def _create_loss(self): with tf.name_scope("loss"): # loss for L(Theta) # loss for L(Theta) UI_u, IU_i, IL_i, LI_l, predict_vector = self._create_inference( self.item_input) if self.ispairwise.lower() == "true": self.output = tf.reduce_sum(predict_vector, 1) _, IU_j, IL_j, _, predict_vector_neg = self._create_inference( self.item_input_neg) output_neg = tf.reduce_sum(predict_vector_neg, 1) self.result = self.output - output_neg self.loss = learner.pairwise_loss(self.loss_function, self.result) + self.reg_mf * ( tf.reduce_sum(tf.square(UI_u)) + tf.reduce_sum(tf.square(IU_i)) + tf.reduce_sum(tf.square(IL_i)) + tf.reduce_sum(tf.square(LI_l)) + tf.reduce_sum(tf.square(LI_l)) + tf.reduce_sum(tf.square(IU_j)) + tf.reduce_sum(tf.square(IL_j))) + \ self.reg_w * (tf.reduce_sum(tf.square(self.W)) + tf.reduce_sum(tf.square(self.h))) else: prediction = tf.layers.dense(inputs=predict_vector, units=1, activation=tf.nn.sigmoid) self.output = tf.squeeze(prediction) self.loss = learner.pointwise_loss( self.loss_function, self.labels, self.output) + self.reg_mf * ( tf.reduce_sum(tf.square(UI_u)) + tf.reduce_sum( tf.square(IU_i)) + tf.reduce_sum(tf.square(IL_i)) + tf.reduce_sum(tf.square(LI_l)))
def _create_loss(self): with tf.name_scope("loss"): # loss for L(Theta) p1, q1, r1, predict_vector = self._create_inference( self.item_input) if self.ispairwise.lower() == "true": self.output = tf.reduce_sum(predict_vector, 1) _, q2, _, predict_vector_neg = self._create_inference( self.item_input_neg) output_neg = tf.reduce_sum(predict_vector_neg, 1) self.result = self.output - output_neg self.loss = learner.pairwise_loss( self.loss_function, self.result) + self.reg_mf * ( tf.reduce_sum(tf.square(p1)) + tf.reduce_sum( tf.square(r1)) + tf.reduce_sum(tf.square(q2)) + tf.reduce_sum(tf.square(q1))) else: prediction = tf.layers.dense(inputs=predict_vector, units=1, activation=tf.nn.sigmoid) self.output = tf.squeeze(prediction) self.loss = learner.pointwise_loss( self.loss_function, self.lables, self.output) + self.reg_mf * (tf.reduce_sum( tf.square(p1)) + tf.reduce_sum(tf.square(r1)) + tf.reduce_sum(tf.square(q1)))
def _create_loss(self): with tf.name_scope("loss"): # loss for L(Theta) p1,q1,r1,predict_vector = self._create_inference() prediction = tf.layers.dense(inputs=predict_vector,units=1, activation=tf.nn.sigmoid) self.output = tf.squeeze(prediction) self.loss = learner.pointwise_loss(self.loss_function,self.lables,self.output) + self.reg_mf * (tf.reduce_sum(tf.square(p1)) \ +tf.reduce_sum(tf.square(r1))+ tf.reduce_sum(tf.square(q1)))
def _create_loss(self): with tf.name_scope("loss"): self.loss = learner.pointwise_loss(self.loss_function, self.input_R, self.output) self.reg_loss = self.reg * ( tf.nn.l2_loss(self.weights['encoder']) + tf.nn.l2_loss(self.weights['decoder']) + tf.nn.l2_loss(self.biases['encoder']) + tf.nn.l2_loss(self.biases['decoder'])) self.loss = self.loss + self.reg_loss
def _create_loss(self): with tf.name_scope("loss"): UI_u, IU_i, LI_l, predict_vector = self._create_inference() prediction = tf.layers.dense(inputs=predict_vector, units=1, activation=tf.nn.sigmoid) self.output = tf.squeeze(prediction) self.loss = learner.pointwise_loss(self.loss_function,self.lables,self.output) + self.reg* (tf.reduce_sum(tf.square(UI_u)) \ +tf.reduce_sum(tf.square(IU_i))+tf.reduce_sum(tf.square(LI_l)))
def _create_loss(self): with tf.name_scope("loss"): p1, q1, self.output = self._create_inference(self.item_input) if self.is_pairwise is True: _, q2, self.output_neg = self._create_inference(self.item_input_neg) result = self.output - self.output_neg self.loss = learner.pairwise_loss(self.loss_function, result) + self.reg_mlp * l2_loss(p1, q2, q1) else: self.loss = learner.pointwise_loss(self.loss_function, self.labels, self.output) + \ self.reg_mlp * l2_loss(p1, q1)
def _create_loss(self): with tf.name_scope("loss"): # loss for L(Theta) p1,q1,r1,self.output = self._create_inference(self.item_input) if self.ispairwise.lower() =="true": _, q2,_,output_neg = self._create_inference(self.item_input_neg) self.result = self.output - output_neg self.loss = learner.pairwise_loss(self.loss_function,self.result) + self.reg_mf * ( tf.reduce_sum(tf.square(p1)) \ +tf.reduce_sum(tf.square(r1)) + tf.reduce_sum(tf.square(q2)) + tf.reduce_sum(tf.square(q1))) else : self.loss = learner.pointwise_loss(self.loss_function,self.lables,self.output) + self.reg_mf * (tf.reduce_sum(tf.square(p1)) \ +tf.reduce_sum(tf.square(r1))+ tf.reduce_sum(tf.square(q1)))
