Ejemplo n.º 1
0
    def __init__(self, dim_z, x_train, x_test, diff=None, magic=5000):
        ####################################### SETTINGS ###################################
        self.x_train = x_train
        self.x_test = x_test
        self.diff = diff
        self.batch_size = 100.
        self.learning_rate = theano.shared(np.float32(0.0008))
        self.momentum = 0.3
        self.performance = {"train": [], "test": []}
        self.inpt = T.ftensor4(name='input')
        self.df = T.fmatrix(name='differential')
        self.dim_z = dim_z
        self.generative_z = theano.shared(np.float32(np.zeros([1, dim_z])))
        self.activation = relu
        self.generative = False
        self.out_distribution = False
        #self.y = T.matrix(name="y")
        self.in_filters = [5, 5, 5]
        self.filter_lengths = [10., 10., 10.]
        self.params = []
        #magic = 73888.
        self.magic = magic

        self.dropout_symbolic = T.fscalar()
        self.dropout_prob = theano.shared(np.float32(0.0))
        ####################################### LAYERS ######################################
        # LAYER 1 ##############################
        self.conv1 = one_d_conv_layer(self.inpt,
                                      self.in_filters[0],
                                      1,
                                      self.filter_lengths[0],
                                      param_names=["W1", 'b1'])
        self.params += self.conv1.params
        self.bn1 = batchnorm(self.conv1.output)
        self.nl1 = self.activation(self.bn1.X)
        self.maxpool1 = ds.max_pool_2d(self.nl1, [3, 1],
                                       st=[2, 1],
                                       ignore_border=False).astype(
                                           theano.config.floatX)
        self.layer1_out = dropout(self.maxpool1, self.dropout_symbolic)
        #self.layer1_out = self.maxpool1
        # LAYER2 ################################
        self.flattened = T.flatten(self.layer1_out, outdim=2)
        # Variational Layer #####################
        self.latent_layer = variational_gauss_layer(self.flattened, self.magic,
                                                    dim_z)
        self.params += self.latent_layer.params
        self.latent_out = self.latent_layer.output
        # Hidden Layer #########################
        self.hidden_layer = hidden_layer(self.latent_out, dim_z, self.magic)
        self.params += self.hidden_layer.params
        self.hid_out = dropout(
            self.activation(self.hidden_layer.output).reshape(
                (self.inpt.shape[0], self.in_filters[-1],
                 int(self.magic / self.in_filters[-1]), 1)),
            self.dropout_symbolic)
        # Devonvolutional 1 ######################
        self.deconv1 = one_d_deconv_layer(self.hid_out,
                                          1,
                                          self.in_filters[2],
                                          self.filter_lengths[2],
                                          pool=2.,
                                          param_names=["W3", 'b3'],
                                          distribution=False)
        self.params += self.deconv1.params
        #self.nl_deconv1 = dropout(self.activation(self.deconv1.output),self.dropout_symbolic)
        self.tanh_out = self.deconv1.output
        self.last_layer = self.deconv1

        if self.out_distribution == True:
            self.trunk_sigma = self.last_layer.log_sigma[:, :, :self.inpt.
                                                         shape[2], :]
        self.trunc_output = self.tanh_out[:, :, :self.inpt.shape[2], :]

        ################################### FUNCTIONS ######################################################
        self.get_latent_states = theano.function(
            [self.inpt],
            self.latent_out,
            givens=[[self.dropout_symbolic, self.dropout_prob]])
        #self.prior_debug = theano.function([self.inpt],[self.latent_out,self.latent_layer.mu_encoder,self.latent_layer.log_sigma_encoder,self.latent_layer.prior])
        #self.get_prior = theano.function([self.inpt],self.latent_layer.prior)
        #self.convolve1 = theano.function([self.inpt],self.layer1_out)
        #self.convolve2 = theano.function([self.inpt],self.layer2_out)
        self.output = theano.function(
            [self.inpt],
            self.trunc_output,
            givens=[[self.dropout_symbolic, self.dropout_prob]])
        self.get_flattened = theano.function(
            [self.inpt],
            self.flattened,
            givens=[[self.dropout_symbolic, self.dropout_prob]])
        #self.deconvolve1 = theano.function([self.inpt],self.deconv1.output)
        #self.deconvolve2 = theano.function([self.inpt],self.deconv2.output)
        #self.sig_out = theano.function([self.inpt],T.flatten(self.trunk_sigma,outdim=2))
        self.output = theano.function(
            [self.inpt],
            self.trunc_output,
            givens=[[self.dropout_symbolic, self.dropout_prob]])
        #self.generate_from_z = theano.function([self.inpt],self.trunc_output,givens = [[self.latent_out,self.generative_z]])
        self.generate_from_z = theano.function(
            [self.inpt],
            self.trunc_output,
            givens=[[self.dropout_symbolic, self.dropout_prob],
                    [self.latent_out, self.generative_z]])

        self.cost = self.MSE()
        self.mse = self.MSE()
        #self.likelihood = self.log_px_z()
        #self.get_cost = theano.function([self.inpt],[self.cost,self.mse])

