def data_convert(): x_c, y = data_loader.process_file(all_data_dir, character_to_id, cat_to_id, config.seq_length_c) x_w, _ = data_loader_wordlevel.process_file(all_data_dir, word_to_id, cat_to_id, config.seq_length_w) file_x_c_id = open('data\\10-fold-original-data\\data-convert\\x_c_id.txt','w',encoding='utf-8') file_x_w_id = open('data\\10-fold-original-data\\data-convert\\x_w_id.txt','w',encoding='utf-8') file_y_id = open('data\\10-fold-original-data\\data-convert\\y_id.txt','w',encoding='utf-8') for data in x_c: print(len(data)) for i in data: file_x_c_id.write(str(i) + ' ') file_x_c_id.write('\n') for data in x_w: print(len(data)) for i in data: file_x_w_id.write(str(i) + ' ') file_x_w_id.write('\n') for data in y: print(len(data)) for i in data: file_y_id.write(str(i) + ' ') file_y_id.write('\n') file_x_c_id.close() file_x_w_id.close() file_y_id.close()
def test(): print("Loading test data...") start_time = time.time() x_test, y_test = process_file(test_dir, word_to_id, cat_to_id, config.seq_length) session = tf.Session() session.run(tf.global_variables_initializer()) saver = tf.train.Saver() saver.restore(sess=session, save_path=save_path) # 读取保存的模型 print('Testing...') loss_test, acc_test = evaluate(session, x_test, y_test) msg = 'Test Loss: {0:>6.2}, Test Acc: {1:>7.2%}' print(msg.format(loss_test, acc_test)) batch_size = 128 data_len = len(x_test) num_batch = int((data_len - 1) / batch_size) + 1 y_test_cls = np.argmax(y_test, 1) y_pred_cls = np.zeros(shape=len(x_test), dtype=np.int32) # 保存预测结果 for i in range(num_batch): # 逐批次处理 start_id = i * batch_size end_id = min((i + 1) * batch_size, data_len) sequence_length_vector = [ get_sequence_length() for x in range(end_id - start_id) ] feed_dict = { model.input_x: x_test[start_id:end_id], model.keep_prob: 1.0, model.sequence_length_vector: sequence_length_vector } y_pred_cls[start_id:end_id] = session.run(model.y_pred_cls, feed_dict=feed_dict) # 评估 print("Precision, Recall and F1-Score...") print( metrics.classification_report(y_test_cls, y_pred_cls, target_names=categories)) # 混淆矩阵 print("Confusion Matrix...") cm = metrics.confusion_matrix(y_test_cls, y_pred_cls) print(cm) time_dif = get_time_dif(start_time) print("Time usage:", time_dif)
def train(): print('Configuring TensorBoard and Saver...') # 配置Tensorboard ,重新训练时请将tensorboard文件夹删除,不然会覆盖 tensorboard_dir = 'tensorboard/textrnn' if not os.path.exists(tensorboard_dir): os.makedirs(tensorboard_dir) tf.summary.scalar('loss', model.loss) tf.summary.scalar('accuracy', model.acc) merged_summary = tf.summary.merge_all() writer = tf.summary.FileWriter(tensorboard_dir) # 配置 Saver saver = tf.train.Saver() if not os.path.exists(save_dir): os.makedirs(save_dir) print('Loading train and validationn data...') # 载入训练集合验证集 start_time = time.time() x_train, y_train = process_file(train_dir, word_to_id, cat_to_id, config.seq_length) x_val, y_val = process_file(val_dir) time_dif = get_time_dif(start_time) print('Time usage:', time_dif) # 创建session session = tf.Session() session.run(tf.global_variables_initializer()) writer.add_graph(session.graph) print('Training and evaluting...') start_time = time.time() total_batch = 0 # 总批次 best_acc_val = 0.0 #最佳验证集准确率 last_improved = 0 #记录上一次提升批次 require_improvement = 1000 # 如果草错1000轮未提升,提前结束训练 flag = False for epoch in range(config.num_rpochs): print('Epoch:', epoch + 1) batch_train = batch_iter(x_train, y_train, config.batch_size) for