【猫狗数据集】使用top1和top5准确率衡量模型

数据集下载地址：

链接：https://pan.baidu.com/s/1l1AnBgkAAEhh0vI5_loWKw
提取码：2xq4

创建数据集：https://www.cnblogs.com/xiximayou/p/12398285.html

读取数据集：https://www.cnblogs.com/xiximayou/p/12422827.html

进行训练：https://www.cnblogs.com/xiximayou/p/12448300.html

保存模型并继续进行训练：https://www.cnblogs.com/xiximayou/p/12452624.html

加载保存的模型并测试：https://www.cnblogs.com/xiximayou/p/12459499.html

划分验证集并边训练边验证：https://www.cnblogs.com/xiximayou/p/12464738.html

使用学习率衰减策略并边训练边测试：https://www.cnblogs.com/xiximayou/p/12468010.html

利用tensorboard可视化训练和测试过程：https://www.cnblogs.com/xiximayou/p/12482573.html

从命令行接收参数：https://www.cnblogs.com/xiximayou/p/12488662.html

epoch、batchsize、step之间的关系：https://www.cnblogs.com/xiximayou/p/12405485.html

之前使用的仅仅是top1准确率。在图像分类中，一般使用top1和top5来衡量分类模型的好坏。下面来看看。

首先在util下新建一个acc.py文件，向里面加入计算top1和top5准确率的代码：

import torch
def accu(output, target, topk=(1,)):
    """Computes the accuracy over the k top predictions for the specified values of k"""
    with torch.no_grad():
        maxk = max(topk)
        batch_size = target.size(0)
        _, pred = output.topk(maxk, 1, True, True)
        pred = pred.t()
        correct = pred.eq(target.view(1, -1).expand_as(pred))

        res = []
        for k in topk:
            correct_k = correct[:k].view(-1).float().sum(0, keepdim=True)
            res.append(correct_k.mul_(100.0 / batch_size))
        return res

重点就是topk()函数：

torch.topk(input, k, dim=None, largest=True, sorted=True, out=None) -> (Tensor, LongTensor)
input：输入张量
k：指定返回的前几位的值
dim：排序的维度
largest：返回最大值
sorted：返回值是否排序
out：可选输出张量

需要注意的是我们这里只有两类，因此不存在top5。因此如果设置参数topk=(1,5)，则会报错：RuntimeError:invalid argument 5:k not in range for dimension at /pytorch/ate ... 

因此我们只能设置topk=(1,2)，而且top2的值肯定是100%。最终res中第一位存储的是top1准确率，第二位存储的是top2准确率。

然后修改对应的train.py：

import torch
from tqdm import tqdm
from tensorflow import summary
import datetime
from utils import acc

"""
current_time = str(datetime.datetime.now().timestamp())
train_log_dir = '/content/drive/My Drive/colab notebooks/output/tsboardx/train/' + current_time
test_log_dir = '/content/drive/My Drive/colab notebooks/output/tsboardx/test/' + current_time
val_log_dir = '/content/drive/My Drive/colab notebooks/output/tsboardx/val/' + current_time
train_summary_writer = summary.create_file_writer(train_log_dir)
val_summary_writer = summary.create_file_writer(val_log_dir)
test_summary_writer = summary.create_file_writer(test_log_dir)
"""
class Trainer:
  def __init__(self,criterion,optimizer,model):
    self.criterion=criterion
    self.optimizer=optimizer
    self.model=model
  def get_lr(self):
    for param_group in self.optimizer.param_groups:
        return param_group['lr']
  def loop(self,num_epochs,train_loader,val_loader,test_loader,scheduler=None,acc1=0.0):
    self.acc1=acc1
    for epoch in range(1,num_epochs+1):
      lr=self.get_lr()
      print("epoch：{}，lr：{:.6f}".format(epoch,lr))
      self.train(train_loader,epoch,num_epochs)
      self.val(val_loader,epoch,num_epochs)
      self.test(test_loader,epoch,num_epochs)
      if scheduler is not None:
        scheduler.step()

