0

我想创建一个具有 3000 个输入、2 个隐藏和 3000 个输出神经元的简单自动编码器：

def build_autoencoder(input_var=None):
    l_in = InputLayer(shape=(None,3000), input_var=input_var)

    l_hid = DenseLayer(
            l_in, num_units=2,
            nonlinearity=rectify,
            W=lasagne.init.GlorotUniform())

    l_out = DenseLayer(
            l_hid, num_units=3000,
            nonlinearity=softmax)

    return l_out

训练数据的形状如下：

train.shape = (3000,3)

这是输入、目标和损失函数定义：

import sys
import os
import time
import numpy as np
import theano
import theano.tensor as T
import lasagne
from lasagne.updates import rmsprop
from lasagne.layers import DenseLayer, DropoutLayer, InputLayer
from lasagne.nonlinearities import rectify, softmax
from lasagne.objectives import categorical_crossentropy
# Creating the Theano variables
input_var = T.dmatrix('inputs')
target_var = T.dmatrix('targets')

# Building the Theano expressions on these variables
network = build_autoencoder(input_var)

prediction = lasagne.layers.get_output(network)
loss = categorical_crossentropy(prediction, target_var)
loss = loss.mean()

test_prediction = lasagne.layers.get_output(network,
                                                    deterministic=True)
test_loss = categorical_crossentropy(test_prediction, target_var)
test_loss = test_loss.mean()
test_acc = T.mean(T.eq(T.argmax(test_prediction, axis=1), target_var),
                          dtype=theano.config.floatX)

我只是运行一个时代，但得到一个错误：

params = lasagne.layers.get_all_params(network, trainable=True)
updates = rmsprop(loss, params, learning_rate=0.001)

# Compiling the graph by declaring the Theano functions

train_fn = theano.function([input_var, target_var],
                                   loss, updates=updates)
val_fn = theano.function([input_var, target_var],
                                 [test_loss, test_acc])

# For loop that goes each time through the hole training
# and validation data
print("Starting training...")
for epoch in range(1):

    # Going over the training data
    train_err = 0
    train_batches = 0
    start_time = time.time()
    print 'test1'
    train_err += train_fn(train, train)
    train_batches += 1

    # Going over the validation data
    val_err = 0
    val_acc = 0
    val_batches = 0
    err, acc = val_fn(train, train)
    val_err += err
    val_acc += acc
    val_batches += 1

    # Then we print the results for this epoch:
    print("Epoch {} of {} took {:.3f}s".format(epoch + 1, num_epochs, time.time() - start_time))
    print("training loss:\t\t{:.6f}".format(train_err / train_batches))
    print("validation loss:\t\t{:.6f}".format(val_err / val_batches))
    print("validation accuracy:\t\t{:.2f} %".format(val_acc / val_batches * 100))

这是错误：

ValueError: ('shapes (3000,3) and (3000,2) not aligned: 3 (dim 1) != 3000 (dim 0)', (3000, 3), (3000, 2)) 应用导致错误：Dot22(inputs, W) 拓扑排序索引：3 输入类型：[TensorType(float64, matrix), TensorType(float64, matrix)] 输入形状：[(3000, 3), (3000, 2)] 输入步幅：[ (24, 8), (16, 8)] 输入值：['未显示'，'未显示'] 输出客户端：[[Elemwise{add,no_inplace}(Dot22.0, InplaceDimShuffle{x,0}.0 ), Elemwise{Composite{(i0 * (Abs(i1) + i2 + i3))}}[(0, 2)](TensorConstant{(1, 1) of 0.5}, Elemwise{add,no_inplace}.0, Dot22.0, InplaceDimShuffle{x,0}.0)]]

在我看来，自动编码器的瓶颈似乎是问题所在。有任何想法吗？

4

1 回答 1

0

刚刚从我的 IBM 学院 ( Erwan ) 那里得到了一些帮助，我已经将工作解决方案发布到了这个GIST，相关部分是这些：

首先，正确获取训练数据的形状：

train.shape = (3, 3000)

然后在 InputLayer 上使用相同的形状：

def build_autoencoder(input_var=None):
    l_in = InputLayer(shape=(3, 3000), input_var=input_var)

    l_hid = DenseLayer(
            l_in, num_units=2,
            nonlinearity=rectify,
            W=lasagne.init.GlorotUniform())

    l_out = DenseLayer(
            l_hid, num_units=3000,
            nonlinearity=softmax)

return l_out

所以这个问题解决了，下一个问题是在训练期间降低成本，但这是另一个话题:)

于 2016-09-05T17:30:02.053 回答