        #self.get_likelihood = theano.function([self.layer1.inpt],[self.likelihood])
        self.derivatives = T.grad(self.cost, self.params)
        #self.get_gradients = theano.function([self.inpt],self.derivatives)
        self.updates = adam(self.params, self.derivatives, self.learning_rate)
        #self.updates =momentum_update(self.params,self.derivatives,self.learning_rate,self.momentum)
        self.train_model = theano.function(
            inputs=[self.inpt, self.df],
            outputs=self.cost,
            updates=self.updates,
            givens=[[self.dropout_symbolic, self.dropout_prob]])
    def __init__(self, dim_z, x_train, x_test, diff=None, magic=5000):
        ####################################### SETTINGS ###################################
        self.x_train = x_train
        self.x_test = x_test
        self.diff = diff
        self.batch_size = 100.0
        self.learning_rate = theano.shared(np.float32(0.0008))
        self.momentum = 0.3
        self.performance = {"train": [], "test": []}
        self.inpt = T.ftensor4(name="input")
        self.df = T.fmatrix(name="differential")
        self.dim_z = dim_z
        self.generative_z = theano.shared(np.float32(np.zeros([1, dim_z])))
        self.activation = relu
        self.generative = False
        self.out_distribution = False
        # self.y = T.matrix(name="y")
        self.in_filters = [64, 64, 64]
        self.filter_lengths = [10.0, 10.0, 10.0]
        self.params = []
        # magic = 73888.
        self.magic = magic

        self.dropout_symbolic = T.fscalar()
        self.dropout_prob = theano.shared(np.float32(0.0))
        ####################################### LAYERS ######################################
        # LAYER 1 ##############################
        self.conv1 = one_d_conv_layer(
            self.inpt, self.in_filters[0], 1, self.filter_lengths[0], param_names=["W1", "b1"]
        )
        self.params += self.conv1.params
        self.bn1 = batchnorm(self.conv1.output)
        self.nl1 = self.activation(self.bn1.X)
        self.maxpool1 = pool_2d(self.nl1, [3, 1], stride=[2, 1], mode="average_exc_pad").astype(theano.config.floatX)
        self.layer1_out = dropout(self.maxpool1, self.dropout_symbolic)
        # self.layer1_out = self.maxpool1
        # LAYER2 ################################
        self.flattened = T.flatten(self.layer1_out, outdim=2)
        # Variational Layer #####################
        self.latent_layer = variational_gauss_layer(self.flattened, self.magic, dim_z)
        self.params += self.latent_layer.params
        self.latent_out = self.latent_layer.output
        # Hidden Layer #########################
        self.hidden_layer = hidden_layer(self.latent_out, dim_z, self.magic)
        self.params += self.hidden_layer.params
        self.hid_out = dropout(
            self.activation(self.hidden_layer.output).reshape(
                (self.inpt.shape[0], self.in_filters[-1], int(self.magic / self.in_filters[-1]), 1)
            ),
            self.dropout_symbolic,
        )
        # Devonvolutional 1 ######################
        self.deconv1 = one_d_deconv_layer(
            self.hid_out,
            1,
            self.in_filters[2],
            self.filter_lengths[2],
            pool=2.0,
            param_names=["W3", "b3"],
            distribution=False,
        )
        self.params += self.deconv1.params
        # self.nl_deconv1 = dropout(self.activation(self.deconv1.output),self.dropout_symbolic)
        self.tanh_out = self.deconv1.output
        self.last_layer = self.deconv1

        if self.out_distribution == True:
            self.trunk_sigma = self.last_layer.log_sigma[:, :, : self.inpt.shape[2], :]
        self.trunc_output = self.tanh_out[:, :, : self.inpt.shape[2], :]

