def __init__(self, np_rng = None,**kwargs):

        self.word_ids = T.imatrix('input')

        self.word_num = kwargs['word_num']
        self.window_size = kwargs['window_size']
        self.feature_num = kwargs['feature_num']
        self.hidden_layer_size = kwargs['hidden_layer_size']
        self.n_outs = kwargs['n_outs']


        self.lookup_table_layer = LookupTableLayer(self.word_num,self.feature_num)

        self.hidden_layer = HiddenLayer(rng=np_rng, input=self.lookup_table_layer.output(self.word_ids),
                                       n_in = self.window_size * self.feature_num,
                                       n_out = self.hidden_layer_size,
                                       activation=T.tanh)

        # The logistic regression layer gets as input the hidden units
        # of the hidden layer
        self.output_layer = SoftMaxLayer(
                                        input=self.hidden_layer.output,
                                        n_in=self.hidden_layer_size,
                                        n_out=self.n_outs)

        self.params = self.lookup_table_layer.params() + \
                self.hidden_layer.params() + \
                self.output_layer.params()
Beispiel #2
0
    def __init__(self, numpy_rng, theano_rng=None, n_ins=784,
                 hidden_layers_sizes=[500, 500], n_outs=10,
                 corruption_levels=[0.1, 0.1]):
        """ This class is made to support a variable number of layers.

        :type numpy_rng: numpy.random.RandomState
        :param numpy_rng: numpy random number generator used to draw initial
                    weights

        :type theano_rng: theano.tensor.shared_randomstreams.RandomStreams
        :param theano_rng: Theano random generator; if None is given one is
                           generated based on a seed drawn from `rng`

        :type n_ins: int
        :param n_ins: dimension of the input to the sdA

        :type n_layers_sizes: list of ints
        :param n_layers_sizes: intermediate layers size, must contain
                               at least one value

        :type n_outs: int
        :param n_outs: dimension of the output of the network

        :type corruption_levels: list of float
        :param corruption_levels: amount of corruption to use for each
                                  layer
        """

        self.sigmoid_layers = []
        self.dA_layers = []
        self.params = []
        self.n_layers = len(hidden_layers_sizes)

        assert self.n_layers > 0

        if not theano_rng:
            theano_rng = RandomStreams(numpy_rng.randint(2 ** 30))
        # allocate symbolic variables for the data
        self.x = T.matrix('x')  # the data is presented as rasterized images
        self.y = T.ivector('y')  # the labels are presented as 1D vector of
                                 # [int] labels

        # The SdA is an MLP, for which all weights of intermediate layers
        # are shared with a different denoising autoencoders
        # We will first construct the SdA as a deep multilayer perceptron,
        # and when constructing each sigmoidal layer we also construct a
        # denoising autoencoder that shares weights with that layer
        # During pretraining we will train these autoencoders (which will
        # lead to chainging the weights of the MLP as well)
        # During finetunining we will finish training the SdA by doing
        # stochastich gradient descent on the MLP

        for i in xrange(self.n_layers):
            # construct the sigmoidal layer

            # the size of the input is either the number of hidden units of
            # the layer below or the input size if we are on the first layer
            if i == 0:
                input_size = n_ins
            else:
                input_size = hidden_layers_sizes[i - 1]

            # the input to this layer is either the activation of the hidden
            # layer below or the input of the SdA if you are on the first
            # layer
            if i == 0:
                layer_input = self.x
            else:
                layer_input = self.sigmoid_layers[-1].output

            sigmoid_layer = HiddenLayer(rng=numpy_rng,
                                        input=layer_input,
                                        n_in=input_size,
                                        n_out=hidden_layers_sizes[i],
                                        activation=T.nnet.sigmoid)
            # add the layer to our list of layers
            self.sigmoid_layers.append(sigmoid_layer)
            # its arguably a philosophical question...
            # but we are going to only declare that the parameters of the
            # sigmoid_layers are parameters of the StackedDAA
            # the visible biases in the dA are parameters of those
            # dA, but not the SdA
            self.params.extend(sigmoid_layer.params)

