使用Chainer对MLP进行错误训练

Question

我正试图训练和测试一个简单的多层感知器，与第一个Chainer教程完全一样，但是使用我自己的数据集而不是MNIST。这是我使用的代码(主要来自本教程)：

class MLP(Chain):
    def __init__(self, n_units, n_out):
        super(MLP, self).__init__()
        with self.init_scope():
            self.l1 = L.Linear(None, n_units)
            self.l2 = L.Linear(None, n_units)
            self.l3 = L.Linear(None, n_out)
    def __call__(self, x):
        h1 = F.relu(self.l1(x))
        h2 = F.relu(self.l2(h1))
        y = self.l3(h2)
        return y

X, X_test, y, y_test, xHeaders, yHeaders = load_train_test_data('xHeuristicData.csv', 'yHeuristicData.csv')

print 'dataset shape   X:', X.shape, '  y:', y.shape

model = MLP(100, 1)
optimizer = optimizers.SGD()
optimizer.setup(model)

train = tuple_dataset.TupleDataset(X, y)
test = tuple_dataset.TupleDataset(X_test, y_test)

train_iter = iterators.SerialIterator(train, batch_size=100, shuffle=True)
test_iter = iterators.SerialIterator(test, batch_size=100, repeat=False, shuffle=False)
updater = training.StandardUpdater(train_iter, optimizer)
trainer = training.Trainer(updater, (10, 'epoch'), out='result')

trainer.extend(extensions.Evaluator(test_iter, model))
trainer.extend(extensions.LogReport())
trainer.extend(extensions.PrintReport(['epoch', 'main/accuracy', 'validation/main/accuracy']))
trainer.extend(extensions.ProgressBar())

trainer.run()

print 'Predicted value for a test example'
print model(X_test[0])

我没有训练和打印预测值，而是在“trainer.run()”中得到以下错误：

dataset shape   X: (1003, 116)   y: (1003,)
Exception in main training loop: __call__() takes exactly 2 arguments (3 given)
Traceback (most recent call last):
  File "/usr/local/lib/python2.7/dist-packages/chainer/training/trainer.py", line 299, in run
    update()
  File "/usr/local/lib/python2.7/dist-packages/chainer/training/updater.py", line 223, in update
    self.update_core()
  File "/usr/local/lib/python2.7/dist-packages/chainer/training/updater.py", line 234, in update_core
    optimizer.update(loss_func, *in_arrays)
  File "/usr/local/lib/python2.7/dist-packages/chainer/optimizer.py", line 534, in update
    loss = lossfun(*args, **kwds)
Will finalize trainer extensions and updater before reraising the exception.
Traceback (most recent call last):
  File "trainHeuristicChainer.py", line 76, in <module>
    trainer.run()
  File "/usr/local/lib/python2.7/dist-packages/chainer/training/trainer.py", line 313, in run
    six.reraise(*sys.exc_info())
  File "/usr/local/lib/python2.7/dist-packages/chainer/training/trainer.py", line 299, in run
    update()
  File "/usr/local/lib/python2.7/dist-packages/chainer/training/updater.py", line 223, in update
    self.update_core()
  File "/usr/local/lib/python2.7/dist-packages/chainer/training/updater.py", line 234, in update_core
    optimizer.update(loss_func, *in_arrays)
  File "/usr/local/lib/python2.7/dist-packages/chainer/optimizer.py", line 534, in update
    loss = lossfun(*args, **kwds)
TypeError: __call__() takes exactly 2 arguments (3 given)

我不知道如何处理这个错误。我使用其他框架成功地训练了类似的网络，但我对Chainer很感兴趣，因为它与PyPy兼容。

包含这些文件的tgz可以在这里获得：https://mega.nz/#!wwsBiSwY!g72pC5ZgekeMiVr-UODJOqQfQZZU3lCqm9Er2jH4UD8

Answer 1

您正在将(X, y)的元组发送到MLP中，而实现的__call__只接受x。

可以将实现修改为

class MLP(Chain):
    def __init__(self, n_units, n_out):
        super(MLP, self).__init__()
        with self.init_scope():
            self.l1 = L.Linear(None, n_units)
            self.l2 = L.Linear(None, n_units)
            self.l3 = L.Linear(None, n_out)
    def __call__(self, x, y):
        h1 = F.relu(self.l1(x))
        h2 = F.relu(self.l2(h1))
        predict = self.l3(h2)
        loss = F.squared_error(predict, y)
        // or you can write it on your own as follows
        // loss = F.sum(F.square(predict - y))
        return loss

默认情况下，标准更新程序假定__call__为丢失函数，在chainer中可能与其他框架不同。因此，调用model(X, y)将返回当前迷你批处理的损失。这就是为什么chainer教程引入了另一个Classifier类来计算损失函数并保持MLP简单。分类器在MNIST中是有意义的，但不适合您的任务，所以您需要自己来实现丢失函数。

当您完成培训后，您可以只保存模型实例(可能通过在训练器中添加snapshot_object的扩展)。

要使用保存的模型，就像在测试中一样，您必须在类中使用与当前__call__相同的代码在类中编写另一个可能命名为test的方法，该方法只有X输入，因此不需要其他y。

此外，如果您不喜欢在MLP类中添加任何额外的方法，使其变得纯净，那么您需要自己编写更新程序并更自然地计算损失函数。为了更容易地继承标准，您可以按以下方式编写它，

class MyUpdater(chainer.training.StandardUpdater):
    def __init__(self, data_iter, model, opt, device=-1):
        super(MyUpdater, self).__init__(data_iter, opt, device=device)
        self.mlp = model

    def update_core(self):
        batch = self.get_iterator('main').next()
        x, y = self.converter(batch, self.device)
        predict = self.mlp(x)
        loss = F.squared_error(predict, y)
        self.mlp.cleargrads()
        loss.backward()
        self.get_iterator('main').update()

updater = MyUpdater(train_iter, model, optimizer)