0

3000 個の入力、2 個の非表示ニューロン、および 3000 個の出力ニューロンを持つ単純なオートエンコーダーを作成したいと考えています。

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

トレーニング データの形状は次のとおりです。

train.shape = (3000,3)

これは、入力、ターゲット、および損失関数の定義です。

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)

1 つのエポックを実行しているだけですが、エラーが発生します。

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))

これはエラーです：

ValueError: ('shapes (3000,3) and (3000,2) notaligned: 3 (dim 1) != 3000 (dim 0)', (3000, 3), (3000, 2)) 原因となった適用ノードエラー: Dot22(inputs, W) Toposort インデックス: 3 入力タイプ: [TensorType(float64, matrix), TensorType(float64, matrix)] 入力形状: [(3000, 3), (3000, 2)] 入力ストライド: [ (24, 8), (16, 8)] 入力値: ['not shown', 'not shown'] 出力クライアント: [[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)]]

私には、自動エンコーダーのボトルネックが問題のようです。何か案は？

4

1 に答える 1