Python LogisticRegression.prediction方法代码示例

# 需要导入模块: from layers.logistic_sgd import LogisticRegression [as 别名]
# 或者: from layers.logistic_sgd.LogisticRegression import prediction [as 别名]
class DNN(nnet):

    def __init__(self, numpy_rng, theano_rng=None, n_ins=784,
                 hidden_layers_sizes=[500, 500], n_outs=10,
                 activation = T.nnet.sigmoid, adv_activation = None,
                 max_col_norm = None, l1_reg = None, l2_reg = None):

        super(DNN, self).__init__()
        
        self.layers = []
        self.n_layers = len(hidden_layers_sizes)

        self.max_col_norm = max_col_norm
        self.l1_reg = l1_reg
        self.l2_reg = l2_reg

        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') 
        self.y = T.ivector('y')

        for i in xrange(self.n_layers):
            # construct the sigmoidal layer
            if i == 0:
                input_size = n_ins
                layer_input = self.x
            else:
                input_size = hidden_layers_sizes[i - 1]
                layer_input = self.layers[-1].output

            if not adv_activation is  None:
                sigmoid_layer = HiddenLayer(rng=numpy_rng,
                                        input=layer_input,
                                        n_in=input_size,
                                        n_out=hidden_layers_sizes[i] * pool_size,
                                        activation = activation,
                                        adv_activation_method = adv_activation['method'],
                                        pool_size = adv_activation['pool_size'],
                                        pnorm_order = adv_activation['pnorm_order'])
            else:
                sigmoid_layer = HiddenLayer(rng=numpy_rng,
                                        input=layer_input,
                                        n_in=input_size,
                                        n_out=hidden_layers_sizes[i],
                                        activation=activation)
                                        
            # add the layer to our list of layers
            self.layers.append(sigmoid_layer)
            self.params.extend(sigmoid_layer.params)
            self.delta_params.extend(sigmoid_layer.delta_params)
            
        # We now need to add a logistic layer on top of the MLP
        self.logLayer = LogisticRegression(
                         input=self.layers[-1].output,
                         n_in=hidden_layers_sizes[-1], n_out=n_outs)

        self.layers.append(self.logLayer)
        self.params.extend(self.logLayer.params)
        self.delta_params.extend(self.logLayer.delta_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)
        self.errors = self.logLayer.errors(self.y)

        if self.l1_reg is not None:
            self.__l1Regularization__();

        if self.l2_reg is not None:
            self.__l2Regularization__();

        self.output = self.logLayer.prediction();
        self.features = self.layers[-2].output;
        self.features_dim = self.layers[-2].n_out

# 需要导入模块: from layers.logistic_sgd import LogisticRegression [as 别名]
# 或者: from layers.logistic_sgd.LogisticRegression import prediction [as 别名]

#.........这里部分代码省略.........
                                        activation=activation)

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

            # 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)
            self.delta_params.extend(sigmoid_layer.delta_params)

            # Construct an RBM that shared weights with this layer
            # the first layer could be Gaussian-Bernoulli RBM
            # other layers are Bernoulli-Bernoulli RBMs
            if i == 0 and first_layer_gb:
                rbm_layer = GBRBM(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)
            else:
                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 = LogisticRegression(
            input=self.layers[-1].output,
            n_in=hidden_layers_sizes[-1],
            n_out=n_outs)
        self.layers.append(self.logLayer)
        self.params.extend(self.logLayer.params)
        self.delta_params.extend(self.logLayer.delta_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)

        self.output = self.logLayer.prediction();
        self.features = self.layers[-2].output;
        self.features_dim = self.layers[-2].n_out

    def pretraining_functions(self, train_set_x, batch_size, weight_cost):
        '''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 weight_cost: weigth cost

        '''

        # index to a [mini]batch
        index = T.lscalar('index')  # index to a minibatch
        momentum = T.scalar('momentum')
        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,k=1) for training each RBM.
            r_cost, fe_cost, updates = rbm.get_cost_updates(batch_size, learning_rate,
                                                            momentum, weight_cost)
            # compile the theano function
            fn = theano.function(inputs=[index,
                              theano.Param(learning_rate, default=0.0001),
                              theano.Param(momentum, default=0.5)],
                              outputs= [r_cost, fe_cost],
                              updates=updates,
                              givens={self.x: train_set_x[batch_begin:batch_end]})
            # append function to the list of functions
            pretrain_fns.append(fn)

        return pretrain_fns

# 需要导入模块: from layers.logistic_sgd import LogisticRegression [as 别名]
# 或者: from layers.logistic_sgd.LogisticRegression import prediction [as 别名]

#.........这里部分代码省略.........
            else:
                dropout_layer = DropoutHiddenLayer(rng=numpy_rng,
                                        input=dropout_layer_input,
                                        n_in=input_size,
                                        n_out=hidden_layers_sizes[i],
                                        activation= activation,
                                        dropout_factor=self.dropout_factor[i])
                sigmoid_layer = HiddenLayer(rng=numpy_rng,
                                        input=layer_input,
                                        n_in=input_size,
                                        n_out=hidden_layers_sizes[i] ,
                                        activation= activation,
                                        W=dropout_layer.W, b=dropout_layer.b)
                                        