            # Construct a denoising autoencoder that shared weights with this
            # layer
            dA_layer = dA(numpy_rng=numpy_rng,
                          theano_rng=theano_rng,
                          input=layer_input,
                          n_visible=input_size,
                          n_hidden=hidden_layers_sizes[i],
                          W=sigmoid_layer.W,
                          bhid=sigmoid_layer.b)
            self.dA_layers.append(dA_layer)

        # We now need to add a logistic layer on top of the MLP
        self.logLayer = SoftMaxLayer(
                         input=self.sigmoid_layers[-1].output,
                         n_in=hidden_layers_sizes[-1], n_out=n_outs)

        self.params.extend(self.logLayer.params)
        # construct a function that implements one step of finetunining

        # compute the cost for second phase of training,
        # defined as the negative log likelihood
        self.finetune_cost = self.logLayer.negative_log_likelihood(self.y)
        # compute the gradients with respect to the model parameters
        # symbolic variable that points to the number of errors made on the
        # minibatch given by self.x and self.y
        self.errors = self.logLayer.errors(self.y)
Beispiel #3
0
class SdA(object):
    """Stacked denoising auto-encoder class (SdA)

    A stacked denoising autoencoder model is obtained by stacking several
    dAs. The hidden layer of the dA at layer `i` becomes the input of
    the dA at layer `i+1`. The first layer dA gets as input the input of
    the SdA, and the hidden layer of the last dA represents the output.
    Note that after pretraining, the SdA is dealt with as a normal MLP,
    the dAs are only used to initialize the weights.
    """

    def __init__(self, numpy_rng, theano_rng=None, n_ins=784,
                 hidden_layers_sizes=[500, 500], n_outs=10,
                 corruption_levels=[0.1, 0.1]):
        """ This class is made to support a variable number of layers.

        :type numpy_rng: numpy.random.RandomState
        :param numpy_rng: numpy random number generator used to draw initial
                    weights

        :type theano_rng: theano.tensor.shared_randomstreams.RandomStreams
        :param theano_rng: Theano random generator; if None is given one is
                           generated based on a seed drawn from `rng`

        :type n_ins: int
        :param n_ins: dimension of the input to the sdA

        :type n_layers_sizes: list of ints
        :param n_layers_sizes: intermediate layers size, must contain
                               at least one value

        :type n_outs: int
        :param n_outs: dimension of the output of the network

        :type corruption_levels: list of float
        :param corruption_levels: amount of corruption to use for each
                                  layer
        """

        self.sigmoid_layers = []
        self.dA_layers = []
        self.params = []
        self.n_layers = len(hidden_layers_sizes)

        assert self.n_layers > 0

        if not theano_rng:
            theano_rng = RandomStreams(numpy_rng.randint(2 ** 30))
        # allocate symbolic variables for the data
        self.x = T.matrix('x')  # the data is presented as rasterized images
        self.y = T.ivector('y')  # the labels are presented as 1D vector of
                                 # [int] labels

        # The SdA is an MLP, for which all weights of intermediate layers
        # are shared with a different denoising autoencoders
        # We will first construct the SdA as a deep multilayer perceptron,
        # and when constructing each sigmoidal layer we also construct a
        # denoising autoencoder that shares weights with that layer
        # During pretraining we will train these autoencoders (which will
        # lead to chainging the weights of the MLP as well)
        # During finetunining we will finish training the SdA by doing
        # stochastich gradient descent on the MLP

        for i in xrange(self.n_layers):
            # construct the sigmoidal layer

            # the size of the input is either the number of hidden units of
            # the layer below or the input size if we are on the first layer
            if i == 0:
                input_size = n_ins
            else:
                input_size = hidden_layers_sizes[i - 1]

