如何解决:" ValueError:没有足够的尺寸在Elemwise {neg,no_inplace} .0上减少轴5000和#34;?

时间:2016-01-19 09:04:04

标签: python matlab theano conv-neural-network

我正在尝试使用DeepLearning教程中讲授的CNN代码(Convolutional_mlp.py)对大小为166x166(Matlab裁剪)的图像进行分类。输入是.mat文件,其中X_2k.mat用于输入图像像素值,y_2k.mat用于这些图像的输出标签。目前,我们提供2115张图像及其标签作为训练数据,测试数据和验证数据。我已经将从.mat文件中获得的numpy nd数组转换为相应数据类型的相应Tensor共享变量,即从uint8矩阵转换为X的float64矩阵,并转换为Y的int32向量。(另请注释此部分在代码),为了解决错误"在X"的情况下,不能将张量类型(uint8,矩阵)转换为张量类型(浮点数64,矩阵),这在给出.mat输入时发生。图像有3个类,0,1和2.但需要帮助解决错误:" ValueError:没有足够的尺寸在Elemwise上{neg,no_inplace} .0来减少轴5000"

import os
import sys
import timeit
import random
import numpy
import cPickle
import gzip
import scipy.io as sio
from random import shuffle
import theano
from theano.tensor import *
import theano.tensor as T
from theano.tensor.signal import downsample
from theano.tensor.nnet import conv

from logistic_sgd import LogisticRegression, load_data
from mlp import HiddenLayer



class LeNetConvPoolLayer(object):
    """Pool Layer of a convolutional network """

    def __init__(self, rng, input, filter_shape, image_shape, poolsize=(2, 2)):
        """
        Allocate a LeNetConvPoolLayer with shared variable internal parameters.

        :type rng: numpy.random.RandomState
        :param rng: a random number generator used to initialize weights

        :type input: theano.tensor.dtensor4
        :param input: symbolic image tensor, of shape image_shape

        :type filter_shape: tuple or list of length 4
        :param filter_shape: (number of filters, num input feature maps,
                              filter height, filter width) #FILTER IS LOCAL RECEPTIVE FIELD

        :type image_shape: tuple or list of length 4
        :param image_shape: (batch size, num input feature maps,
                             image height, image width)

        :type poolsize: tuple or list of length 2
        :param poolsize: the downsampling (pooling) factor (#rows, #cols)
        """

        assert image_shape[1] == filter_shape[1]
        self.input = input

        # there are "num input feature maps * filter height * filter width"
        # inputs to each hidden unit
        fan_in = numpy.prod(filter_shape[1:])
        # each unit in the lower layer receives a gradient from:
        # "num output feature maps * filter height * filter width" /
        #   pooling size
        fan_out = (filter_shape[0] * numpy.prod(filter_shape[2:]) /
                   numpy.prod(poolsize))
        # initialize weights with random weights
        W_bound = numpy.sqrt(6. / (fan_in + fan_out))
        self.W = theano.shared(
            numpy.asarray(
                rng.uniform(low=-W_bound, high=W_bound, size=filter_shape),
                dtype=theano.config.floatX
            ),
            borrow=True
        )

        # the bias is a 1D tensor -- one bias per output feature map
        b_values = numpy.zeros((filter_shape[0],), dtype=theano.config.floatX)
        self.b = theano.shared(value=b_values, borrow=True)

        # convolve input feature maps with filters
        conv_out = conv.conv2d(
            input=input,
            filters=self.W,
            filter_shape=filter_shape,
            image_shape=image_shape
        )

        # downsample each feature map individually, using maxpooling
        pooled_out = downsample.max_pool_2d(
            input=conv_out,
            ds=poolsize,
            ignore_border=True
        )

        # add the bias term. Since the bias is a vector (1D array), we first
        # reshape it to a tensor of shape (1, n_filters, 1, 1). Each bias will
        # thus be broadcasted across mini-batches and feature map
        # width & height
        self.output = T.tanh(pooled_out + self.b.dimshuffle('x', 0, 'x', 'x'))


        # store parameters of this layer
        self.params = [self.W, self.b]

        # keep track of model input
        self.input = input


def evaluate_lenet5(learning_rate=0.1, n_epochs=200,
                    dataset='mnist.pkl.gz',
                    nkerns=[20, 50], batch_size=500):
    """ Demonstrates lenet on MNIST dataset

