当我开始训练我的模型时，损失值在下降，但准确率值始终不变。我不知道为什么？

# -*- coding: utf-8 -*-#Librariesimport torchimport torch.nn.functional as Ffrom torch import autograd, nnfrom torch.autograd import Variableimport numpy as npimport matplotlib.pyplot as pltfrom torchvision import transforms, datasetsfrom torch.utils import data"""Olivetti face dataset"""from sklearn.datasets import fetch_olivetti_faces# Olivetti dataset downloadolivetti = fetch_olivetti_faces()train = olivetti.imageslabel = olivetti.targetX = trainY = labelprint("Format for X:", X.shape)print("Format for Y: ", Y.shape)print("\nDownload Ok")"""Set for train"""train_rate = 0.8X_train = np.zeros([int(train_rate * X.shape[0]),64,64], dtype=float)Y_train = np.zeros([int(train_rate * X.shape[0])], dtype=int)X_val = np.zeros([int((1-train_rate) * X.shape[0]+1),64,64], dtype=float)Y_val = np.zeros([int((1-train_rate) * X.shape[0]+1)], dtype=int)#Split data for train and validationfor i in range(X.shape[0]):    ie=0    iv=0    if (i%10)/10 >= train_rate:        X_train[ie] = X[i]        Y_train[ie] = Y[i]        ie += 1    else:        X_val[iv] = X[i]        Y_val[iv] = Y[i]        iv += 1X_train = X_train.reshape(320,-1,64,64)X_val = X_val.reshape(80,-1,64,64)print(Y_train.shape)X_train = torch.Tensor(X_train)Y_train = torch.Tensor(Y_train)X_val = torch.Tensor(X_val)Y_val = torch.Tensor(Y_val)  batch_size = 20train_loader = torch.utils.data.DataLoader(X_train,                                             batch_size=batch_size,                                            )val_loader = torch.utils.data.DataLoader(X_val,                                             batch_size=batch_size,                                             )class CNNModule(nn.Module):    def __init__(self):        super(CNNModule, self).__init__()        self.conv1 = nn.Conv2d(1, 6, 5)        self.pool = nn.MaxPool2d(2, 2)        self.conv2 = nn.Conv2d(6, 16, 5)        self.fc1 = nn.Linear(16 * 13 * 13, 120)        self.fc2 = nn.Linear(120, 84)        self.fc3 = nn.Linear(84, 40)    def forward(self, x):        x = self.pool(F.relu(self.conv1(x)))        x = self.pool(F.relu(self.conv2(x)))        x = x.view(-1, 16 * 13 * 13)        x = F.relu(self.fc1(x))        x = F.relu(self.fc2(x))        x = self.fc3(x)        return xdef make_train(model,dataset,n_iters,gpu):    # Organize data    X_train,Y_train,X_val,Y_val = dataset    kriter = nn.CrossEntropyLoss()    optimizer = torch.optim.SGD(model.parameters(),lr=0.01)    #Arrays to save loss and accuracy    tl=np.zeros(n_iters)    #For train loss    ta=np.zeros(n_iters)    #For train accuracy    vl=np.zeros(n_iters)    #For validation loss    va=np.zeros(n_iters)    #For validation accuracy    # Convert labels to long    Y_train = Y_train.long()    Y_val = Y_val.long()    # GPU control    if gpu:        X_train,Y_train = X_train.cuda(),Y_train.cuda()        X_val,Y_val = X_val.cuda(),Y_val.cuda()        model = model.cuda() # Parameters to GPU!        print("Using GPU")    else:        print("Using CPU")        # print(X_train.shape)        # print(Y_train.shape)    for i in range(n_iters):          # train forward        train_out = model.forward(X_train)        train_loss = kriter(train_out,Y_train)        # Backward and optimization        train_loss.backward()        optimizer.step()        optimizer.zero_grad()        # Compute train accuracy        train_predict = train_out.cpu().detach().argmax(dim=1)        train_accuracy = (train_predict.cpu().numpy()==Y_train.cpu().numpy()).mean()         # For validation        val_out = model.forward(X_val)        val_loss = kriter(val_out,Y_val)        # Compute validation accuracy        val_predict = val_out.cpu().detach().argmax(dim=1)        val_accuracy = (val_predict.cpu().numpy()==Y_val.cpu().numpy()).mean()        tl[i] = train_loss.cpu().detach().numpy()        ta[i] = train_accuracy        vl[i] = val_loss.cpu().detach().numpy()        va[i] = val_accuracy        # Show result each 5 loop        if i%5==0:            print("Loop --> ",i)            print("Train Loss :",train_loss.cpu().detach().numpy())            print("Train Accuracy :",train_accuracy)            print("Validation Loss :",val_loss.cpu().detach().numpy())            print("Validation Accuracy :",val_accuracy)    model = model.cpu()    #Print result    plt.subplot(2,2,1)    plt.plot(np.arange(n_iters), tl, 'r-')    plt.subplot(2,2,2)    plt.plot(np.arange(n_iters), ta, 'b--')    plt.subplot(2,2,3)    plt.plot(np.arange(n_iters), vl, 'r-')    plt.subplot(2,2,4)    plt.plot(np.arange(n_iters), va, 'b--')    dataset = X_train,Y_train,X_val,Y_valgpu =  Truegpu = gpu and torch.cuda.is_available() model = CNNModule()make_train(model,dataset,100,gpu)

输出:

使用CPULoop –> 0训练损失 : 3.6302185训练准确率 : 0.0验证损失 : 3.6171098验证准确率 : 0.0Loop –> 5训练损失 : 3.557933训练准确率 : 0.996875验证损失 : 3.545982验证准确率 : 0.9875…Loop –> 95训练损失 : 0.04211783训练准确率 : 0.996875验证损失 : 0.13397054验证准确率 : 0.9875

回答：

从你的代码看，

train_accuracy = (train_predict.cpu().numpy()==Y_train.cpu().numpy()).mean()你计算的是正确值的平均值，这就是为什么你在每个循环中得到相同的结果。相反，你应该用总的正确数除以总的样本数来计算准确率。