        ################################### FUNCTIONS ######################################################
        self.get_latent_states = theano.function(
            [self.inpt], self.latent_out, givens=[[self.dropout_symbolic, self.dropout_prob]]
        )
        # self.prior_debug = theano.function([self.inpt],[self.latent_out,self.latent_layer.mu_encoder,self.latent_layer.log_sigma_encoder,self.latent_layer.prior])
        # self.get_prior = theano.function([self.inpt],self.latent_layer.prior)
        # self.convolve1 = theano.function([self.inpt],self.layer1_out)
        # self.convolve2 = theano.function([self.inpt],self.layer2_out)
        self.output = theano.function(
            [self.inpt], self.trunc_output, givens=[[self.dropout_symbolic, self.dropout_prob]]
        )
        self.get_flattened = theano.function(
            [self.inpt], self.flattened, givens=[[self.dropout_symbolic, self.dropout_prob]]
        )
        # self.deconvolve1 = theano.function([self.inpt],self.deconv1.output)
        # self.deconvolve2 = theano.function([self.inpt],self.deconv2.output)
        # self.sig_out = theano.function([self.inpt],T.flatten(self.trunk_sigma,outdim=2))
        self.output = theano.function(
            [self.inpt], self.trunc_output, givens=[[self.dropout_symbolic, self.dropout_prob]]
        )
        # self.generate_from_z = theano.function([self.inpt],self.trunc_output,givens = [[self.latent_out,self.generative_z]])
        self.generate_from_z = theano.function(
            [self.inpt],
            self.trunc_output,
            givens=[[self.dropout_symbolic, self.dropout_prob], [self.latent_out, self.generative_z]],
        )

        self.cost = self.MSE()
        self.mse = self.MSE()
        # self.likelihood = self.log_px_z()
        # self.get_cost = theano.function([self.inpt],[self.cost,self.mse])

        # self.get_likelihood = theano.function([self.layer1.inpt],[self.likelihood])
        self.derivatives = T.grad(self.cost, self.params)
        # self.get_gradients = theano.function([self.inpt],self.derivatives)
        self.updates = adam(self.params, self.derivatives, self.learning_rate)
        # self.updates =momentum_update(self.params,self.derivatives,self.learning_rate,self.momentum)
        self.train_model = theano.function(
            inputs=[self.inpt, self.df],
            outputs=self.cost,
            updates=self.updates,
            givens=[[self.dropout_symbolic, self.dropout_prob]],
        )
Ejemplo n.º 3
0
	def __init__(self,x_train,dim_z=10,batch_size = 10,filter_no = [5.,5.,5.],filter_l = [10.,10.,10.],
		pooling_d=3,pooling_s=2,learning_rate = 0.0008,dim_y=None,y_train=None,diff=None,magic=5000):
		####################################### SETTINGS ###################################
		self.x_train = x_train
		self.y_train = y_train
		if y_train !=None:
			self.dim_y = dim_y
		self.diff=diff
		self.batch_size = batch_size
		self.learning_rate = theano.shared(np.float32(learning_rate))
		self.performance = {"train":[]}
		self.inpt = T.ftensor4(name='input')
		self.Y = T.fcol(name= 'label')
		self.df = T.fmatrix(name='differential')
		self.dim_z = dim_z
		self.magic =magic
		self.pooling_d = pooling_d
		self.pooling_s = pooling_s
		self.generative_z = theano.shared(np.float32(np.zeros([1,dim_z])))
		self.generative_hid = theano.shared(np.float32(np.zeros([1,magic])))
		self.activation =relu
		self.out_distribution=False
		self.in_filters = filter_l
		self.filter_lengths = filter_no
		self.params = []