            # the input to this layer is either the activation of the hidden
            # layer below or the input of the SdA if you are on the first
            # layer
            if i == 0:
                layer_input = self.x
            else:
                layer_input = self.sigmoid_layers[-1].output

            sigmoid_layer = HiddenLayer(rng=numpy_rng,
                                        input=layer_input,
                                        n_in=input_size,
                                        n_out=hidden_layers_sizes[i],
                                        activation=T.nnet.sigmoid)
            # add the layer to our list of layers
            self.sigmoid_layers.append(sigmoid_layer)
            # its arguably a philosophical question...
            # but we are going to only declare that the parameters of the
            # sigmoid_layers are parameters of the StackedDAA
            # the visible biases in the dA are parameters of those
            # dA, but not the SdA
            self.params.extend(sigmoid_layer.params)

            # Construct a denoising autoencoder that shared weights with this
            # layer
            dA_layer = dA(numpy_rng=numpy_rng,
                          theano_rng=theano_rng,
                          input=layer_input,
                          n_visible=input_size,
                          n_hidden=hidden_layers_sizes[i],
                          W=sigmoid_layer.W,
                          bhid=sigmoid_layer.b)
            self.dA_layers.append(dA_layer)

        # We now need to add a logistic layer on top of the MLP
        self.logLayer = SoftMaxLayer(
                         input=self.sigmoid_layers[-1].output,
                         n_in=hidden_layers_sizes[-1], n_out=n_outs)

        self.params.extend(self.logLayer.params)
        # construct a function that implements one step of finetunining

        # compute the cost for second phase of training,
        # defined as the negative log likelihood
        self.finetune_cost = self.logLayer.negative_log_likelihood(self.y)
        # compute the gradients with respect to the model parameters
        # symbolic variable that points to the number of errors made on the
        # minibatch given by self.x and self.y
        self.errors = self.logLayer.errors(self.y)

    def pretraining_functions(self, train_set_x, batch_size):
        ''' Generates a list of functions, each of them implementing one
        step in trainnig the dA corresponding to the layer with same index.
        The function will require as input the minibatch index, and to train
        a dA you just need to iterate, calling the corresponding function on
        all minibatch indexes.

        :type train_set_x: theano.tensor.TensorType
        :param train_set_x: Shared variable that contains all datapoints used
                            for training the dA

        :type batch_size: int
        :param batch_size: size of a [mini]batch

        :type learning_rate: float
        :param learning_rate: learning rate used during training for any of
                              the dA layers
        '''

        # index to a [mini]batch
        index = T.lscalar('index')  # index to a minibatch
        corruption_level = T.scalar('corruption')  # % of corruption to use
        learning_rate = T.scalar('lr')  # learning rate to use
        # number of batches
        n_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
        # begining of a batch, given `index`
        batch_begin = index * batch_size
        # ending of a batch given `index`
        batch_end = batch_begin + batch_size

        pretrain_fns = []
        for dA in self.dA_layers:
            # get the cost and the updates list
            cost, updates = dA.get_cost_updates(corruption_level,
                                                learning_rate)
            # compile the theano function
            fn = theano.function(inputs=[index,
                              theano.Param(corruption_level, default=0.2),
                              theano.Param(learning_rate, default=0.1)],
                                 outputs=cost,
                                 updates=updates,
                                 givens={self.x: train_set_x[batch_begin:
                                                             batch_end]})
            # append `fn` to the list of functions
            pretrain_fns.append(fn)

        return pretrain_fns

    def build_finetune_functions(self, datasets, batch_size, learning_rate):
        '''Generates a function `train` that implements one step of
        finetuning, a function `validate` that computes the error on
        a batch from the validation set, and a function `test` that
        computes the error on a batch from the testing set

        :type datasets: list of pairs of theano.tensor.TensorType
        :param datasets: It is a list that contain all the datasets;
                         the has to contain three pairs, `train`,
                         `valid`, `test` in this order, where each pair
                         is formed of two Theano variables, one for the
                         datapoints, the other for the labels

        :type batch_size: int
        :param batch_size: size of a minibatch

        :type learning_rate: float
        :param learning_rate: learning rate used during finetune stage
        '''

