def train_one_step(batch, loss_op, train_op): feed_dict = expand_feed_dict({model.src_pls: batch[0], model.dst_pls: batch[1]}) step, lr, loss, _ = sess.run( [model.global_step, model.learning_rate, loss_op, train_op], feed_dict=feed_dict) if step % config.train.summary_freq == 0: summary = sess.run(model.summary_op, feed_dict=feed_dict) summary_writer.add_summary(summary, global_step=step) return step, lr, loss
def train_one_step(batch): feat_batch, target_batch,batch_size = batch feed_dict = expand_feed_dict({model.src_pls: feat_batch, model.dst_pls: target_batch}) step, lr, loss, _ = sess.run( [model.global_step, model.learning_rate, model.loss, model.train_op], feed_dict=feed_dict) if step % config.train.summary_freq == 0: summary = sess.run(model.summary_op, feed_dict=feed_dict) summary_writer.add_summary(summary, global_step=step) return step, lr, loss
def loss_label(self, X, Y, Z): return self.sess.run(self.model.loss_sum, feed_dict=expand_feed_dict({self.model.src_pls: X, self.model.dst_pls: Y, self.model.label_pls: Z}))
def loss(self, X, Y): return self.sess.run(self.model.loss_sum, feed_dict=expand_feed_dict({self.model.src_pls: X, self.model.dst_pls: Y}))
def beam_search_label(self, X, Y, Z, X_lens): return self.sess.run([self.model.prediction, self.model.prediction_label], feed_dict=expand_feed_dict({self.model.src_pls: X, self.model.dst_pls: Y, self.model.label_pls: Z, self.model.src_len_pls: X_lens}))
def beam_search(self, X): return self.sess.run(self.model.prediction, feed_dict=expand_feed_dict({self.model.src_pls: X}))