pytorch 使用预训练过的ResNet 进行微调，训练新的数据集CIFAR100
from __future__ import print_function
import torch
import time
import torch.nn as nn
import torch.nn.functional as F
import torchvision
import torchvision.transforms as transforms
from torch import optim
from torch.autograd import Variable
from torch.utils.data import DataLoader
from torchvision.transforms import ToPILImage
show=ToPILImage()
import numpy as np
import matplotlib.pyplot as plt
#
batchSize=32
#
transform=transforms.Compose([transforms.Resize(224),transforms.ToTensor(),transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5))])
train_set=torchvision.datasets.CIFAR100(root='../../data', train=True, download=True, transform=transform)
trainloader=torch.utils.data.DataLoader(train_set,batch_size=batchSize,shuffle=True,num_workers=0)
test_set=torchvision.datasets.CIFAR100(root="../../data",train=False,download=True,transform=transform)
testloader=torch.utils.data.DataLoader(test_set,batch_size=batchSize,shuffle=True,num_workers=0)
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
#network
model=torchvision.models.resnet18(pretrained=True)
model.fc=nn.Linear(512,100,bias=True)
print (model)
#train
net=model.cuda()
criterion=nn.CrossEntropyLoss()
optimizer=optim.SGD(net.parameters(),lr=0.01,momentum=0.9)
print ("training begin")
for epoch in range(3):
start = time.time()
running_loss=0
for i,data in enumerate(trainloader,0):
# print (inputs,labels)
image,label=data
image=image.cuda()
label=label.cuda()
image=Variable(image)
label=Variable(label)
# imshow(torchvision.utils.make_grid(image))
# plt.show()
# print (label)
optimizer.zero_grad()
outputs=net(image)
# print (outputs)
loss=criterion(outputs,label)
loss.backward()
optimizer.step()
running_loss+=loss.data
if i%100==99:
end=time.time()
print ('[epoch %d,imgs %5d] loss: %.7f time: %0.3f s'%(epoch+1,(i+1)*batchSize,running_loss/100,(end-start)))
start=time.time()
running_loss=0
print ("finish training")
ResNet(
(conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(layer1): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(1): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(layer2): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(layer3): Sequential(
(0): BasicBlock(
(conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(layer4): Sequential(
(0): BasicBlock(
(conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(avgpool): AvgPool2d(kernel_size=7, stride=1, padding=0)
(fc): Linear(in_features=512, out_features=100, bias=True)
)
training begin
[epoch 1,imgs 12800] loss: 2.7901773 time: 22.506 s
[epoch 1,imgs 25600] loss: 1.2604527 time: 20.781 s
[epoch 1,imgs 38400] loss: 1.0245405 time: 20.829 s
[epoch 2,imgs 12800] loss: 0.6451855 time: 20.892 s
[epoch 2,imgs 25600] loss: 0.6338561 time: 20.909 s
[epoch 2,imgs 38400] loss: 0.6310505 time: 20.904 s
[epoch 3,imgs 12800] loss: 0.3535683 time: 20.935 s
[epoch 3,imgs 25600] loss: 0.3353625 time: 20.934 s
[epoch 3,imgs 38400] loss: 0.3590593 time: 20.947 s
finish training