		self.d_o_prob = theano.shared(np.float32(0.0))
		####################################### LAYERS ######################################
		# LAYER 1 ##############################
		self.conv1 = one_d_conv_layer(self.inpt,self.in_filters[0],1,self.filter_lengths[0],param_names = ["W1",'b1']) 
		self.params+=self.conv1.params
		self.bn1 = batchnorm(self.conv1.output)
		self.nl1 = self.activation(self.bn1.X)
		self.maxpool1 = ds.max_pool_2d(self.nl1,[self.pooling_d,1],st=[self.pooling_s,1],ignore_border = False).astype(theano.config.floatX)
		self.layer1_out = dropout(self.maxpool1,self.d_o_prob)
		self.flattened = T.flatten(self.layer1_out,outdim = 2)
		# Conditional +variational layer layer #####################
		if y_train != None:
			self.c_enc =hidden_layer(self.Y,1,self.dim_y)
			self.c_dec = hidden_layer(self.Y,1,self.dim_y,param_names = ["W10",'b10'])
			self.params+=self.c_enc.params
			self.params+=self.c_dec.params
			self.c_nl = self.activation(self.c_enc.output)
			self.c_nl_dec = self.activation(self.c_dec.output)
			self.concatenated = T.concatenate((self.flattened,self.c_nl),axis = 1)
			self.latent_layer = variational_gauss_layer(self.concatenated,self.magic+self.dim_y,dim_z)
		else:
			self.latent_layer = variational_gauss_layer(self.flattened,self.magic,dim_z)
		self.params+=self.latent_layer.params
		self.latent_out = self.latent_layer.output
		# Hidden Layer #########################
		if y_train!= None:
			self.dec_concat = T.concatenate((self.latent_out,self.c_nl_dec),axis = 1)
			self.hidden_layer = hidden_layer(self.dec_concat,self.dim_z+self.dim_y,self.magic)
		else:
			self.hidden_layer = hidden_layer(self.latent_out,dim_z,self.magic)
		self.params+=self.hidden_layer.params
		self.hid_out = dropout(self.activation(self.hidden_layer.output).reshape((self.inpt.shape[0],self.in_filters[-1],int(self.magic/self.in_filters[-1]),1)),self.d_o_prob)
		# Devonvolutional 1 ######################
		self.deconv1 = one_d_deconv_layer(self.hid_out,1,self.in_filters[2],self.filter_lengths[2],pool=self.pooling_d,param_names = ["W3",'b3'],distribution=False)
		self.params+=self.deconv1.params
		#self.nl_deconv1 = dropout(self.activation(self.deconv1.output),self.dropout_symbolic)
		self.tanh_out = self.deconv1.output
		self.last_layer = self.deconv1

		if self.out_distribution==True:
			self.trunk_sigma =  self.last_layer.log_sigma[:,:,:self.inpt.shape[2],:]
		self.trunc_output = self.tanh_out[:,:,:self.inpt.shape[2],:]
		self.cost = self.MSE()
		self.mse = self.MSE()
		#self.likelihood = self.log_px_z()
		#self.get_cost = theano.function([self.inpt],[self.cost,self.mse])

		#self.get_likelihood = theano.function([self.layer1.inpt],[self.likelihood])
		self.derivatives = T.grad(self.cost,self.params)
		#self.get_gradients = theano.function([self.inpt],self.derivatives)
		self.updates =adam(self.params,self.derivatives,self.learning_rate)
		
		################################### FUNCTIONS ######################################################
		#self.prior_debug = theano.function([self.inpt],[self.latent_out,self.latent_layer.mu_encoder,self.latent_layer.log_sigma_encoder,self.latent_layer.prior])
		#self.get_prior = theano.function([self.inpt],self.latent_layer.prior)
		#self.convolve1 = theano.function([self.inpt],self.layer1_out)
		#self.convolve2 = theano.function([self.inpt],self.layer2_out)
		#self.deconvolve1 = theano.function([self.inpt],self.deconv1.output)
		#self.deconvolve2 = theano.function([self.inpt],self.deconv2.output)
		#self.sig_out = theano.function([self.inpt],T.flatten(self.trunk_sigma,outdim=2))
		#self.output = theano.function([self.inpt],self.trunc_output,givens=[[self.dropout_symbolic,self.dropout_prob]])
		#self.generate_from_z = theano.function([self.inpt],self.trunc_output,givens = [[self.latent_out,self.generative_z]])
		#self.get_cost = theano.function([self.inpt],[self.cost,self.mse])
		#self.get_likelihood = theano.function([self.layer1.inpt],[self.likelihood])
		#self.get_gradients = theano.function([self.inpt],self.derivatives)

		self.generate_from_hid = theano.function([self.inpt],self.trunc_output,givens = [[self.hidden_layer.output,self.generative_hid]])
		self.get_flattened = theano.function([self.inpt],self.flattened)
		if self.y_train!=None:
			self.generate_from_z = theano.function([self.inpt,self.Y],self.trunc_output,givens = [[self.latent_out,self.generative_z]])
			self.train_model = theano.function(inputs = [self.inpt,self.df,self.Y],outputs = self.cost,updates = self.updates)
			self.get_latent_states = theano.function([self.inpt,self.Y],self.latent_out)
			self.get_c_enc = theano.function([self.Y],self.c_enc.output)
			self.output = theano.function([self.inpt,self.Y],self.trunc_output)
			self.get_concat = theano.function([self.inpt,self.Y],self.concatenated)
		else:
			self.generate_from_z = theano.function([self.inpt],self.trunc_output,givens = [[self.latent_out,self.generative_z]])
			self.train_model = theano.function(inputs = [self.inpt,self.df],outputs = self.cost,updates = self.updates)
			self.output = theano.function([self.inpt],self.trunc_output)
			self.get_latent_states = theano.function([self.inpt],self.latent_out)