    :type learning_rate: float
    :param learning_rate: learning rate used (factor for the stochastic
                          gradient)

    :type n_epochs: int
    :param n_epochs: maximal number of epochs to run the optimizer AKA ITERATIONS

    :type dataset: string
    :param dataset: path to the dataset used for training /testing (MNIST here)

    :type nkerns: list of ints
    :param nkerns: number of kernels on each layer
    """
    matx = sio.loadmat('X_2k.mat')
    datax = matx['X']
    datax=datax.transpose()
    maty = sio.loadmat('y_2k.mat')
    datay = maty['M']           #M was used while creating the y MAT file
    training_data = (datax , datay)
    validation_data = training_data
    test_data = training_data

    train_set_x = training_data[0]
    train_set_y = training_data[1]
    valid_set_x = training_data[0]
    valid_set_y = training_data[1]
    test_set_x = training_data[0]
    test_set_y = training_data[1]
    rng = numpy.random.RandomState(23455)

    print ' type of train_set_x '
    print train_set_x.dtype


    train_set_x=numpy.ndarray.astype(train_set_x,dtype='float64') #converted from uint8 to float64 matrix
    valid_set_x=numpy.ndarray.astype(valid_set_x,dtype='float64')
    test_set_x=numpy.ndarray.astype(test_set_x,dtype='float64')



    train_set_y=numpy.ndarray.astype(train_set_y,dtype='int32') #converted from uint8 to int32 matrix
    valid_set_y=numpy.ndarray.astype(valid_set_y,dtype='int32')
    test_set_y=numpy.ndarray.astype(test_set_y,dtype='int32')
    train_set_y=train_set_y.reshape((-1,))                      #converted from int32 matrix to int32 vector
    valid_set_y=valid_set_y.reshape((-1,))
    test_set_y=test_set_y.reshape((-1,))

    print train_set_x.dtype
    print 'printing for y'
    print train_set_y.dtype
    train_set_xx=theano.shared(train_set_x)
    train_set_yy=theano.shared(train_set_y)

    valid_set_xx=theano.shared(valid_set_x)
    valid_set_yy=theano.shared(valid_set_y)

    test_set_xx=theano.shared(test_set_x)
    test_set_yy=theano.shared(test_set_y)
    '''datasets = load_data(dataset)

    train_set_x, train_set_y = datasets[0]
    valid_set_x, valid_set_y = datasets[1]
    test_set_x, test_set_y = datasets[2]'''

    print training_data
    print 'datax:  '
    print datax
    print 'datay:  '
    print datay
    print '  '
    print 'type of train_set_xx is :'
    print train_set_xx.type

    print 'type of train_set_yy is :'
    print train_set_yy.type
    print '  '

    # compute number of minibatches for training, validation and testing
    n_train_batches = train_set_xx.get_value(borrow=True).shape[0]
    n_valid_batches = valid_set_xx.get_value(borrow=True).shape[0]
    n_test_batches = test_set_xx.get_value(borrow=True).shape[0]
    n_train_batches /= batch_size
    n_valid_batches /= batch_size
    n_test_batches /= batch_size

    # allocate symbolic variables for the data
    index = T.lscalar()  # index to a [mini]batch

    # start-snippet-1
    x = T.matrix('x')   # the data is presented as rasterized images
    y = T.ivector('y')  # the labels are presented as 1D vector of
                        # [int] labels
    print 'type of x is:'
    print x.type
    print 'type of y is :'
    print y.type


    ######################
    # BUILD ACTUAL MODEL #
    ######################
    print '... building the model'

    # Reshape matrix of rasterized images of shape (batch_size, 28 * 28)
    # to a 4D tensor, compatible with our LeNetConvPoolLayer
    # (28, 28) is the size of MNIST images.
    layer0_input = x.reshape((batch_size, 1, 166, 166))
    print ' LAYER 0 INPUT IS:'
    print layer0_input

    # Construct the first convolutional pooling layer:
    # filtering reduces the image size to (28-5+1 , 28-5+1) = (24, 24)
    # maxpooling reduces this further to (24/2, 24/2) = (12, 12)
    # 4D output tensor is thus of shape (batch_size, nkerns[0], 12, 12)
    layer0 = LeNetConvPoolLayer(
        rng,
        input=layer0_input,
        image_shape=(batch_size, 1, 166, 166),
        filter_shape=(nkerns[0], 1, 11, 11),
        poolsize=(2, 2)
    )

