예제 #1
0
파일: dA.py 프로젝트: karishma14/DAE
def test_dA(learning_rate=0.1, training_epochs=50,
            dataset='../data/train',
            batch_size=100, output_folder='dA_plots'):


    #datasets = load_data(dataset)
    #train_set_x, train_set_y = datasets[0]
    dr = data_reader(dataset,batch_size=2501,patch=256)
    train_set_x = dr.next_batch()
    print train_set_x.get_value(borrow=True).shape

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

    # start-snippet-2
    # 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
    # end-snippet-2

    if not os.path.isdir(output_folder):
        os.makedirs(output_folder)
    os.chdir(output_folder)

    # start-snippet-3
    #####################################
    # BUILDING THE MODEL CORRUPTION 30% #
    #####################################

    rng = numpy.random.RandomState(123)
    theano_rng = RandomStreams(rng.randint(2 ** 30))

    da = dA(
        numpy_rng=rng,
        theano_rng=theano_rng,
        input=x,
        n_visible=256 * 256,
        n_hidden=6000
    )

    cost, updates = da.get_cost_updates(
        corruption_level=0.3,
        learning_rate=learning_rate
    )

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

    start_time = timeit.default_timer()

    ############
    # TRAINING #
    ############

    # go through training epochs
    for epoch in xrange(training_epochs):
        # go through trainng set
        c = []
        for batch_index in xrange(n_train_batches):
            c.append(train_da(batch_index))

        print 'Training epoch %d, cost ' % epoch, numpy.mean(c)

    end_time = timeit.default_timer()

    training_time = (end_time - start_time)

    print >> sys.stderr, ('The 30% corruption code for file ' +
                          os.path.split(__file__)[1] +
                          ' ran for %.2fm' % (training_time / 60.))
    # end-snippet-3

    # start-snippet-4
    image = Image.fromarray(tile_raster_images(
        X=da.W.get_value(borrow=True).T,
        img_shape=(256, 256), tile_shape=(10, 10),
        tile_spacing=(1, 1)))
    image.save('filters_corruption_30_256.png')
    # end-snippet-4

    os.chdir('../')
예제 #2
0
def test_dA(learning_rate=0.1,
            training_epochs=50,
            dataset='../data/train',
            batch_size=100,
            output_folder='dA_plots'):

    #datasets = load_data(dataset)
    #train_set_x, train_set_y = datasets[0]
    dr = data_reader(dataset, batch_size=2501, patch=256)
    train_set_x = dr.next_batch()
    print train_set_x.get_value(borrow=True).shape

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

    # start-snippet-2
    # 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
    # end-snippet-2

    if not os.path.isdir(output_folder):
        os.makedirs(output_folder)
    os.chdir(output_folder)

    # start-snippet-3
    #####################################
    # BUILDING THE MODEL CORRUPTION 30% #
    #####################################

    rng = numpy.random.RandomState(123)
    theano_rng = RandomStreams(rng.randint(2**30))

    da = dA(numpy_rng=rng,
            theano_rng=theano_rng,
            input=x,
            n_visible=256 * 256,
            n_hidden=6000)

    cost, updates = da.get_cost_updates(corruption_level=0.3,
                                        learning_rate=learning_rate)

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

    start_time = timeit.default_timer()

    ############
    # TRAINING #
    ############

    # go through training epochs
    for epoch in xrange(training_epochs):
        # go through trainng set
        c = []
        for batch_index in xrange(n_train_batches):
            c.append(train_da(batch_index))

        print 'Training epoch %d, cost ' % epoch, numpy.mean(c)

    end_time = timeit.default_timer()

    training_time = (end_time - start_time)

    print >> sys.stderr, ('The 30% corruption code for file ' +
                          os.path.split(__file__)[1] + ' ran for %.2fm' %
                          (training_time / 60.))
    # end-snippet-3

    # start-snippet-4
    image = Image.fromarray(
        tile_raster_images(X=da.W.get_value(borrow=True).T,
                           img_shape=(256, 256),
                           tile_shape=(10, 10),
                           tile_spacing=(1, 1)))
    image.save('filters_corruption_30_256.png')
    # end-snippet-4

    os.chdir('../')
예제 #3
0
def test_SdA(finetune_lr=0.1, pretraining_epochs=100,
             pretrain_lr=0.1, training_epochs=1000,
             dataset='mnist.pkl.gz', batch_size=100):
    """
    Demonstrates how to train and test a stochastic denoising autoencoder.