  def train(self,dataloader,epoch,num_epochs):
    self.model.train()
    with torch.enable_grad():
      self._iteration_train(dataloader,epoch,num_epochs)

  def val(self,dataloader,epoch,num_epochs):
    self.model.eval()
    with torch.no_grad():
      self._iteration_val(dataloader,epoch,num_epochs)
  def test(self,dataloader,epoch,num_epochs):
    self.model.eval()
    with torch.no_grad():
      self._iteration_test(dataloader,epoch,num_epochs)

  def _iteration_train(self,dataloader,epoch,num_epochs):
    #total_step=len(dataloader)
    #tot_loss = 0.0
    #correct = 0
    train_loss=AverageMeter()
    train_top1=AverageMeter()
    train_top2=AverageMeter()
    #for i ,(images, labels) in enumerate(dataloader):
    #res=[]
    for images, labels in tqdm(dataloader,ncols=80):
      images = images.cuda()
      labels = labels.cuda()
      # Forward pass
      outputs = self.model(images)
      #_, preds = torch.max(outputs.data,1)
      pred1_train,pred2_train=acc.accu(outputs,labels,topk=(1,2))
      loss = self.criterion(outputs, labels)
      train_loss.update(loss.item(),images.size(0))
      train_top1.update(pred1_train[0],images.size(0))
      train_top2.update(pred2_train[0],images.size(0))
      # Backward and optimizer
      self.optimizer.zero_grad()
      loss.backward()
      self.optimizer.step()
      #tot_loss += loss.data
      """
      if (i+1) % 2 == 0:
          print('Epoch: [{}/{}], Step: [{}/{}], Loss: {:.4f}'
                .format(epoch, num_epochs, i+1, total_step, loss.item()))
      """
      #correct += torch.sum(preds == labels.data).to(torch.float32)
    ### Epoch info ####
    #epoch_loss = tot_loss/len(dataloader.dataset)
    #epoch_acc = correct/len(dataloader.dataset)
    #print('train loss: {:.4f},train acc： {:.4f}'.format(epoch_loss,epoch_acc))
    print(">>>[{}] train_loss:{:.4f} top1:{:.4f} top2:{:.4f}".format("train", train_loss.avg, train_top1.avg, train_top2.avg))
    """
    with train_summary_writer.as_default():
      summary.scalar('loss', train_loss.avg, epoch)
      summary.scalar('accuracy', train_top1.avg, epoch)
    """
    """
    if epoch==num_epochs:
      state = { 
        'model': self.model.state_dict(), 
        'optimizer':self.optimizer.state_dict(), 
        'epoch': epoch,
        'train_loss':train_loss.avg,
        'train_acc':train_top1.avg,
      }
      save_path="/content/drive/My Drive/colab notebooks/output/"   
      torch.save(state,save_path+"/resnet18_final_v2"+".t7")
    """
    t_loss = train_loss.avg,
    t_top1 = train_top1.avg
    t_top2 = train_top2.avg
    return t_loss,t_top1,t_top2
  def _iteration_val(self,dataloader,epoch,num_epochs):
    #total_step=len(dataloader)
    #tot_loss = 0.0
    #correct = 0
    #for i ,(images, labels) in enumerate(dataloader):
    val_loss=AverageMeter()
    val_top1=AverageMeter()
    val_top2=AverageMeter()
    for images, labels in tqdm(dataloader,ncols=80):
        images = images.cuda()
        labels = labels.cuda()