    # Construct the second convolutional pooling layer
    # filtering reduces the image size to (12-5+1, 12-5+1) = (8, 8)
    # maxpooling reduces this further to (8/2, 8/2) = (4, 4)
    # 4D output tensor is thus of shape (batch_size, nkerns[1], 4, 4)
    layer1 = LeNetConvPoolLayer(
        rng,
        input=layer0.output,
        image_shape=(batch_size, nkerns[0], 78, 78),
        filter_shape=(nkerns[1], nkerns[0], 11, 11),
        poolsize=(2, 2)
    )

    # the HiddenLayer being fully-connected, it operates on 2D matrices of
    # shape (batch_size, num_pixels) (i.e matrix of rasterized images).
    # This will generate a matrix of shape (batch_size, nkerns[1] * 4 * 4),
    # or (500, 50 * 4 * 4) = (500, 800) with the default values.
    layer2_input = layer1.output.flatten(2)

    # construct a fully-connected sigmoidal layer
    layer2 = HiddenLayer(
        rng,
        input=layer2_input,
        n_in=nkerns[1] * 34 * 34,
        n_out=500,
        activation=T.tanh
    )

    # classify the values of the fully-connected sigmoidal layer
    layer3 = LogisticRegression(input=layer2.output, n_in=500, n_out=3)

    # the cost we minimize during training is the NLL of the model
    cost = layer3.negative_log_likelihood(y)

    # create a function to compute the mistakes that are made by the model
    test_model = theano.function(
        [index],
        layer3.errors(y),
        givens={
            x: test_set_xx[index * batch_size: (index + 1) * batch_size],
            y: test_set_yy[index * batch_size: (index + 1) * batch_size]
        }
    )
#type of x is float64,matrix
    validate_model = theano.function(
        [index],
        layer3.errors(y),
        givens={
            x: valid_set_xx[index * batch_size: (index + 1) * batch_size],
            y: valid_set_yy[index * batch_size: (index + 1) * batch_size]
        }
    )

    # create a list of all model parameters to be fit by gradient descent
    params = layer3.params + layer2.params + layer1.params + layer0.params

    # create a list of gradients for all model parameters
    grads = T.grad(cost, params)

    # train_model is a function that updates the model parameters by
    # SGD Since this model has many parameters, it would be tedious to
    # manually create an update rule for each model parameter. We thus
    # create the updates list by automatically looping over all
    # (params[i], grads[i]) pairs.
    updates = [
        (param_i, param_i - learning_rate * grad_i)
        for param_i, grad_i in zip(params, grads)
    ]

    train_model = theano.function(
        [index],
        cost,
        updates=updates,
        givens={
            x: train_set_xx[index * batch_size: (index + 1) * batch_size],
            y: train_set_yy[index * batch_size: (index + 1) * batch_size]
        }
    )
    # end-snippet-1

    ###############
    # TRAIN MODEL #
    ###############
    print '... training'
    # early-stopping parameters
    patience = 10000  # look as this many examples regardless
    patience_increase = 2  # wait this much longer when a new best is
                           # found
    improvement_threshold = 0.995  # a relative improvement of this much is
                                   # considered significant
    validation_frequency = min(n_train_batches, patience / 2)  #Error on this Line !!!!
                                  # go through this many
                                  # minibatche before checking the network
                                  # on the validation set; in this case we
                                  # check every epoch

    best_validation_loss = numpy.inf
    best_iter = 0
    test_score = 0.
    start_time = timeit.default_timer()

    epoch = 0
    done_looping = False

    while (epoch < n_epochs) and (not done_looping):
        epoch = epoch + 1
        for minibatch_index in xrange(n_train_batches):

            iter = (epoch - 1) * n_train_batches + minibatch_index

            if iter % 100 == 0:
                print 'training @ iter = ', iter
            cost_ij = train_model(minibatch_index)

            if (iter + 1) % validation_frequency == 0:

                # compute zero-one loss on validation set
                validation_losses = [validate_model(i) for i
                                     in xrange(n_valid_batches)]
                this_validation_loss = numpy.mean(validation_losses)
                print('epoch %i, minibatch %i/%i, validation error %f %%' %
                      (epoch, minibatch_index + 1, n_train_batches,
                       this_validation_loss * 100.))