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

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

        index = T.lscalar('index')  # index to a [mini]batch

        # compute the gradients with respect to the model parameters
        gparams = T.grad(self.finetune_cost, self.params)

        # compute list of fine-tuning updates
        updates = []
        for param, gparam in zip(self.params, gparams):
            updates.append((param, param - gparam * learning_rate))

        train_fn = theano.function(inputs=[index],
              outputs=self.finetune_cost,
              updates=updates,
              givens={
                self.x: train_set_x[index * batch_size:
                                    (index + 1) * batch_size],
                self.y: train_set_y[index * batch_size:
                                    (index + 1) * batch_size]},
              name='train')

        test_score_i = theano.function([index], self.errors,
                 givens={
                   self.x: test_set_x[index * batch_size:
                                      (index + 1) * batch_size],
                   self.y: test_set_y[index * batch_size:
                                      (index + 1) * batch_size]},
                      name='test')

        valid_score_i = theano.function([index], self.errors,
              givens={
                 self.x: valid_set_x[index * batch_size:
                                     (index + 1) * batch_size],
                 self.y: valid_set_y[index * batch_size:
                                     (index + 1) * batch_size]},
                      name='valid')

        # Create a function that scans the entire validation set
        def valid_score():
            return [valid_score_i(i) for i in xrange(n_valid_batches)]

        # Create a function that scans the entire test set
        def test_score():
            return [test_score_i(i) for i in xrange(n_test_batches)]

        return train_fn, valid_score, test_score
Beispiel #4
0
    def __init__(self, numpy_rng, theano_rng=None, n_ins=784,
                 hidden_layers_sizes=[500, 500], n_outs=10):
        """This class is made to support a variable number of layers.

        :type numpy_rng: numpy.random.RandomState
        :param numpy_rng: numpy random number generator used to draw initial
                    weights

        :type theano_rng: theano.tensor.shared_randomstreams.RandomStreams
        :param theano_rng: Theano random generator; if None is given one is
                           generated based on a seed drawn from `rng`

        :type n_ins: int
        :param n_ins: dimension of the input to the DBN

        :type n_layers_sizes: list of ints
        :param n_layers_sizes: intermediate layers size, must contain
                               at least one value

        :type n_outs: int
        :param n_outs: dimension of the output of the network
        """

        self.sigmoid_layers = []
        self.rbm_layers = []
        self.params = []
        self.n_layers = len(hidden_layers_sizes)

        assert self.n_layers > 0

        if not theano_rng:
            theano_rng = RandomStreams(numpy_rng.randint(2 ** 30))

        # allocate symbolic variables for the data
        self.x = T.matrix('x')  # the data is presented as rasterized images
        self.y = T.ivector('y')  # the labels are presented as 1D vector
                                 # of [int] labels

        # The DBN is an MLP, for which all weights of intermediate
        # layers are shared with a different RBM.  We will first
        # construct the DBN as a deep multilayer perceptron, and when
        # constructing each sigmoidal layer we also construct an RBM
        # that shares weights with that layer. During pretraining we
        # will train these RBMs (which will lead to chainging the
        # weights of the MLP as well) During finetuning we will finish
        # training the DBN by doing stochastic gradient descent on the
        # MLP.

        for i in xrange(self.n_layers):
            # construct the sigmoidal layer

            # the size of the input is either the number of hidden
            # units of the layer below or the input size if we are on
            # the first layer
            if i == 0:
                input_size = n_ins
            else:
                input_size = hidden_layers_sizes[i - 1]

            # the input to this layer is either the activation of the
            # hidden layer below or the input of the DBN if you are on
            # the first layer
            if i == 0:
                layer_input = self.x
            else:
                layer_input = self.sigmoid_layers[-1].output

            sigmoid_layer = HiddenLayer(rng=numpy_rng,
                                        input=layer_input,
                                        n_in=input_size,
                                        n_out=hidden_layers_sizes[i],
                                        activation=T.nnet.sigmoid)