            # add the layer to our list of layers
            self.layers.append(sigmoid_layer)
            self.dropout_layers.append(dropout_layer)
            self.params.extend(dropout_layer.params)
            self.delta_params.extend(dropout_layer.delta_params)
            
        # We now need to add a logistic layer on top of the MLP
        self.dropout_logLayer = LogisticRegression(
                                 input=self.dropout_layers[-1].dropout_output,
                                 n_in=hidden_layers_sizes[-1], n_out=n_outs)

        self.logLayer = LogisticRegression(
                         input=(1 - self.dropout_factor[-1]) * self.layers[-1].output,
                         n_in=hidden_layers_sizes[-1], n_out=n_outs,
                         W=self.dropout_logLayer.W, b=self.dropout_logLayer.b)

        self.dropout_layers.append(self.dropout_logLayer)
        self.layers.append(self.logLayer)
        self.params.extend(self.dropout_logLayer.params)
        self.delta_params.extend(self.dropout_logLayer.delta_params)

        # compute the cost
        self.finetune_cost = self.dropout_logLayer.negative_log_likelihood(self.y)
        self.errors = self.logLayer.errors(self.y)

        self.output = self.logLayer.prediction();
        self.features = self.layers[-2].output;
        self.features_dim = self.layers[-2].n_out

        if self.l1_reg is not None:
            self.__l1Regularization__();

        if self.l2_reg is not None:
            self.__l2Regularization__();


    def save(self,filename,start_layer = 0,max_layer_num = -1,withfinal=True):
        nnet_dict = {}
        if max_layer_num == -1:
           max_layer_num = self.n_layers

        for i in range(start_layer, max_layer_num):
           dict_a = str(i) + ' W'
           if i == 0:
               nnet_dict[dict_a] = _array2string((1.0 - self.input_dropout_factor) * (
                self.layers[i].params[0].get_value()))
           else:
               nnet_dict[dict_a] = _array2string((1.0 - self.dropout_factor[i - 1])* (
                self.layers[i].params[0].get_value()))
           dict_a = str(i) + ' b'
           nnet_dict[dict_a] = _array2string(self.layers[i].params[1].get_value())

        if withfinal: 
            dict_a = 'logreg W'
            nnet_dict[dict_a] = _array2string((1.0 - self.dropout_factor[-1])* (
                self.logLayer.params[0].get_value()))
            dict_a = 'logreg b'
            nnet_dict[dict_a] = _array2string(self.logLayer.params[1].get_value())
   
        with open(filename, 'wb') as fp:
            json.dump(nnet_dict, fp, indent=2, sort_keys = True)
            fp.flush()

    def load(self,filename,start_layer = 0,max_layer_num = -1,withfinal=True):
        nnet_dict = {}
        if max_layer_num == -1:
            max_layer_num = self.n_layers

        with open(filename, 'rb') as fp:
            nnet_dict = json.load(fp)
        
        for i in xrange(max_layer_num):
            dict_key = str(i) + ' W'
            self.layers[i].params[0].set_value(numpy.asarray(_string2array(nnet_dict[dict_key]),
                dtype=theano.config.floatX))
            dict_key = str(i) + ' b' 
            self.layers[i].params[1].set_value(numpy.asarray(_string2array(nnet_dict[dict_key]),
                dtype=theano.config.floatX))

        if withfinal:
            dict_key = 'logreg W'
            self.logLayer.params[0].set_value(numpy.asarray(_string2array(nnet_dict[dict_key]),
                dtype=theano.config.floatX))
            dict_key = 'logreg b'
            self.logLayer.params[1].set_value(numpy.asarray(_string2array(nnet_dict[dict_key]),
                dtype=theano.config.floatX))

# 需要导入模块: from layers.logistic_sgd import LogisticRegression [as 别名]
# 或者: from layers.logistic_sgd.LogisticRegression import prediction [as 别名]

#.........这里部分代码省略.........
		hidden_layers = hidden_layer_configs['hidden_layers'];
		self.conv_output_dim = config['output_shape'][1] * config['output_shape'][2] * config['output_shape'][3]
		adv_activation_configs = hidden_layer_configs['adv_activation'] 
		
		#flattening the last convolution output layer
		self.features = self.conv_layers[-1].output.flatten(2);
		self.features_dim = self.conv_output_dim;

		self.dropout_layers = [];
		self.dropout_factor = hidden_layer_configs['dropout_factor'];
		self.input_dropout_factor = hidden_layer_configs['input_dropout_factor'];
		
		for i in xrange(self.hidden_layer_num):		# construct the hidden layer
			if i == 0:				# is first sigmoidla layer
				input_size = self.conv_output_dim
				if self.dropout_factor[i] > 0.0:
					dropout_layer_input = _dropout_from_layer(theano_rng, self.layers[-1].output, self.input_dropout_factor)
				else:
					dropout_layer_input = self.features
				layer_input = self.features
			else:
				input_size = hidden_layers[i - 1]	# number of hidden neurons in previous layers
				dropout_layer_input = self.dropout_layers[-1].dropout_output			
				layer_input = (1 - self.dropout_factor[i-1]) * self.layers[-1].output
				