                # if we got the best validation score until now
                if this_validation_loss < best_validation_loss:

                    #improve patience if loss improvement is good enough
                    if this_validation_loss < best_validation_loss *  \
                       improvement_threshold:
                        patience = max(patience, iter * patience_increase)

                    # save best validation score and iteration number
                    best_validation_loss = this_validation_loss
                    best_iter = iter

                    # test it on the test set
                    test_losses = [
                        test_model(i)
                        for i in xrange(n_test_batches)
                    ]
                    test_score = numpy.mean(test_losses)
                    print(('     epoch %i, minibatch %i/%i, test error of '
                           'best model %f %%') %
                          (epoch, minibatch_index + 1, n_train_batches,
                           test_score * 100.))

            if patience <= iter:
                done_looping = True
                break

    end_time = timeit.default_timer()
    print('Optimization complete.')
    print('Best validation score of %f %% obtained at iteration %i, '
          'with test performance %f %%' %
          (best_validation_loss * 100., best_iter + 1, test_score * 100.))
    print >> sys.stderr, ('The code for file ' +
                          os.path.split(__file__)[1] +
                          ' ran for %.2fm' % ((end_time - start_time) / 60.))

if __name__ == '__main__':
    evaluate_lenet5()


def experiment(state, channel):
    evaluate_lenet5(state.learning_rate, dataset=state.dataset)

输出:

sweta@sweta-HP-Pavilion-15-Notebook-PC:~//Deep_nn$ python convolutional_mlp.py optimizer=fast_compile exception_verbosity=high

 type of train_set_x 

uint8

float64

printing for y

int32
(array([[164, 164, 164, ..., 164, 164,   0],
       [164, 164, 164, ..., 156, 164,   0],
       [164, 164, 164, ..., 164, 164,   0],
       ..., 
       [164,  92,  82, ..., 247, 247,   0],
       [156, 156,  82, ..., 247, 247,   0],
       [164, 156,  82, ..., 247, 247,   0]], dtype=uint8), array([[1],
       [1],
       [1],
       ..., 
       [0],
       [0],
       [0]], dtype=uint8))
datax:  

[[164 164 164 ..., 164 164   0]
 [164 164 164 ..., 156 164   0]
 [164 164 164 ..., 164 164   0]
 ..., 
 [164  92  82 ..., 247 247   0]
 [156 156  82 ..., 247 247   0]
 [164 156  82 ..., 247 247   0]]
datay:  
[[1]
 [1]
 [1]
 ..., 
 [0]
 [0]
 [0]]


type of train_set_xx is :

TensorType(float64, matrix)

type of train_set_yy is :

TensorType(int32, vector)


type of x is:

TensorType(float64, matrix)

type of y is :

TensorType(int32, vector)


... building the model

 LAYER 0 INPUT IS:

Reshape{4}.0

... training




Traceback (most recent call last):

  File "convolutional_mlp.py", line 410, in <module>
    evaluate_lenet5()

  File "convolutional_mlp.py", line 339, in evaluate_lenet5
    validation_frequency = min(n_train_batches, patience / 2)

  File "/usr/local/lib/python2.7/dist-packages/theano/tensor/basic.py", line 1582, in min
    return -max(-x, axis=axis, keepdims=keepdims)

  File "/usr/local/lib/python2.7/dist-packages/theano/tensor/basic.py", line 1537, in max
    out = CAReduce(scal.maximum, axis)(x)

  File "/usr/local/lib/python2.7/dist-packages/theano/gof/op.py", line 507, in __call__
    node = self.make_node(*inputs, **kwargs)

  File "/usr/local/lib/python2.7/dist-packages/theano/tensor/elemwise.py", line 1314, in make_node
    % (input, axis)))


ValueError: Not enough dimensions on Elemwise{neg,no_inplace}.0 to reduce on axis 5000

1 个答案:

答案 0 :(得分:1)

有一个名为'min'的内置函数被覆盖,因为你已经从张量中导入了所有内容。在第339行,尝试使用__ builtin__ .min作为函数调用。