            # add the layer to our list of layers
            self.sigmoid_layers.append(sigmoid_layer)

            # its arguably a philosophical question...  but we are
            # going to only declare that the parameters of the
            # sigmoid_layers are parameters of the DBN. The visible
            # biases in the RBM are parameters of those RBMs, but not
            # of the DBN.
            self.params.extend(sigmoid_layer.params)

            # Construct an RBM that shared weights with this layer
            rbm_layer = RBM(numpy_rng=numpy_rng,
                            theano_rng=theano_rng,
                            input=layer_input,
                            n_visible=input_size,
                            n_hidden=hidden_layers_sizes[i],
                            W=sigmoid_layer.W,
                            hbias=sigmoid_layer.b)
            self.rbm_layers.append(rbm_layer)

        # We now need to add a logistic layer on top of the MLP
        self.logLayer = SoftMaxLayer(
            input=self.sigmoid_layers[-1].output,
            n_in=hidden_layers_sizes[-1],
            n_out=n_outs)
        self.params.extend(self.logLayer.params)

        # compute the cost for second phase of training, defined as the
        # negative log likelihood of the logistic regression (output) layer
        self.finetune_cost = self.logLayer.negative_log_likelihood(self.y)

        # compute the gradients with respect to the model parameters
        # symbolic variable that points to the number of errors made on the
        # minibatch given by self.x and self.y
        self.errors = self.logLayer.errors(self.y)
Beispiel #5
0
class DBN(object):
    """Deep Belief Network

    A deep belief network is obtained by stacking several RBMs on top of each
    other. The hidden layer of the RBM at layer `i` becomes the input of the
    RBM at layer `i+1`. The first layer RBM gets as input the input of the
    network, and the hidden layer of the last RBM represents the output. When
    used for classification, the DBN is treated as a MLP, by adding a logistic
    regression layer on top.
    """

    def __init__(self, numpy_rng, theano_rng=None, n_ins=784,
                 hidden_layers_sizes=[500, 500], n_outs=10):
        """This class is made to support a variable number of layers.

        :type numpy_rng: numpy.random.RandomState
        :param numpy_rng: numpy random number generator used to draw initial
                    weights

        :type theano_rng: theano.tensor.shared_randomstreams.RandomStreams
        :param theano_rng: Theano random generator; if None is given one is
                           generated based on a seed drawn from `rng`

        :type n_ins: int
        :param n_ins: dimension of the input to the DBN

        :type n_layers_sizes: list of ints
        :param n_layers_sizes: intermediate layers size, must contain
                               at least one value

        :type n_outs: int
        :param n_outs: dimension of the output of the network
        """

        self.sigmoid_layers = []
        self.rbm_layers = []
        self.params = []
        self.n_layers = len(hidden_layers_sizes)

        assert self.n_layers > 0

        if not theano_rng:
            theano_rng = RandomStreams(numpy_rng.randint(2 ** 30))

        # allocate symbolic variables for the data
        self.x = T.matrix('x')  # the data is presented as rasterized images
        self.y = T.ivector('y')  # the labels are presented as 1D vector
                                 # of [int] labels

        # The DBN is an MLP, for which all weights of intermediate
        # layers are shared with a different RBM.  We will first
        # construct the DBN as a deep multilayer perceptron, and when
        # constructing each sigmoidal layer we also construct an RBM
        # that shares weights with that layer. During pretraining we
        # will train these RBMs (which will lead to chainging the
        # weights of the MLP as well) During finetuning we will finish
        # training the DBN by doing stochastic gradient descent on the
        # MLP.

        for i in xrange(self.n_layers):
            # construct the sigmoidal layer

            # the size of the input is either the number of hidden
            # units of the layer below or the input size if we are on
            # the first layer
            if i == 0:
                input_size = n_ins
            else:
                input_size = hidden_layers_sizes[i - 1]

            # the input to this layer is either the activation of the
            # hidden layer below or the input of the DBN if you are on
            # the first layer
            if i == 0:
                layer_input = self.x
            else:
                layer_input = self.sigmoid_layers[-1].output

            sigmoid_layer = HiddenLayer(rng=numpy_rng,
                                        input=layer_input,
                                        n_in=input_size,
                                        n_out=hidden_layers_sizes[i],
                                        activation=T.nnet.sigmoid)

            # add the layer to our list of layers
            self.sigmoid_layers.append(sigmoid_layer)

            # its arguably a philosophical question...  but we are
            # going to only declare that the parameters of the
            # sigmoid_layers are parameters of the DBN. The visible
            # biases in the RBM are parameters of those RBMs, but not
            # of the DBN.
            self.params.extend(sigmoid_layer.params)

            # Construct an RBM that shared weights with this layer
            rbm_layer = RBM(numpy_rng=numpy_rng,
                            theano_rng=theano_rng,
                            input=layer_input,
                            n_visible=input_size,
                            n_hidden=hidden_layers_sizes[i],
                            W=sigmoid_layer.W,
                            hbias=sigmoid_layer.b)
            self.rbm_layers.append(rbm_layer)

        # We now need to add a logistic layer on top of the MLP
        self.logLayer = SoftMaxLayer(
            input=self.sigmoid_layers[-1].output,
            n_in=hidden_layers_sizes[-1],
            n_out=n_outs)
        self.params.extend(self.logLayer.params)

        # compute the cost for second phase of training, defined as the
        # negative log likelihood of the logistic regression (output) layer
        self.finetune_cost = self.logLayer.negative_log_likelihood(self.y)

        # compute the gradients with respect to the model parameters
        # symbolic variable that points to the number of errors made on the
        # minibatch given by self.x and self.y
        self.errors = self.logLayer.errors(self.y)

    def pretraining_functions(self, train_set_x, batch_size, k):
        '''Generates a list of functions, for performing one step of
        gradient descent at a given layer. The function will require
        as input the minibatch index, and to train an RBM you just
        need to iterate, calling the corresponding function on all
        minibatch indexes.

        :type train_set_x: theano.tensor.TensorType
        :param train_set_x: Shared var. that contains all datapoints used
                            for training the RBM
        :type batch_size: int
        :param batch_size: size of a [mini]batch
        :param k: number of Gibbs steps to do in CD-k / PCD-k

        '''

        # index to a [mini]batch
        index = T.lscalar('index')  # index to a minibatch
        learning_rate = T.scalar('lr')  # learning rate to use

        # number of batches
        n_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
        # begining of a batch, given `index`
        batch_begin = index * batch_size
        # ending of a batch given `index`
        batch_end = batch_begin + batch_size

        pretrain_fns = []
        for rbm in self.rbm_layers:

            # get the cost and the updates list
            # using CD-k here (persisent=None) for training each RBM.
            # TODO: change cost function to reconstruction error
            cost, updates = rbm.get_cost_updates(learning_rate,
                                                 persistent=None, k=k)

            # compile the theano function
            fn = theano.function(inputs=[index,
                            theano.Param(learning_rate, default=0.1)],
                                 outputs=cost,
                                 updates=updates,
                                 givens={self.x:
                                    train_set_x[batch_begin:batch_end]})
            # append `fn` to the list of functions
            pretrain_fns.append(fn)

        return pretrain_fns

    def build_finetune_functions(self, datasets, batch_size, learning_rate):
        '''Generates a function `train` that implements one step of
        finetuning, a function `validate` that computes the error on a
        batch from the validation set, and a function `test` that
        computes the error on a batch from the testing set

        :type datasets: list of pairs of theano.tensor.TensorType
        :param datasets: It is a list that contain all the datasets;
                        the has to contain three pairs, `train`,
                        `valid`, `test` in this order, where each pair
                        is formed of two Theano variables, one for the
                        datapoints, the other for the labels
        :type batch_size: int
        :param batch_size: size of a minibatch
        :type learning_rate: float
        :param learning_rate: learning rate used during finetune stage

        '''

