SdA.py


# coding: utf-8

# http://deeplearning.net/tutorial/SdA.html  
# http://deeplearning.net/tutorial/code/SdA.py
# 
# 
# os.path.split(__file__)[1] -->  
# os.path.split(os.path.realpath('__file__'))[1]
# 
# ## 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.**
# 
# ## stacked denoising auto-encoders (SdA) using Theano.
# 
#  Denoising autoencoders are the building blocks for SdA.
#  
#  - **Note: go through all pretraining epochs for one layer before to to the next layer**

# In[25]:

from __future__ import print_function

import os
import sys
import timeit

import numpy

import theano
import theano.tensor as T
from theano.tensor.shared_randomstreams import RandomStreams

import six.moves.cPickle as pickle
from logistic_sgd import LogisticRegression, load_data
from mlp import HiddenLayer
from dA import dA

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]
    ):
        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 range(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 one 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 r on the first layer
            if i==0:
                layer_input=self.x
            else:
                layer_input=self.sigmoid_layers[i-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)
            
            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 layers
            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 = LogisticRegression(
            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.
        '''
        
        # index to a [mini]batch
        index=T.lscalar('index')
        corruption_level=T.scalar('corruption')
        learning_rate=T.scalar('lr')
        
        # begining of a batch, given index
        batch_begin=index*batch_size
        batch_end=batch_begin+batch_size
        
        pretrain_fns=[]
        for layer_i,dA in enumerate(self.dA_layers):
            print('pretraining layer %d functions built.'%layer_i)
            # 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.In(corruption_level, value=0.2),
                    theano.In(learning_rate, value=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
        '''

        (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 = [ (param, param - gparam * learning_rate)
            for param, gparam in zip(self.params, gparams) ]

        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 range(n_valid_batches)]

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

        return train_fn, valid_score, test_score


# In[26]:

def test_SdA(finetune_lr=0.1, pretraining_epochs=15,
             pretrain_lr=0.001, training_epochs=1000,
             dataset='mnist.pkl.gz', batch_size=1):
    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_train_batches //= batch_size

    # numpy random generator
    numpy_rng = numpy.random.RandomState(89677)
    print('... building the model')
    # construct the stacked denoising autoencoder class
    sda = SdA(
        numpy_rng=numpy_rng,
        n_ins=28 * 28,
        hidden_layers_sizes=[1000, 1000, 1000],
        n_outs=10
    )
    
    #########################
    # 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, .3]
    for i in range(sda.n_layers):
        # go through pretraining epochs for one layer
        for epoch in range(pretraining_epochs):
            # go through the training set
            c = []
            for batch_index in range(n_train_batches):
                c.append(pretraining_fns[i](index=batch_index,
                         corruption=corruption_levels[i],
                         lr=pretrain_lr))
                if batch_index%10000==0:
                    print('  Pre-training layer %i, epoch %d, batch %d'%(i, epoch, batch_index))
            print('Pre-training layer %i, epoch %d, cost %f' % (i, epoch, numpy.mean(c)))

    end_time = timeit.default_timer()

    print(('The pretraining code for file ' +
           os.path.split(os.path.realpath('__file__'))[1] +
           ' ran for %.2fm' % ((end_time - start_time) / 60.)), file=sys.stderr)
    
    ########################
    # 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 range(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.))
                    
                    with open('best_sda_model.pkl', 'wb') as f:
                        pickle.dump(sda, f)

            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(('The training code for file ' +
           os.path.split(os.path.realpath('__file__'))[1] +
           ' ran for %.2fm' % ((end_time - start_time) / 60.)), file=sys.stderr)
    
if __name__=='__main__':
    test_SdA(pretraining_epochs=10, batch_size=50)
    #test_SdA()


# 

# In[ ]:

<img src="https://www.filepicker.io/api/file/rljyb6zhQDarTk1btPCt"></img>