def _create_loss(self): with tf.name_scope("loss"): p1, q1, self.output = self._create_inference(self.user_input, self.item_input, self.num_idx) if self.is_pairwise is True: _, q2, output_neg = self._create_inference(self.user_input_neg, self.item_input_neg, self.num_idx_neg) self.result = self.output - output_neg self.loss = learner.pairwise_loss(self.loss_function, self.result) + \ self.lambda_bilinear * l2_loss(p1) + \ self.gamma_bilinear * l2_loss(q2, q1) else: self.loss = learner.pointwise_loss(self.loss_function, self.labels, self.output) + \ self.lambda_bilinear * l2_loss(p1) + \ self.gamma_bilinear * l2_loss(q1)
def _create_loss(self): with tf.name_scope("loss"): # loss for L(Theta) p1, r1, q1, b1, self.output = self._create_inference( self.item_input) if self.is_pairwise is True: _, _, q2, b2, output_neg = self._create_inference( self.item_input_neg) self.result = self.output - output_neg self.loss = learner.pairwise_loss(self.loss_function, self.result) + \ self.reg_mf * l2_loss(p1, r1, q2, q1, b1, b2, self.global_embedding) else: self.loss = learner.pointwise_loss(self.loss_function, self.labels, self.output) + \ self.reg_mf * l2_loss(p1, r1, q1, b1, self.global_embedding)
def _create_loss(self): with tf.name_scope("loss"): UI_u, IU_i, IL_i, LI_l, self.output = self._create_inference( self.item_input) if self.is_pairwise is True: _, IU_j, IL_j, _, output_neg = self._create_inference( self.item_input_neg) self.result = self.output - output_neg self.loss = learner.pairwise_loss(self.loss_function, self.result) + \ self.reg_mf * l2_loss(UI_u, IU_i, IL_i, LI_l, IU_j, IL_j) + \ self.reg_w * l2_loss(self.W, self.h) else: self.loss = learner.pointwise_loss(self.loss_function, self.labels, self.output) + \ self.reg_mf * l2_loss(UI_u, IU_i, IL_i, LI_l)
def _create_loss(self): with tf.name_scope("loss"): # loss for L(Theta) UI_u, IU_i, IL_i, LI_l, self.output = self._create_inference( self.item_input) if self.ispairwise.lower() == "true": _, IU_j, IL_j, _, output_neg = self._create_inference( self.item_input_neg) self.result = self.output - output_neg self.loss = learner.pairwise_loss(self.loss_function,self.result) + self.reg_mf * ( tf.reduce_sum(tf.square(UI_u)) \ + tf.reduce_sum(tf.square(IU_i)) + tf.reduce_sum(tf.square(IL_i)) + tf.reduce_sum(tf.square(LI_l))+ \ tf.reduce_sum(tf.square(LI_l))+tf.reduce_sum(tf.square(IU_j))+tf.reduce_sum(tf.square(IL_j))) else: self.loss = learner.pointwise_loss(self.loss_function,self.lables,self.output) + self.reg_mf * (tf.reduce_sum(tf.square(UI_u)) \ +tf.reduce_sum(tf.square(IU_i))+ tf.reduce_sum(tf.square(IL_i))+tf.reduce_sum(tf.square(LI_l)))
def _create_loss(self): with tf.name_scope("loss"): p1, q1, self.output = self._create_inference( self.user_input, self.item_input, self.num_idx) if self.ispairwise.lower() == "true": _, q2, output_neg = self._create_inference( self.user_input_neg, self.item_input_neg, self.num_idx_neg) self.result = self.output - output_neg self.loss = learner.pairwise_loss(self.loss_function,self.result) + self.lambda_bilinear * ( tf.reduce_sum(tf.square(p1))) \ +self.gamma_bilinear*(tf.reduce_sum(tf.square(q2)) + tf.reduce_sum(tf.square(q1))) else: self.loss = learner.pointwise_loss(self.loss_function, \ self.lables,tf.sigmoid(self.output)) + self.lambda_bilinear *\ (tf.reduce_sum(tf.square(p1)))+self.gamma_bilinear *(tf.reduce_sum(tf.square(q1)))
def _create_loss(self): with tf.name_scope("loss"): # loss for L(Theta) p1,q1,r1,self.output = self._create_inference() self.loss = learner.pointwise_loss(self.loss_function,self.lables,self.output) + self.reg_mf * (tf.reduce_sum(tf.square(p1)) \ +tf.reduce_sum(tf.square(r1))+ tf.reduce_sum(tf.square(q1)))
#!/usr/local/bin/python
def _create_loss(self): with tf.name_scope("loss"): UI_u, IU_i, LI_l, self.output = self._create_inference() self.loss = learner.pointwise_loss(self.loss_function, self.labels, self.output) + \ self.reg * l2_loss(UI_u, IU_i, LI_l)
def _create_loss(self): with tf.name_scope("loss"): self.loss = learner.pointwise_loss(self.loss_function, self.labels, self.output)
def _create_loss(self): with tf.name_scope("loss"): UI_u, IU_i, LI_l, self.output = self._create_inference() self.loss = learner.pointwise_loss(self.loss_function,self.lables,self.output) + self.reg* (tf.reduce_sum(tf.square(UI_u)) \ +tf.reduce_sum(tf.square(IU_i))+tf.reduce_sum(tf.square(LI_l)))
def _create_loss(self): with tf.name_scope("loss"): # loss for L(Theta) p1, q1, r1, self.output = self._create_inference() self.loss = learner.pointwise_loss(self.loss_function, self.labels, self.output) + \ self.reg_mf * l2_loss(p1, r1, q1)