處理多類別分類任務時，可以使用Lasagne庫中的NeuralNetwork類來構建神經網絡模型。以下是一個示例代碼，展示如何在Lasagne中處理多類別分類任務：

import lasagne
import theano
import theano.tensor as T

# 定義輸入數據和標簽的符號變量
input_var = T.tensor4('inputs')
target_var = T.ivector('targets')

# 構建神經網絡模型
network = lasagne.layers.InputLayer(shape=(None, num_channels, input_height, input_width), input_var=input_var)
network = lasagne.layers.Conv2DLayer(network, num_filters=32, filter_size=(3,3), nonlinearity=lasagne.nonlinearities.rectify)
network = lasagne.layers.MaxPool2DLayer(network, pool_size=(2,2))
network = lasagne.layers.Conv2DLayer(network, num_filters=64, filter_size=(3,3), nonlinearity=lasagne.nonlinearities.rectify)
network = lasagne.layers.MaxPool2DLayer(network, pool_size=(2,2))
network = lasagne.layers.DenseLayer(lasagne.layers.dropout(network, p=0.5), num_units=256, nonlinearity=lasagne.nonlinearities.rectify)
network = lasagne.layers.DenseLayer(lasagne.layers.dropout(network, p=0.5), num_units=num_classes, nonlinearity=lasagne.nonlinearities.softmax)

# 定義損失函數和更新規則
prediction = lasagne.layers.get_output(network)
loss = lasagne.objectives.categorical_crossentropy(prediction, target_var)
loss = loss.mean()
params = lasagne.layers.get_all_params(network, trainable=True)
updates = lasagne.updates.adam(loss, params)

# 編譯訓練函數和測試函數
train_fn = theano.function([input_var, target_var], loss, updates=updates)
test_fn = theano.function([input_var, target_var], loss)

# 訓練模型
for epoch in range(num_epochs):
    train_loss = 0
    for batch in iterate_minibatches(X_train, y_train, batch_size):
        inputs, targets = batch
        train_loss += train_fn(inputs, targets)
    train_loss /= len(X_train)
    
    test_loss = 0
    for batch in iterate_minibatches(X_test, y_test, batch_size):
        inputs, targets = batch
        test_loss += test_fn(inputs, targets)
    test_loss /= len(X_test)
    
    print("Epoch {}, Train loss: {}, Test loss: {}".format(epoch, train_loss, test_loss))

在上面的代碼中，首先定義了輸入數據和標簽的符號變量，然后構建了一個包含卷積層、池化層和全連接層的神經網絡模型。接著定義了損失函數和更新規則，以及編譯了訓練函數和測試函數。最后，在訓練模型的循環中，通過調用訓練函數和測試函數來訓練和評估模型。

通過使用Lasagne庫，可以方便地構建和訓練深度神經網絡模型，處理多類別分類任務。