如何为不同的输入重用计算图? [英] How to reuse computation graph for different inputs?

问题描述

我设置了主要的计算流程，可以使用

I have my main flow of computation set up that I can train using

train = theano.function(inputs=[x], outputs=[cost], updates=updates)

同样，我有一个预测功能

Similarly, I have a function for predictions

predict = theano.function(inputs=[x], outputs=[output])

这两个函数都接受输入 x 并通过相同的计算图发送它.

Both of these functions accept the input x and send it through the same computation graph.

我现在想修改一些东西，以便在训练时，我可以使用嘈杂的输入进行训练，所以我有类似的东西

I would now like to modify things so that when training, I can train using a noisy input, so I have something like

input = get_corrupted_input(self.theano_rng, x, 0.5)

在计算开始时.

但这也会影响我的 predict 函数，因为它的输入也会被破坏.如何为 train 和 predict 重用相同的代码，但只为前者提供嘈杂的输入?

But this will also affect my predict function, since its input will get corrupted as well. How can I reuse the same code for train and predict, but only provide the former with the noisy input?

推荐答案

你可以这样组织你的代码:

You can organise your code like this:

import numpy
import theano
import theano.tensor as tt
import theano.tensor.shared_randomstreams


def get_cost(x, y):
    return tt.mean(tt.sum(tt.sqr(x - y), axis=1))


def get_output(x, w, b_h, b_y):
    h = tt.tanh(tt.dot(x, w) + b_h)
    y = tt.dot(h, w.T) + b_y
    return y


def corrupt_input(x, corruption_level):
    rng = tt.shared_randomstreams.RandomStreams()
    return rng.binomial(size=x.shape, n=1, p=1 - corruption_level,
                        dtype=theano.config.floatX) * x


def compile(input_size, hidden_size, corruption_level, learning_rate):
    x = tt.matrix()
    w = theano.shared(numpy.random.randn(input_size,
                      hidden_size).astype(theano.config.floatX))
    b_h = theano.shared(numpy.zeros(hidden_size, dtype=theano.config.floatX))
    b_y = theano.shared(numpy.zeros(input_size, dtype=theano.config.floatX))
    cost = get_cost(x, get_output(corrupt_input(x, corruption_level), w, b_h, b_y))
    updates = [(p, p - learning_rate * tt.grad(cost, p)) for p in (w, b_h, b_y)]
    train = theano.function(inputs=[x], outputs=cost, updates=updates)
    predict = theano.function(inputs=[x], outputs=get_output(x, w, b_h, b_y))
    return train, predict


def main():
    train, predict = compile(input_size=3, hidden_size=2,
                             corruption_level=0.2, learning_rate=0.01)


main()

请注意，get_output 被调用了两次.对于 train 函数，它提供了损坏的输入，但对于 predict 函数，它提供了干净的输入.get_output 需要包含您所说的相同的计算图".我只是在里面放了一个很小的自动编码器，但你可以在里面放任何你想要的东西.

Note that get_output is called twice. For the train function it is provided with the corrupted input but for the predict function it is provided with the clean input. get_output needs to contain "the same computation graph" that you talk of. I've just put a tiny autoencoder in there but you can put whatever you want in there.

假设损坏的输入与输入具有相同的形状，get_output 函数不会关心它的输入是 x 还是 x 的损坏版本.所以 get_output 可以共享但不需要包含损坏代码.

Assuming the corrupted input has the same shape as the input, the get_output function won't care whether its input is x or the corrupted version of x. So get_output can be shared but need not contain the corruption code.

这篇关于如何为不同的输入重用计算图?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！