【深度学习】交叉熵和MSE的理解

先说结论：
原来，他们与维度无关，
只要维度合适，都能计算。哈哈哈哈
测试代码：

    model = Net(10,128,Config.num_output_feat)
    inputs = torch.randn(3,5,10)
    res = model(inputs)
    # 3X5
    print(res)
    label = torch.randn(3,5)
    # loss_fn mseloss的事搞定了，哈哈哈哈
    loss_fn = nn.MSELoss()
    print(loss_fn(res,label))
    a = torch.Tensor(1)
    print("aaaa===",a)
    print("bbbb===",loss_fn(a,a))
    print("cccc====",torch.Tensor([1,2]))
    print("dddd=====",loss_fn(torch.Tensor([1,2]),torch.Tensor([1,2])))

    ### 下面验证 分类损失的事
    loss_fn = nn.CrossEntropyLoss()
    # 3 X 4
    inputs = torch.Tensor([[1,2,3,4],[4,3,2,1],[0,0,1,2]])
    labels = torch.Tensor([
        [0,1,0,0],
        [1,0,0,0],
        [1,0,0,0]])
    res1 = loss_fn(inputs,labels)
    res = torch.argmax(inputs,dim=1)
    label1 = torch.argmax(labels,dim=1)
    print("res1=",res1, "res=",res,"labels=",labels,"label1=",label1,(res==label1).sum()/3)

因此，对于回归问题而言，最好可以用卷积来取代线性层！！