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

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

        index = T.lscalar('index')  # index to a [mini]batch

        # compute the gradients with respect to the model parameters
        gparams = T.grad(self.finetune_cost, self.params)

        # compute list of fine-tuning updates
        updates = []
        for param, gparam in zip(self.params, gparams):
            updates.append((param, param - gparam * learning_rate))

        train_fn = theano.function(inputs=[index],
              outputs=self.finetune_cost,
              updates=updates,
              givens={self.x: train_set_x[index * batch_size:
                                          (index + 1) * batch_size],
                      self.y: train_set_y[index * batch_size:
                                          (index + 1) * batch_size]})

        test_score_i = theano.function([index], self.errors,
                 givens={self.x: test_set_x[index * batch_size:
                                            (index + 1) * batch_size],
                         self.y: test_set_y[index * batch_size:
                                            (index + 1) * batch_size]})

        valid_score_i = theano.function([index], self.errors,
              givens={self.x: valid_set_x[index * batch_size:
                                          (index + 1) * batch_size],
                      self.y: valid_set_y[index * batch_size:
                                          (index + 1) * batch_size]})

        # Create a function that scans the entire validation set
        def valid_score():
            return [valid_score_i(i) for i in xrange(n_valid_batches)]

        # Create a function that scans the entire test set
        def test_score():
            return [test_score_i(i) for i in xrange(n_test_batches)]

        return train_fn, valid_score, test_score
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

    :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
    """

    rng = numpy.random.RandomState(23455)

    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]

    # compute number of minibatches for training, validation and testing
    n_train_batches = train_set_x.get_value(borrow=True).shape[0]
    n_valid_batches = valid_set_x.get_value(borrow=True).shape[0]
    n_test_batches = test_set_x.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
    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

    ishape = (28, 28)  # this is the size of MNIST images

    ######################
    # 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
    layer0_input = x.reshape((batch_size, 1, 28, 28))

    # 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, 28, 28), filter_shape=(nkerns[0], 1, 5, 5), 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 (nkerns[0],nkerns[1],4,4)
    layer1 = LeNetConvPoolLayer(
        rng,
        input=layer0.output,
        image_shape=(batch_size, nkerns[0], 12, 12),
        filter_shape=(nkerns[1], nkerns[0], 5, 5),
        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 (20,32*4*4) = (20,512)
    layer2_input = layer1.output.flatten(2)

    # construct a fully-connected sigmoidal layer
    layer2 = HiddenLayer(rng, input=layer2_input, n_in=nkerns[1] * 4 * 4, n_out=500, activation=T.tanh)

    # classify the values of the fully-connected sigmoidal layer
    layer3 = SoftMaxLayer(input=layer2.output, n_in=500, n_out=10)

    # 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_x[index * batch_size : (index + 1) * batch_size],
            y: test_set_y[index * batch_size : (index + 1) * batch_size],
        },
    )

    validate_model = theano.function(
        [index],
        layer3.errors(y),
        givens={
            x: valid_set_x[index * batch_size : (index + 1) * batch_size],
            y: valid_set_y[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 = []
    for param_i, grad_i in zip(params, grads):
        updates.append((param_i, param_i - learning_rate * grad_i))

    train_model = theano.function(
        [index],
        cost,
        updates=updates,
        givens={
            x: train_set_x[index * batch_size : (index + 1) * batch_size],
            y: train_set_y[index * batch_size : (index + 1) * batch_size],
        },
    )

    ###############
    # 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)
    # go through this many
    # minibatche before checking the network
    # on the validation set; in this case we
    # check every epoch

    best_params = None
    best_validation_loss = numpy.inf
    best_iter = 0
    test_score = 0.0
    start_time = time.clock()

    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 * 100.0)
                )

                # 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 * 100.0)
                    )

            if patience <= iter:
                done_looping = True
                break

    end_time = time.clock()
    print ("Optimization complete.")
    print (
        "Best validation score of %f %% obtained at iteration %i,"
        "with test performance %f %%" % (best_validation_loss * 100.0, best_iter + 1, test_score * 100.0)
    )
    print >> sys.stderr, (
        "The code for file " + os.path.split(__file__)[1] + " ran for %.2fm" % ((end_time - start_time) / 60.0)
    )