Question

我正在使用PyTorch代码在无人监督的环境中训练自定义丢失函数。但是，在训练阶段期间，损失不会在可能的时期内下降并保持不变。请参阅下面的培训代码段：

X = np.load(<data path>) #Load dataset which is a numpy array of N points with some dimension each.
num_samples, num_features = X.shape

gmm = GaussianMixture(n_components=num_classes, covariance_type='spherical')
gmm.fit(X)
z_gmm = gmm.predict(X)

R_gmm = gmm.predict_proba(X)
pre_R = Variable(torch.log(torch.from_numpy(R_gmm + 1e-8)).type(dtype), requires_grad=True)
R = torch.nn.functional.softmax(pre_R)

F = torch.stack(Variable(torch.from_numpy(X).type(dtype), requires_grad=True))
U = Variable(torch.from_numpy(gmm.means_).type(dtype), requires_grad=False)

z_pred = torch.max(R, 1)[1]

distances = torch.sum(((F.unsqueeze(1) - U) ** 2), dim=2)
custom_loss = torch.sum(R * distances) / num_samples

learning_rate = 1e-3
opt_train= torch.optim.Adam([train_var], lr = learning_rate)
U = torch.div(torch.mm(torch.t(R), F), torch.sum(R, dim=0).unsqueeze(1)) #In place assignment with a formula over variables and hence no gradient update is needed.

for epoch in range(max_epochs+1):
    running_loss = 0.0
    for i in range(stepSize):
    # zero the parameter gradients
    opt_train.zero_grad()

    # forward + backward + optimize
    loss = custom_loss
    loss.backward(retain_graph=True)
    opt_train.step()
    running_loss += loss.data[0]

if epoch % 25 == 0:
    print(epoch, loss.data[0]) # OR running_loss also gives the same values.
    running_loss = 0.0

O/P: 0 5.8993988037109375 25 5.8993988037109375 50 5.8993988037109375 75 5.8993988037109375 100 5.8993988037109375

我在培训中遗漏了什么？我跟着这个example/tutorial。在这方面的任何帮助和指示将不胜感激。

Answer 1

尝试使用此结构进行自定义丢失功能并进行必要的更改。通过在代码中编写此语句来使用此损失函数：

criterion = Custom_Loss()

这里我展示了一个名为Custom_Loss的自定义丢失，它将输入x和y作为输入。然后它将x重新整形为与y类似，最后通过计算重新形成的x和y之间的L2差异来返回损失。这是您在训练网络中经常遇到的标准事情。

将x视为形状（5,10），将y视为形状（5,5,10）。因此，我们需要为x添加维度，然后沿添加的维度重复它以匹配y的维度。然后，（x-y）将是形状（5,5,10）。我们将不得不添加所有三个维度，即三个torch.sum（）来获得标量。

class Custom_Loss(torch.nn.Module):

def __init__(self):
    super(Regress_Loss,self).__init__()

def forward(self,x,y):
    y_shape = y.size()[1]
    x_added_dim = x.unsqueeze(1)
    x_stacked_along_dimension1 = x_added_dim.repeat(1,NUM_WORDS,1)
    diff = torch.sum((y - x_stacked_along_dimension1)**2,2)
    totloss = torch.sum(torch.sum(torch.sum(diff)))
    return totloss

自定义丢失功能在PyTorch中不会最小化

1 个答案: