def evaluate(model, Loss, x_val, y_val): """测试集上准确率评估""" batch_val = batch_iter(x_val, y_val, 64) acc = 0 los = 0 model.eval() with torch.no_grad(): for x_batch, y_batch in batch_val: size = len(x_batch) x = np.array(x_batch) y = np.array(y_batch) x = torch.LongTensor(x) y = torch.Tensor(y) # y = torch.LongTensor(y) # x = Variable(x) # y = Variable(y) out = model(x) loss = Loss(out, y) # optimizer.zero_grad() # loss.backward() # optimizer.step() loss_value = np.mean(loss.numpy()) accracy = np.mean((torch.argmax(out, 1) == torch.argmax(y, 1)).numpy()) acc += accracy * size los += loss_value * size model.train() return los / len(x_val), acc / len(x_val)
def evaluate(sess,x_,y_): data_len=len(x_) batch_eval=batch_iter(x_,y_,128) total_loss=0.0 total_acc=0.0 for x_batch,y_batch in batch_eval: batch_len=len(x_batch) feed_dict=feed_data(x_batch,y_batch,1.0) loss,acc=sess.run([model.loss,model.acc],feed_dict=feed_dict) total_loss+=loss*batch_len total_acc+=acc*batch_len return total_loss/data_len,total_acc/data_len
def evaluate(sess, x_, y_): """评估在某一数据上的准确率和损失""" data_len = len(x_) batch_eval = batch_iter(x_, y_, 128) total_loss = 0.0 total_acc = 0.0 for x_batch, y_batch in batch_eval: batch_len = len(x_batch) feed_dict = feed_data(x_batch, y_batch, 1.0) y_pred_class,loss, acc = sess.run([model.y_pred_cls,model.loss, model.acc], feed_dict=feed_dict) total_loss += loss * batch_len total_acc += acc * batch_len return y_pred_class,total_loss / data_len, total_acc / data_len
def train(): x_train, y_train = process_file(train_dir, word_to_id, cat_to_id, 600) #获取训练数据每个字的id和对应标签的oe-hot形式 x_val, y_val = process_file(val_dir, word_to_id, cat_to_id, 600) #使用LSTM或者CNN model = TextRNN() model.train() # model = TextCNN() #选择损失函数 Loss = nn.MultiLabelSoftMarginLoss() # Loss = nn.BCELoss() # Loss = nn.MSELoss() optimizer = optim.Adam(model.parameters(), lr=0.001) best_val_acc = 0 for epoch in range(100): i = 0 print('epoch:{}'.format(epoch)) batch_train = batch_iter(x_train, y_train, 64) for x_batch, y_batch in batch_train: i += 1 # print(i) x = np.array(x_batch) y = np.array(y_batch) x = torch.LongTensor(x) y = torch.Tensor(y) # y = torch.LongTensor(y) # x = Variable(x) # y = Variable(y) out = model(x) loss = Loss(out, y) optimizer.zero_grad() loss.backward() optimizer.step() # 对模型进行验证 if i % 90 == 0: los, accracy = evaluate(model, Loss, x_val, y_val) # 此处不需要优化器参数 print('loss:{},accracy:{}'.format(los, accracy)) if accracy > best_val_acc: torch.save(model.state_dict(), 'model_params.pkl') best_val_acc = accracy
def train(): print("Configuring TensorBoard and Saver...") # 配置 Tensorboard,重新训练时,请将tensorboard文件夹删除,不然图会覆盖 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 training and validation data...") # 载入训练集与验证集 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, word_to_id, 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(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, 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: {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
def train(): print("Configuring TensorBoard and Saver...") tensorboard_dir = 'tensorboard/textcnn' if not os.path.exists(tensorboard_dir): os.makedirs(tensorboard_dir) tf.summary.scalar("loss", model.loss) tf.summary.scalar("accuracy", model.acc) # 用到 tf.summary 中的方法保存日志数据,用于tensorboard可视化操作。 # 用 tf.summary.scalar 保存标量,一般用来保存loss,accuary,学习率等数据 merged_summary = tf.summary.merge_all() writer = tf.summary.FileWriter(tensorboard_dir) # 使用 tf.summaries.merge_all() 对所有的汇总操作进行合并 # 将数据写入本地磁盘: tf.summary.FileWriter saver = tf.train.Saver() if not os.path.exists(save_dir): os.makedirs(save_dir) print("Loading training and validation data...") 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, word_to_id, cat_to_id, config.seq_length) time_dif = get_time_dif(start_time) print("Time usage:", time_dif) 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 best_acc_val = 0.0 last_improved = 0 require_improvement = 1000 # 如果超过1000轮未提升,提前结束训练,防止过拟合。 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(x_batch, y_batch, config.dropout_keep_prob) if total_batch % config.save_per_batch == 0: s = session.run(merged_summary, feed_dict=feed_dict) writer.add_summary(s, total_batch) 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 = evaluate(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: {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 if flag: break
def train(): print("configuring tensorboard and saver") tensorboard_dir="tensorboard/textcnn" 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) saver=tf.train.Saver() if not os.path.exists(save_dir): os.makedirs(save_dir) print("loading training and validation data..") 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,word_to_id,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 evaluate...") start_time=time.time() total_batch=0 best_acc_val=0.0 last_improved=0 require_improvement=1000 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(x_batch,y_batch,config.dropout_keep_prob) if(total_batch%config.save_per_batch==0): s=session.run(merged_summary,feed_dict=feed_dict) writer.add_summary(s,total_batch) 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=evaluate( session,x_val,y_val ) # 保存最好的结果 if acc_val>best_acc_val: best_acc_val=acc_val last_improved=0 saver.save(sess=session,save_path=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}" 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) total_batch+=1 if total_batch-last_improved>require_improvement: print("no optimization for a long time, auto-stopping...") flag=True break if flag: break