    This is demonstrated on MNIST.

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

    :type pretraining_epochs: int
    :param pretraining_epochs: number of epoch to do pretraining

    :type pretrain_lr: float
    :param pretrain_lr: learning rate to be used during pre-training

    :type n_iter: int
    :param n_iter: maximal number of iterations ot run the optimizer

    :type dataset: string
    :param dataset: path the the pickled dataset

    """

    #datasets = load_data(dataset)
    train_path = "../data/train"
    train_label_path = "../train_label"
    test_path = "../data/test"
    test_label_path = "../data/test_label"
    val_path = "../data/val"
    val_label_path = "../data/val_label"
    
    dr_train = data_reader(train_path,train_label_path,2501,patch=256)
    dr_test = data_reader(test_path,test_label_path,4952,patch=256)
    dr_val = data_reader(val_path,val_label_path,2509,patch=256)

    train_set_x, train_set_y = dr_train.next_batch() 
    valid_set_x, valid_set_y = dr_val.next_batch()
    test_set_x, test_set_y = dr_test.next_batch()
    
    datasets = [(train_set_x, train_set_y), (valid_set_x, valid_set_y),(test_set_x, test_set_y)]
    print train_set_x.get_value(borrow=True).shape
    print test_set_x.get_value(borrow=True).shape
    print valid_set_x.get_value(borrow=True).shape
    

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

    # numpy random generator
    # start-snippet-3
    numpy_rng = numpy.random.RandomState(89677)
    print '... building the model'
    # construct the stacked denoising autoencoder class
    sda = SdA(
        numpy_rng=numpy_rng,
        n_ins=256*256,
        hidden_layers_sizes=[3000, 500],
        n_outs=20
    )
    # end-snippet-3 start-snippet-4
    #########################
    # PRETRAINING THE MODEL #
    #########################
    print '... getting the pretraining functions'
    pretraining_fns = sda.pretraining_functions(train_set_x=train_set_x,
                                                batch_size=batch_size)

    print '... pre-training the model'
    start_time = timeit.default_timer()
    ## Pre-train layer-wise
    corruption_levels = [.1, .2]
    for i in xrange(sda.n_layers):
        # go through pretraining epochs
        for epoch in xrange(pretraining_epochs):
            # go through the training set
            c = []
            for batch_index in xrange(n_train_batches):
                c.append(pretraining_fns[i](index=batch_index,
                         corruption=corruption_levels[i],
                         lr=pretrain_lr))
            print 'Pre-training layer %i, epoch %d, cost ' % (i, epoch),
            print numpy.mean(c)

    end_time = timeit.default_timer()

    print >> sys.stderr, ('The pretraining code for file ' +
                          os.path.split(__file__)[1] +
                          ' ran for %.2fm' % ((end_time - start_time) / 60.))
    # end-snippet-4
    ########################
    # FINETUNING THE MODEL #
    ########################

    # get the training, validation and testing function for the model
    print '... getting the finetuning functions'
    train_fn, validate_model, test_model = sda.build_finetune_functions(
        datasets=datasets,
        batch_size=batch_size,
        learning_rate=finetune_lr
    )

    print '... finetunning the model'
    # early-stopping parameters
    patience = 10 * n_train_batches  # 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_validation_loss = numpy.inf
    test_score = 0.
    start_time = timeit.default_timer()

    done_looping = False
    epoch = 0

    while (epoch < training_epochs) and (not done_looping):
        epoch = epoch + 1
        for minibatch_index in xrange(n_train_batches):
            minibatch_avg_cost = train_fn(minibatch_index)
            iter = (epoch - 1) * n_train_batches + minibatch_index

            if (iter + 1) % validation_frequency == 0:
                validation_losses = validate_model()
                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()
                    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 with best validation score of %f %%, '
            'on iteration %i, '
            'with test performance %f %%'
        )
        % (best_validation_loss * 100., best_iter + 1, test_score * 100.)
    )
    print >> sys.stderr, ('The training code for file ' +
                          os.path.split(__file__)[1] +
                          ' ran for %.2fm' % ((end_time - start_time) / 60.))