美文网首页
Pytorch ResNet Fashion-Mnist

Pytorch ResNet Fashion-Mnist

作者: hyhchaos | 来源:发表于2018-09-27 15:44 被阅读168次

    pytorch 实现 ResNet on Fashion-MNIST

    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=128
    
    ##load data
    transform = transforms.Compose([transforms.Resize(96),transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
    
    trainset = torchvision.datasets.FashionMNIST(root='./data', train=True, download=True, transform=transform)
    trainloader = torch.utils.data.DataLoader(trainset, batch_size=batchSize, shuffle=True, num_workers=0)
    
    testset = torchvision.datasets.FashionMNIST(root='./data', train=False, download=True, transform=transform)
    testloader = torch.utils.data.DataLoader(testset, batch_size=batchSize, shuffle=False, num_workers=0)
    
    classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
    
    def imshow(img):
        img = img / 2 + 0.5
        npimg = img.numpy()
        plt.imshow(np.transpose(npimg, (1, 2, 0)))
    
    ####network
    class Residual(nn.Module):
        def __init__(self,in_channel,num_channel,use_conv1x1=False,strides=1):
            super(Residual,self).__init__()
            self.relu=nn.ReLU()
            self.bn1=nn.BatchNorm2d(in_channel,eps=1e-3)
            self.conv1=nn.Conv2d(in_channels =in_channel,out_channels=num_channel,kernel_size=3,padding=1,stride=strides)
            self.bn2=nn.BatchNorm2d(num_channel,eps=1e-3)
            self.conv2=nn.Conv2d(in_channels=num_channel,out_channels=num_channel,kernel_size=3,padding=1)
            if use_conv1x1:
                self.conv3=nn.Conv2d(in_channels=in_channel,out_channels=num_channel,kernel_size=1,stride=strides)
            else:
                self.conv3=None
    
    
        def forward(self, x):
            y=self.conv1(self.relu(self.bn1(x)))
            y=self.conv2(self.relu(self.bn2(y)))
            # print (y.shape)
            if self.conv3:
                x=self.conv3(x)
            # print (x.shape)
            z=y+x
            return z
    
    # blk = Residual(3,3,True)
    # X = Variable(torch.zeros(4, 3, 96, 96))
    # out=blk(X)
    
    def ResNet_block(in_channels,num_channels,num_residuals,first_block=False):
        layers=[]
        for i in range(num_residuals):
            if i==0 and not first_block:
                layers+=[Residual(in_channels,num_channels,use_conv1x1=True,strides=2)]
            elif i>0 and not first_block:
                layers+=[Residual(num_channels,num_channels)]
            else:
                layers += [Residual(in_channels, num_channels)]
        blk=nn.Sequential(*layers)
        return blk
    
    
    class ResNet(nn.Module):
        def __init__(self,in_channel,num_classes):
            super(ResNet,self).__init__()
            self.block1=nn.Sequential(nn.Conv2d(in_channels=in_channel,out_channels=64,kernel_size=7,stride=2,padding=3),
                                      nn.BatchNorm2d(64),
                                      nn.ReLU(),
                                      nn.MaxPool2d(kernel_size=3,stride=2,padding=1))
            self.block2=nn.Sequential(ResNet_block(64,64,2,True),
                                      ResNet_block(64,128,2),
                                      ResNet_block(128,256,2),
                                      ResNet_block(256,512,2))
            self.block3=nn.Sequential(nn.AvgPool2d(kernel_size=3))
            self.Dense=nn.Linear(512,10)
    
    
        def forward(self,x):
            y=self.block1(x)
            y=self.block2(y)
            y=self.block3(y)
            y=y.view(-1,512)
            y=self.Dense(y)
            return y
    
    
    net=ResNet(1,10).cuda()
    print (net)
    criterion=nn.CrossEntropyLoss()
    optimizer=optim.SGD(net.parameters(),lr=0.05,momentum=0.9)
    
    #train
    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")
    
    
    #test
    net.eval()
    correct=0
    total=0
    for data in testloader:
        images,labels=data
        images=images.cuda()
        labels=labels.cuda()
        outputs=net(Variable(images))
        _,predicted=torch.max(outputs,1)
        total+=labels.size(0)
        correct+=(predicted==labels).sum()
    print('Accuracy of the network on the %d test images: %d %%' % (total , 100 * correct / total))
    

    运行过程

    ResNet(
      (block1): Sequential(
        (0): Conv2d(1, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3))
        (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU()
        (3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
      )
      (block2): Sequential(
        (0): Sequential(
          (0): Residual(
            (relu): ReLU()
            (bn1): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (bn2): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          )
          (1): Residual(
            (relu): ReLU()
            (bn1): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (bn2): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          )
        )
        (1): Sequential(
          (0): Residual(
            (relu): ReLU()
            (bn1): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
            (bn2): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (conv3): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2))
          )
          (1): Residual(
            (relu): ReLU()
            (bn1): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (bn2): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          )
        )
        (2): Sequential(
          (0): Residual(
            (relu): ReLU()
            (bn1): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
            (bn2): BatchNorm2d(256, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2))
          )
          (1): Residual(
            (relu): ReLU()
            (bn1): BatchNorm2d(256, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (bn2): BatchNorm2d(256, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          )
        )
        (3): Sequential(
          (0): Residual(
            (relu): ReLU()
            (bn1): BatchNorm2d(256, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
            (bn2): BatchNorm2d(512, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2))
          )
          (1): Residual(
            (relu): ReLU()
            (bn1): BatchNorm2d(512, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (bn2): BatchNorm2d(512, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          )
        )
      )
      (block3): Sequential(
        (0): AvgPool2d(kernel_size=3, stride=3, padding=0)
      )
      (Dense): Linear(in_features=512, out_features=10, bias=True)
    )
    training begin
    [epoch 1,imgs 12800] loss: 0.6906891  time: 5.284 s
    [epoch 1,imgs 25600] loss: 0.4192125  time: 5.254 s
    [epoch 1,imgs 38400] loss: 0.3470914  time: 5.261 s
    [epoch 1,imgs 51200] loss: 0.3338268  time: 5.266 s
    [epoch 2,imgs 12800] loss: 0.2725625  time: 5.286 s
    [epoch 2,imgs 25600] loss: 0.2590218  time: 5.277 s
    [epoch 2,imgs 38400] loss: 0.2629448  time: 5.273 s
    [epoch 2,imgs 51200] loss: 0.2552892  time: 5.283 s
    [epoch 3,imgs 12800] loss: 0.2204756  time: 5.299 s
    [epoch 3,imgs 25600] loss: 0.2263550  time: 5.292 s
    [epoch 3,imgs 38400] loss: 0.2150247  time: 5.294 s
    [epoch 3,imgs 51200] loss: 0.2215548  time: 5.299 s
    finish training
    Accuracy of the network on the 10000 test images: 90 %
    

    相关文章

      网友评论

          本文标题:Pytorch ResNet Fashion-Mnist

          本文链接:https://www.haomeiwen.com/subject/xlieoftx.html