			if adv_activation_configs is None:
				dropout_sigmoid_layer = DropoutHiddenLayer(rng=numpy_rng, input=layer_input,n_in=input_size, 
						n_out = hidden_layers[i], activation=hidden_activation,
						dropout_factor = self.dropout_factor[i]);
						
				sigmoid_layer = HiddenLayer(rng=numpy_rng, input=layer_input,n_in=input_size, 
						n_out = hidden_layers[i], activation=hidden_activation,
						W=dropout_sigmoid_layer.W, b=dropout_sigmoid_layer.b);
										
						
			else:
				dropout_sigmoid_layer = DropoutHiddenLayer(rng=numpy_rng, input=layer_input,n_in=input_size, 
						n_out = hidden_layers[i]*adv_activation_configs['pool_size'], activation=hidden_activation,
						adv_activation_method = adv_activation_configs['method'],
						pool_size = adv_activation_configs['pool_size'],
						pnorm_order = adv_activation_configs['pnorm_order'],
						dropout_factor = self.dropout_factor[i]);
						
				sigmoid_layer = HiddenLayer(rng=numpy_rng, input=layer_input,n_in=input_size, 
						n_out = hidden_layers[i]*adv_activation_configs['pool_size'], activation=hidden_activation,
						adv_activation_method = adv_activation_configs['method'],
						pool_size = adv_activation_configs['pool_size'],
						pnorm_order = adv_activation_configs['pnorm_order'],
						W=dropout_sigmoid_layer.W, b=dropout_sigmoid_layer.b);
						
			self.layers.append(sigmoid_layer)
			self.dropout_layers.append(dropout_sigmoid_layer)
			self.mlp_layers.append(sigmoid_layer)

			if config['update']==True:	# only few layers of hidden layer are considered for updation
						self.params.extend(dropout_sigmoid_layer.params)
						self.delta_params.extend(dropout_sigmoid_layer.delta_params)

		self.dropout_logLayer = LogisticRegression(input=self.dropout_layers[-1].dropout_output,n_in=hidden_layers[-1],n_out=n_outs)
		self.logLayer = LogisticRegression(
							input=(1 - self.dropout_factor[-1]) * self.layers[-1].output,
							n_in=hidden_layers[-1],n_out=n_outs,
							W=self.dropout_logLayer.W, b=self.dropout_logLayer.b)
		
		self.dropout_layers.append(self.dropout_logLayer)
		self.layers.append(self.logLayer)
		self.params.extend(self.dropout_logLayer.params)
		self.delta_params.extend(self.dropout_logLayer.delta_params)
		
		self.finetune_cost = self.dropout_logLayer.negative_log_likelihood(self.y)
		self.errors = self.logLayer.errors(self.y)
		self.output = self.logLayer.prediction()
		
		#regularization
		if self.l1_reg is not None:
			self.__l1Regularization__(self.hidden_layer_num*2);
		if self.l2_reg is not None:
			self.__l2Regularization__(self.hidden_layer_num*2);
			
			
			
	def save_mlp2dict(self,withfinal=True,max_layer_num=-1):
		if max_layer_num == -1:
		   max_layer_num = self.hidden_layer_num
		mlp_dict = {}
		for i in range(max_layer_num):
			dict_a = str(i) +' W'
			if i == 0:
				mlp_dict[dict_a] = _array2string((1.0 - self.input_dropout_factor) *self.mlp_layers[i].params[0].get_value())
			else:
				mlp_dict[dict_a] = _array2string((1.0 - self.dropout_factor[i - 1]) * self.mlp_layers[i].params[0].get_value())
			dict_a = str(i) + ' b'
			mlp_dict[dict_a] = _array2string(self.mlp_layers[i].params[1].get_value())	

		if withfinal: 
			dict_a = 'logreg W'
			mlp_dict[dict_a] = _array2string((1.0 - self.dropout_factor[-1])*self.logLayer.params[0].get_value())
			dict_a = 'logreg b'
			mlp_dict[dict_a] = _array2string(self.logLayer.params[1].get_value())
		return mlp_dict

# 需要导入模块: from layers.logistic_sgd import LogisticRegression [as 别名]
# 或者: from layers.logistic_sgd.LogisticRegression import prediction [as 别名]

#.........这里部分代码省略.........

            # 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.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.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)
            self.delta_params.extend(sigmoid_layer.delta_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,
                          activation=T.nnet.sigmoid)
            self.dA_layers.append(dA_layer)

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

        self.output = self.logLayer.prediction();
        self.features = self.layers[-2].output;
        self.features_dim = self.layers[-2].n_out

    def pretraining_functions(self, train_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_x: theano.tensor.TensorType
        :param train_x: Shared variable that contains all datapoints used
                            for training the dA

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

        # 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_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_x[batch_begin:
                                                             batch_end]})
            # append `fn` to the list of functions
            pretrain_fns.append(fn)

        return pretrain_fns