x_batch, y_batch in batch_train: feed_dict = feed_data(x_batch, y_batch, config.dropout_keep_prob) if total_batch % config.save_per_batch == 0: # 每多少轮将训练结果写入tensorboard scalar s = sesion.run(merged_summary, feed_dict=feed_dict) if total_batch % config.print_per_batch == 0: feed_dict[model.keep_prob] = 1.0 loss_train, acc_train = session.run([model.loss, model.acc], feed_dict=feed_dict) loss_val, acc_val = evalute(session, x_val, y_val) # todo if acc_val > best_acc_val: # 保存最好结果 best_acc_val = acc_val last_improved = total_batch saver.save(sess=session, save_path=save_path) improved_str = '*' else: improved_str = '' time_dif = get_time_dif(start_time) msg = "Iter:{:>6},Train Loss:{:>6.2},Train Acc:{:>7.2%}," + 'Val Loss:{:>6.2}, Val Acc:{:>7.2%} ,Time:{} {}' print( msg.format(total_batch, loss_train, acc_train, loss_val, acc_val, time_dif, improved_str)) session.run(model.optim, feed_dict=feed_dict) total_batch += 1 if total_batch - last_improved > require_improvement: # 验证集正确率长期不提升,提前结束训练 print('No optimization for a long time ,auto-stopping...') flag = True break if flag: break
def train(config, model): print("Configuring TensorBoard and Saver...") # 配置 Tensorboard,重新训练时,请将tensorboard文件夹删除,不然图会覆盖 tf.summary.scalar("loss", model.loss) tf.summary.scalar("accuracy", model.acc) merged_summary = tf.summary.merge_all() writer = tf.summary.FileWriter(config.tensorboard_dir) # 配置 Saver saver = tf.train.Saver() print("Loading training and validation data...") # 载入训练集与验证集 start_time = time.time() x_train, y_train = process_file(config.train_dir, config.word_to_id, config.cat_to_id, config.seq_length) x_val, y_val = process_file(config.val_dir, config.word_to_id, config.cat_to_id, config.seq_length) time_dif = get_time_dif(start_time) print("Time usage:", time_dif) # 创建session session = tf.Session() session.run(tf.global_variables_initializer()) writer.add_graph(session.graph) print('Training and evaluating...') start_time = time.time() total_batch = 0 # 总批次 best_acc_val = 0.0 # 最佳验证集准确率 last_improved = 0 # 记录上一次提升批次 require_improvement = 1000 # 如果超过1000轮未提升,提前结束训练 flag = False for epoch in range(config.num_epochs): print('Epoch:', epoch + 1) batch_train = batch_iter(x_train, y_train, config.batch_size) for x_batch, y_batch in batch_train: feed_dict = feed_data(model, x_batch, y_batch, config.dropout_keep_prob) if total_batch % config.save_per_batch == 0: # 每多少轮次将训练结果写入tensorboard scalar s = session.run(merged_summary, feed_dict=feed_dict) writer.add_summary(s, total_batch) if total_batch % config.print_per_batch == 0: # 每多少轮次输出在训练集和验证集上的性能 feed_dict[model.keep_prob] = 1.0 loss_train, acc_train = session.run([model.loss, model.acc], feed_dict=feed_dict) loss_val, acc_val = evaluate(session, model, x_val, y_val) if acc_val > best_acc_val: # 保存最好结果 best_acc_val = acc_val last_improved = total_batch saver.save(sess=session, save_path=config.save_path) improved_str = '*' else: improved_str = '' time_dif = get_time_dif(start_time) msg = 'Iter: {0:>6}, Train Loss: {1:>6.2}, Train Acc: {2:>7.2%},' \ + ' Val Loss: {3:>6.2}, Val Acc: {4:>7.2%}, Time: {5} {6}' print( msg.format(total_batch, loss_train, acc_train, loss_val, acc_val, time_dif, improved_str)) session.run(model.optim, feed_dict=feed_dict) # 运行优化 total_batch += 1 if total_batch - last_improved > require_improvement: # 验证集正确率长期不提升,提前结束训练 print("No optimization for a long time, auto-stopping...") flag = True break # 跳出循环 if flag: # 同上 break