, planes * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
if planes == 64:
self.globalAvgPool = nn.AvgPool2d(56, stride=1)
elif planes == 128:
self.globalAvgPool = nn.AvgPool2d(28, stride=1)
elif planes == 256:
self.globalAvgPool = nn.AvgPool2d(14, stride=1)
elif planes == 512:
self.globalAvgPool = nn.AvgPool2d(7, stride=1)
self.fc1 = nn.Linear(in_features=planes * 4, out_features=round(planes / 4))
self.fc2 = nn.Linear(in_features=round(planes / 4), out_features=planes * 4)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
residual = self.downsample(x)
original_out = out
out = self.globalAvgPool(out)
out = out.view(out.size(0), -1)
out = self.fc1(out)
out = self.relu(out)
out = self.fc2(out)
out = self.sigmoid(out)
out = out.view(out.size(0), out.size(1), 1, 1)
out = out * original_out
out += residual
out = self.relu(out)
return out
class SE_ResNeXt(nn.Module):
def __init__(self, block, layers, num_classes=1000, num_group=32):
self.inplanes = 64
super(SE_ResNeXt, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0], num_group)
self.layer2 = self._make_layer(block, 128, layers[1], num_group, stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], num_group, stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], num_group, stride=2)
self.avgpool = nn.AvgPool2d(7, stride=1)
self.fc = nn.Linear(512 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def _make_layer(self, block, planes, blocks, num_group, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample, num_group=num_group))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes, num_group=num_group))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
return x
def se_resnext_50(**kwargs):
"""Constructs a ResNeXt-50 model.
"""
model = SE_ResNeXt(Bottleneck, [3, 4, 6, 3], **kwargs)
return model
def se_resnext_101(**kwargs):
"""Constructs a ResNeXt-101 model.
"""
model = SE_ResNeXt(Bottleneck, [3, 4, 23, 3], **kwargs)
return model
def se_resnext_152(**kwargs):
"""Constructs a ResNeXt-152 model.
"""
model = SE_ResNeXt(Bottleneck, [3, 8, 36, 3], **kwargs)
return model