p6_fastTextB_model_multilabel.py 文件源码

def loss(self,l2_lambda=0.0001):
        """calculate loss using (NCE)cross entropy here"""
        # Compute the average NCE loss for the batch.
        # tf.nce_loss automatically draws a new sample of the negative labels each
        # time we evaluate the loss.
        if self.is_training:#training
            #labels=tf.reshape(self.labels,[-1])               #3.[batch_size,max_label_per_example]------>[batch_size*max_label_per_example,]
            #labels=tf.expand_dims(labels,1)                   #[batch_size*max_label_per_example,]----->[batch_size*max_label_per_example,1]
            #nce_loss: notice-->for now, if you have a variable number of target classes, you can pad them out to a constant number by either repeating them or by padding with an otherwise unused class.
            loss = tf.reduce_mean(#inputs's SHAPE should be: [batch_size, dim]
                tf.nn.nce_loss(weights=tf.transpose(self.W),  #[embed_size, label_size]--->[label_size,embed_size]. nce_weights:A `Tensor` of shape `[num_classes, dim].O.K.
                               biases=self.b,                 #[label_size]. nce_biases:A `Tensor` of shape `[num_classes]`.
                               labels=self.labels,                 #4.[batch_size,max_label_per_example]. train_labels, # A `Tensor` of type `int64` and shape `[batch_size,num_true]`. The target classes.
                               inputs=self.sentence_embeddings,#TODO [None,self.embed_size] #A `Tensor` of shape `[batch_size, dim]`.  The forward activations of the input network.
                               num_sampled=self.num_sampled,  #  scalar. 100
                               num_true=self.max_label_per_example,
                               num_classes=self.label_size,partition_strategy="div"))  #scalar. 1999
        else:#eval(/inference)
            labels_multi_hot = self.labels_l1999 #[batch_size,label_size]
            #sigmoid_cross_entropy_with_logits:Computes sigmoid cross entropy given `logits`.Measures the probability error in discrete classification tasks in which each class is independent and not mutually exclusive.  For instance, one could perform multilabel classification where a picture can contain both an elephant and a dog at the same time.
            loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=labels_multi_hot,logits=self.logits) #labels:[batch_size,label_size];logits:[batch, label_size]
            loss = tf.reduce_sum(loss, axis=1)

        # add regularization result in not converge
        l2_losses = tf.add_n([tf.nn.l2_loss(v) for v in tf.trainable_variables() if 'bias' not in v.name]) * l2_lambda
        loss=loss+l2_losses
        return loss