Question

我想用3000输入，2个隐藏和3000个输出神经元创建一个简单的自动编码器：

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)

我只是运行一个纪元，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）和（3000,2）未对齐：3（dim 1）！= 3000（dim 0）'，（3000,3），（3000,2））应用导致错误的节点： Dot22（输入，W）Toposort索引：3输入类型：[TensorType（float64，矩阵），TensorType（float64，matrix）]输入形状：[（3000,3），（3000,2）]输入步幅：[（24,8），（16,8）]输入值：['not not 显示'，'未显示']输出客户： [[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）]]

对我而言，似乎是自动编码器的瓶颈问题。有什么想法吗？

Answer 1

刚从我的IBM大学（Erwan）获得了一些帮助，我已经将工作解决方案发布到此GIST，相关部分就是这些：

首先，让训练数据的形状正确：

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

所以这个问题已经解决，接下来的问题是在培训期间降低成本，但这是另一个topic :)

在Theano / Lasagne中创建前馈自动编码器时，尺寸错误

1 个答案: