def train(self, sess, save_file, X_train, y_train, X_val, y_val): count = 0 max_f = -1 writer = tf.summary.FileWriter('./graphs_ar', sess.graph) trainloss = tf.summary.scalar("training_loss", self.ner_model.loss) for epoch in range(self.num_epochs): print "current epoch: %d" % (epoch) for iteration in range(self.num_iterations): print "this iteration is %d"%(iteration) X_train_batch, y_train_batch = helper.nextRandomBatch(X_train, y_train, batch_size=self.batch_size) transition_batch = helper.getTransition(y_train_batch) _, train_loss, loss_train, max_scores, max_scores_pre, length =\ sess.run([ self.ner_model.optimizer, trainloss, self.ner_model.loss, self.ner_model.max_scores, self.ner_model.max_scores_pre, self.ner_model.length, ], feed_dict={ self.ner_model.input_data:X_train_batch, self.ner_model.targets:y_train_batch, self.ner_model.targets_transition:transition_batch }) print "the loss : %f"%loss_train#, X_train_batch writer.add_summary(train_loss, epoch*self.num_iterations+iteration) if iteration % 100 == 0: presicion_loc, recall_loc, f_loc, presicion_org, recall_org, f_org, presicion_per, recall_per, f_per = \ self.validationBatch(sess, X_val, y_val) print "iteration: %5d, valid , valid precision: LOC %.5f, ORG %.5f, PER %.5f, valid recall: LOC %.5f, ORG %.5f, PER %.5f, valid f1: LOC %.5f, ORG %.5f, PER %.5f" %\ (iteration, presicion_loc, presicion_org, presicion_per, recall_loc, recall_org, recall_per, f_loc, f_org, f_per) if f_loc + f_org + f_per >= max_f: max_f = f_loc + f_org + f_per saver = tf.train.Saver() save_path = saver.save(sess, save_file) print "saved the best model with f1: %.5f" % (max_f / 3.0) self.last_f = f_loc + f_org + f_per
def train(self, sess, save_file, X_train, y_train, X_val, y_val): saver = tf.train.Saver() char2id, id2char = helper.loadMap("char2id") label2id, id2label = helper.loadMap("label2id") merged = tf.contrib.deprecated.merge_all_summaries() summary_writer_train = tf.contrib.summary.SummaryWriter( 'loss_log/train_loss', sess.graph) summary_writer_val = tf.contrib.summary.SummaryWriter( 'loss_log/val_loss', sess.graph) num_iterations = int(math.ceil(1.0 * len(X_train) / self.batch_size)) cnt = 0 for epoch in range(self.num_epochs): # shuffle train in each epoch sh_index = np.arange(len(X_train)) np.random.shuffle(sh_index) X_train = X_train[sh_index] y_train = y_train[sh_index] print("current epoch: %d" % (epoch)) for iteration in range(num_iterations): # train X_train_batch, y_train_batch = helper.nextBatch( X_train, y_train, start_index=iteration * self.batch_size, batch_size=self.batch_size) y_train_weight_batch = 1 + np.array( (y_train_batch == label2id['B']) | (y_train_batch == label2id['E']), float) transition_batch = helper.getTransition(y_train_batch) _, loss_train, max_scores, max_scores_pre, length, train_summary = \ sess.run([ self.optimizer, self.loss, self.max_scores, self.max_scores_pre, self.length, self.train_summary ], feed_dict={ self.targets_transition: transition_batch, self.inputs: X_train_batch, self.targets: y_train_batch, self.targets_weight: y_train_weight_batch }) predicts_train = self.viterbi(max_scores, max_scores_pre, length, predict_size=self.batch_size) if iteration % 10 == 0: cnt += 1 precision_train, recall_train, f1_train = self.evaluate( X_train_batch, y_train_batch, predicts_train, id2char, id2label) summary_writer_train.add_summary(train_summary, cnt) print( "iteration: %5d, train loss: %5d, train precision: %.5f, train recall: %.5f, train f1: %.5f" % (iteration, loss_train, precision_train, recall_train, f1_train)) # validation if iteration % 100 == 0: X_val_batch, y_val_batch = helper.nextRandomBatch( X_val, y_val, batch_size=self.batch_size) y_val_weight_batch = 1 + np.array( (y_val_batch == label2id['B']) | (y_val_batch == label2id['E']), float) transition_batch = helper.getTransition(y_val_batch) loss_val, max_scores, max_scores_pre, length, val_summary = \ sess.run([ self.loss, self.max_scores, self.max_scores_pre, self.length, self.val_summary ], feed_dict={ self.targets_transition: transition_batch, self.inputs: X_val_batch, self.targets: y_val_batch, self.targets_weight: y_val_weight_batch }) predicts_val = self.viterbi(max_scores, max_scores_pre, length, predict_size=self.batch_size) precision_val, recall_val, f1_val = self.evaluate( X_val_batch, y_val_batch, predicts_val, id2char, id2label) summary_writer_val.add_summary(val_summary, cnt) print( "iteration: %5d, valid loss: %5d, valid precision: %.5f, valid recall: %.5f, valid f1: %.5f" % (iteration, loss_val, precision_val, recall_val, f1_val)) if f1_val > self.max_f1: self.max_f1 = f1_val save_path = saver.save(sess, save_file) print("saved the best model with f1: %.5f" % (self.max_f1))
def train(self, sess, save_file, train_data, val_data): saver = tf.train.Saver(max_to_keep=3) #train data X_train = train_data['char'] X_left_train = train_data['left'] X_right_train = train_data['right'] X_pos_train = train_data['pos'] X_lpos_train = train_data['lpos'] X_rpos_train = train_data['rpos'] X_rel_train = train_data['rel'] X_dis_train = train_data['dis'] y_train = train_data['label'] #dev data X_val = val_data['char'] X_left_val = val_data['left'] X_right_val = val_data['right'] X_pos_val = val_data['pos'] X_lpos_val = val_data['lpos'] X_rpos_val = val_data['rpos'] X_rel_val = val_data['rel'] X_dis_val = val_data['dis'] y_val = val_data['label'] #dictionary char2id, id2char = helper.loadMap("char2id") pos2id, id2pos = helper.loadMap("pos2id") label2id, id2label = helper.loadMap("label2id") merged = tf.summary.merge_all() summary_writer_train = tf.summary.FileWriter('loss_log/train_loss', sess.graph) summary_writer_val = tf.summary.FileWriter('loss_log/val_loss', sess.graph) num_iterations = int(math.ceil(1.0 * len(X_train) / self.batch_size)) cnt = 0 for epoch in range(self.num_epochs): # shuffle train in each epoch sh_index = np.arange(len(X_train)) np.random.shuffle(sh_index) X_train = X_train[sh_index] X_left_train = X_left_train[sh_index] X_right_train = X_right_train[sh_index] X_pos_train = X_pos_train[sh_index] X_lpos_train = X_lpos_train[sh_index] X_rpos_train = X_rpos_train[sh_index] X_rel_train = X_rel_train[sh_index] X_dis_train = X_dis_train[sh_index] y_train = y_train[sh_index] train_data['char'] = X_train train_data['left'] = X_left_train train_data['right'] = X_right_train train_data['pos'] = X_pos_train train_data['lpos'] = X_lpos_train train_data['rpos'] = X_rpos_train train_data['rel'] = X_rel_train train_data['dis'] = X_dis_train train_data['label'] = y_train print "current epoch: %d" % (epoch) for iteration in range(num_iterations): # train #get batch train_batches = helper.nextBatch(train_data, start_index=iteration * self.batch_size, batch_size=self.batch_size) X_train_batch = train_batches['char'] X_left_train_batch = train_batches['left'] X_right_train_batch = train_batches['right'] X_pos_train_batch = train_batches['pos'] X_lpos_train_batch = train_batches['lpos'] X_rpos_train_batch = train_batches['rpos'] X_rel_train_batch = train_batches['rel'] X_dis_train_batch = train_batches['dis'] y_train_batch = train_batches['label'] # feed batch to model and run _, loss_train, length, train_summary, logits, trans_params =\ sess.run([ self.optimizer, self.loss, self.length, self.train_summary, self.logits, self.trans_params, ], feed_dict={ self.inputs:X_train_batch, self.lefts:X_left_train_batch, self.rights:X_right_train_batch, self.poses:X_pos_train_batch, self.lposes:X_lpos_train_batch, self.rposes:X_rpos_train_batch, self.rels:X_rel_train_batch, self.dises:X_dis_train_batch, self.targets:y_train_batch # self.targets_weight:y_train_weight_batch }) # print (len(length)) #get predict f1 predicts_train = self.viterbi(logits, trans_params, length, predict_size=self.batch_size) if iteration > 0 and iteration % 10 == 0: cnt += 1 hit_num, pred_num, true_num = self.evaluate(y_train_batch, predicts_train, id2char, id2label) precision_train, recall_train, f1_train = self.caculate(hit_num, pred_num, true_num) summary_writer_train.add_summary(train_summary, cnt) print "iteration: %5d/%5d, train loss: %5d, train precision: %.5f, train recall: %.5f, train f1: %.5f" % (iteration, num_iterations, loss_train, precision_train, recall_train, f1_train) # a batch in validation if iteration > 0 and iteration % 100 == 0: val_batches = helper.nextRandomBatch(val_data, batch_size=self.batch_size) X_val_batch = val_batches['char'] X_left_val_batch = val_batches['left'] X_right_val_batch = val_batches['right'] X_pos_val_batch = val_batches['pos'] X_lpos_val_batch = val_batches['lpos'] X_rpos_val_batch = val_batches['rpos'] X_rel_val_batch = val_batches['rel'] X_dis_val_batch = val_batches['dis'] y_val_batch = val_batches['label'] loss_val, length, val_summary, logits, trans_params =\ sess.run([ self.loss, self.length, self.val_summary, self.logits, self.trans_params, ], feed_dict={ self.inputs:X_val_batch, self.lefts:X_left_val_batch, self.rights:X_right_val_batch, self.poses:X_pos_val_batch, self.lposes:X_lpos_val_batch, self.rposes:X_rpos_val_batch, self.rels:X_rel_val_batch, self.dises:X_dis_val_batch, self.targets:y_val_batch # self.targets_weight:y_val_weight_batch }) predicts_val = self.viterbi(logits, trans_params, length, predict_size=self.batch_size) hit_num, pred_num, true_num = self.evaluate(y_val_batch, predicts_val, id2char, id2label) precision_val, recall_val, f1_val = self.caculate(hit_num, pred_num, true_num) summary_writer_val.add_summary(val_summary, cnt) print "iteration: %5d, valid loss: %5d, valid precision: %.5f, valid recall: %.5f, valid f1: %.5f" % (iteration, loss_val, precision_val, recall_val, f1_val) # calc f1 for the whole dev set if epoch > 0 and iteration == num_iterations -1: num_val_iterations = int(math.ceil(1.0 * len(X_val) / self.batch_size)) preds_lines = [] for val_iteration in range(num_val_iterations): val_batches = helper.nextBatch(val_data, start_index=val_iteration * self.batch_size, batch_size=self.batch_size) X_val_batch = val_batches['char'] X_left_val_batch = val_batches['left'] X_right_val_batch = val_batches['right'] X_pos_val_batch = val_batches['pos'] X_lpos_val_batch = val_batches['lpos'] X_rpos_val_batch = val_batches['rpos'] X_rel_val_batch = val_batches['rel'] X_dis_val_batch = val_batches['dis'] y_val_batch = val_batches['label'] loss_val, length, val_summary, logits, trans_params =\ sess.run([ self.loss, self.length, self.val_summary, self.logits, self.trans_params, ], feed_dict={ self.inputs:X_val_batch, self.lefts:X_left_val_batch, self.rights:X_right_val_batch, self.poses:X_pos_val_batch, self.lposes:X_lpos_val_batch, self.rposes:X_rpos_val_batch, self.rels:X_rel_val_batch, self.dises:X_dis_val_batch, self.targets:y_val_batch # self.targets_weight:y_val_weight_batch }) predicts_val = self.viterbi(logits, trans_params, length, predict_size=self.batch_size) preds_lines.extend(predicts_val) preds_lines = preds_lines[:len(y_val)] recall_val, precision_val, f1_val, errors = helper.calc_f1(preds_lines, id2label, 'cpbdev.txt', 'validation.out') if f1_val > self.max_f1: self.max_f1 = f1_val save_path = saver.save(sess, save_file) helper.calc_f1(preds_lines, id2label, 'cpbdev.txt', 'validation.out.best') print "saved the best model with f1: %.5f" % (self.max_f1) print "valid precision: %.5f, valid recall: %.5f, valid f1: %.5f, errors: %5d" % (precision_val, recall_val, f1_val, errors)
def train(self, sess, save_file, X_train, y_train, X_val, y_val): saver = tf.train.Saver() char2id, id2char = helper.loadMap("char2id") label2id, id2label = helper.loadMap("label2id") merged = tf.merge_all_summaries() summary_writer_train = tf.train.SummaryWriter('loss_log/train_loss', sess.graph) summary_writer_val = tf.train.SummaryWriter('loss_log/val_loss', sess.graph) num_iterations = int(math.ceil(1.0 * len(X_train) / self.batch_size)) cnt = 0 for epoch in range(self.num_epochs): # shuffle train in each epoch sh_index = np.arange(len(X_train)) np.random.shuffle(sh_index) X_train = X_train[sh_index] y_train = y_train[sh_index] print "current epoch: %d" % (epoch) for iteration in range(num_iterations): # train X_train_batch, y_train_batch = helper.nextBatch(X_train, y_train, start_index=iteration * self.batch_size, batch_size=self.batch_size) y_train_weight_batch = 1 + np.array((y_train_batch == label2id['B']) | (y_train_batch == label2id['E']), float) transition_batch = helper.getTransition(y_train_batch) _, loss_train, max_scores, max_scores_pre, length, train_summary =\ sess.run([ self.optimizer, self.loss, self.max_scores, self.max_scores_pre, self.length, self.train_summary ], feed_dict={ self.targets_transition:transition_batch, self.inputs:X_train_batch, self.targets:y_train_batch, self.targets_weight:y_train_weight_batch }) predicts_train = self.viterbi(max_scores, max_scores_pre, length, predict_size=self.batch_size) if iteration % 10 == 0: cnt += 1 precision_train, recall_train, f1_train = self.evaluate(X_train_batch, y_train_batch, predicts_train, id2char, id2label) summary_writer_train.add_summary(train_summary, cnt) print "iteration: %5d, train loss: %5d, train precision: %.5f, train recall: %.5f, train f1: %.5f" % (iteration, loss_train, precision_train, recall_train, f1_train) # validation if iteration % 100 == 0: X_val_batch, y_val_batch = helper.nextRandomBatch(X_val, y_val, batch_size=self.batch_size) y_val_weight_batch = 1 + np.array((y_val_batch == label2id['B']) | (y_val_batch == label2id['E']), float) transition_batch = helper.getTransition(y_val_batch) loss_val, max_scores, max_scores_pre, length, val_summary =\ sess.run([ self.loss, self.max_scores, self.max_scores_pre, self.length, self.val_summary ], feed_dict={ self.targets_transition:transition_batch, self.inputs:X_val_batch, self.targets:y_val_batch, self.targets_weight:y_val_weight_batch }) predicts_val = self.viterbi(max_scores, max_scores_pre, length, predict_size=self.batch_size) precision_val, recall_val, f1_val = self.evaluate(X_val_batch, y_val_batch, predicts_val, id2char, id2label) summary_writer_val.add_summary(val_summary, cnt) print "iteration: %5d, valid loss: %5d, valid precision: %.5f, valid recall: %.5f, valid f1: %.5f" % (iteration, loss_val, precision_val, recall_val, f1_val) if f1_val > self.max_f1: self.max_f1 = f1_val save_path = saver.save(sess, save_file) print "saved the best model with f1: %.5f" % (self.max_f1)
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) # Initializing the variables init = tf.global_variables_initializer() # Launch the graph with tf.Session() as sess: sess.run(init) step = 0 # Keep training until reach max iterations while step < training_iters: # batch_x, batch_y = mnist.train.next_batch(batch_size) batch_x, batch_y = helper.nextRandomBatch(X_train, y_train, batch_size=125) batch_y = batch_y[:, 2] tmp_y = [] for i in range(0, batch_y.shape[0]): if batch_y[i] == 2: tmp_y.append([0, 1]) else: tmp_y.append([1, 0]) tmp_y = np.array(tmp_y) batch_y = tmp_y # Run optimization op (backprop) sess.run(optimizer, feed_dict={x1: batch_x, y: batch_y}) if step % display_step == 0: # Calculate batch accuracy
def train(self, sess, save_file, X_train, y_train, X_val, y_val): saver = tf.train.Saver() summary_writer_train = tf.summary.FileWriter('loss_log/train_loss', sess.graph) summary_writer_val = tf.summary.FileWriter('loss_log/val_loss', sess.graph) num_iterations = int(math.ceil(1.0 * len(X_train) / self.batch_size)) for epoch in range(self.num_epochs): # shuffle train in each epoch sh_index = np.arange(len(X_train)) np.random.shuffle(sh_index) X_train = X_train[sh_index] y_train = y_train[sh_index] print("current epoch: %d" % (epoch)) for iteration in range(num_iterations): # train X_train_batch1, X_train_batch2, y_train_batch = helper.nextBatch( X_train, y_train, iteration * self.batch_size, self.batch_size) _, train_loss, train_acc, train_summary = sess.run( [ self.optimizer, self.loss, # self.predictions, self.accuracy, self.summary_op ], feed_dict={ self.input1: X_train_batch1, self.input2: X_train_batch2, self.targets: y_train_batch }) if iteration % 20 == 0: # train_acc = helper.extractSense(y_train_batch, train_y_hat) summary_writer_train.add_summary(train_summary, iteration) print( "iteration: %5d, train loss: %5d, train precision: %.5f" % (iteration, train_loss, train_acc)) # validation if iteration % 20 == 0: X_val_batch1, X_val_batch2, y_val_batch = helper.nextRandomBatch( X_val, y_val, self.batch_size) dev_loss, dev_acc, val_summary = sess.run( [ self.loss, # self.predictions, self.accuracy, self.summary_op ], feed_dict={ self.input1: X_val_batch1, self.input2: X_val_batch2, self.targets: y_val_batch }) # test_acc = helper.extractSense(y_val_batch, dev_y_hat) summary_writer_val.add_summary(val_summary, iteration) print( "iteration: %5d, dev loss: %5d, dev precision: %.5f" % (iteration, dev_loss, dev_acc)) if dev_acc > self.max_acc: self.max_acc = dev_acc saver.save(sess, save_file) print("saved the best model with accuracy: %.5f" % (self.max_acc))