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)) self.x = T.matrix('x') self.y = T.ivector('y') for i in xrange(self.n_layers): if i == 0: input_size = n_ins layer_input = self.x else: input_size = hidden_layers_sizes[i - 1] 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 ) self.sigmoid_layers.append(sigmoid_layer) self.params.extend(sigmoid_layer.params) dA_layer = DenoisingAutoencoder( 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) 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) self.finetune_cost = self.logLayer.negative_log_likelihood(self.y) self.errors = self.logLayer.errors(self.y)
class StackedDenoisingAutoencoder(object): 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)) self.x = T.matrix('x') self.y = T.ivector('y') for i in xrange(self.n_layers): if i == 0: input_size = n_ins layer_input = self.x else: input_size = hidden_layers_sizes[i - 1] 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 ) self.sigmoid_layers.append(sigmoid_layer) self.params.extend(sigmoid_layer.params) dA_layer = DenoisingAutoencoder( 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) 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) self.finetune_cost = self.logLayer.negative_log_likelihood(self.y) self.errors = self.logLayer.errors(self.y) def create_pretraining_functions(self, train_set_x, batch_size): index = T.lscalar('index') corruption_level = T.scalar('corruption') learning_rate = T.scalar('learning_rate') batch_begin = index * batch_size batch_end = (index + 1) * batch_size pretrain_fns = [] for dae in self.dA_layers: cost, updates = dae.get_cost_updates( corruption_level=corruption_level, learning_rate=learning_rate ) 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] } ) pretrain_fns.append(fn) return pretrain_fns def build_finetune_functions(self, datasets, batch_size, learning_rate): (train_set_x, train_set_y) = datasets[0] (valid_set_x, valid_set_y) = datasets[1] (test_set_x, test_set_y) = datasets[2] 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') gparams = T.grad(self.finetune_cost, self.params) updates = [ (param, param - learning_rate * gparam) 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( inputs=[index], outputs=self.errors, updates=updates, 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( inputs=[index], outputs=self.errors, updates=updates, 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' ) def valid_score(): return [valid_score_i(i) for i in xrange(n_valid_batches)] def test_score(): return [test_score_i(i) for i in xrange(n_test_batches)] return train_fn, valid_score, test_score