        # Forward pass
        outputs = self.model(images)
        #_, preds = torch.max(outputs.data,1)
        pred1_val,pred2_val=acc.accu(outputs,labels,topk=(1,2))
        loss = self.criterion(outputs, labels)
        val_loss.update(loss.item(),images.size(0))
        val_top1.update(pred1_val[0],images.size(0))
        val_top2.update(pred2_val[0],images.size(0))
        #tot_loss += loss.data
        #correct += torch.sum(preds == labels.data).to(torch.float32)
        """
        if (i+1) % 2 == 0:
            print('Epoch: [{}/{}], Step: [{}/{}], Loss: {:.4f}'
                  .format(1, 1, i+1, total_step, loss.item()))
        """
    ### Epoch info ####
    #epoch_loss = tot_loss/len(dataloader.dataset)
    #epoch_acc = correct/len(dataloader.dataset)
    #print('val loss: {:.4f}，val acc: {:.4f}'.format(epoch_loss,epoch_acc))
    print(">>>[{}] val_loss:{:.4f} top1:{:.4f} top2:{:.4f}".format("val", val_loss.avg, val_top1.avg, val_top2.avg))
    """
    with val_summary_writer.as_default():
      summary.scalar('loss', val_loss.avg, epoch)
      summary.scalar('accuracy', val_top1.avg, epoch)
    """
    t_loss = val_loss.avg,
    t_top1 = val_top1.avg
    t_top2 = val_top2.avg
    return t_loss,t_top1,t_top2
  def _iteration_test(self,dataloader,epoch,num_epochs):
    #total_step=len(dataloader)
    #tot_loss = 0.0
    #correct = 0
    #for i ,(images, labels) in enumerate(dataloader):
    test_loss=AverageMeter()
    test_top1=AverageMeter()
    test_top2=AverageMeter()
    for images, labels in tqdm(dataloader,ncols=80):
        images = images.cuda()
        labels = labels.cuda()

        # Forward pass
        outputs = self.model(images)
        #_, preds = torch.max(outputs.data,1)
        pred1_test,pred2_test=acc.accu(outputs,labels,topk=(1,2))
        loss = self.criterion(outputs, labels)
        test_loss.update(loss.item(),images.size(0))
        test_top1.update(pred1_test[0],images.size(0))
        test_top2.update(pred2_test[0],images.size(0))
        #tot_loss += loss.data
        #correct += torch.sum(preds == labels.data).to(torch.float32)
        """
        if (i+1) % 2 == 0:
            print('Epoch: [{}/{}], Step: [{}/{}], Loss: {:.4f}'
                  .format(1, 1, i+1, total_step, loss.item()))
        """          
    ### Epoch info ####
    #epoch_loss = tot_loss/len(dataloader.dataset)
    #epoch_acc = correct/len(dataloader.dataset) * 100
    #print('test loss: {:.4f}，test acc： {:.4f}'.format(epoch_loss,epoch_acc))
    print(">>>[{}] test_loss:{:.4f} top1:{:.4f} top2:{:.4f}".format("test", test_loss.avg, test_top1.avg, test_top2.avg))
    t_loss = test_loss.avg,
    t_top1 = test_top1.avg
    t_top2 = test_top2.avg
    """
    with test_summary_writer.as_default():
      summary.scalar('loss', test_loss.avg, epoch)
      summary.scalar('accuracy', test_top1.avg, epoch)
    """
    """
    if epoch_acc > self.acc1:
      state = {  
      "model": self.model.state_dict(),
      "optimizer": self.optimizer.state_dict(),
      "epoch": epoch,
      "epoch_loss": test_loss.avg,
      "epoch_acc": test_top1.avg,
      }
      save_path="/content/drive/My Drive/colab notebooks/output/"
      print("在第{}个epoch取得最好的测试准确率，准确率为：{:.4f}".format(epoch,test_top1.avg))   
      torch.save(state,save_path+"/resnet18_best_v2"+".t7")
      self.acc1=max(self.acc1,test_top1.avg)
    """
    return t_loss,t_top1,t_top2

class AverageMeter(object):
    def __init__(self):
        self.reset()

    def reset(self):
        self.val = 0
        self.avg = 0
        self.sum = 0
        self.count = 0

    def update(self, val, n=1):
        self.val = val
        self.sum += float(val) * n
        self.count += n
        self.avg = self.sum / self.count

我们新建了一个AverageMeter类来存储结果。

最终结果：

下一节：加载预训练的模型并进行微调。