def main(_): model = BERT_NER(param) model.build(input_shape=(4, param.batch_size, param.maxlen)) model.summary() # 写入数据 通过check_exist=True参数控制仅在第一次调用时写入 writer = TFWriter(param.maxlen, vocab_file, data_dir=FLAGS.data_dir, modes=["test"], check_exist=True) ner_load = TFLoader(param.maxlen, param.batch_size, data_dir=FLAGS.data_dir) # Metrics f1score = Metric.SparseF1Score("macro", predict_sparse=True) precsionscore = Metric.SparsePrecisionScore("macro", predict_sparse=True) recallscore = Metric.SparseRecallScore("macro", predict_sparse=True) accuarcyscore = Metric.SparseAccuracy(predict_sparse=True) # 保存模型 checkpoint = tf.train.Checkpoint(model=model) checkpoint.restore(tf.train.latest_checkpoint('./save')) # For test model # print(dir(checkpoint)) Batch = 0 f1s = [] precisions = [] recalls = [] accuracys = [] for X, token_type_id, input_mask, Y in ner_load.load_test(): predict = model.predict([X, token_type_id, input_mask, Y]) # [batch_size, max_length,label_size] f1s.append(f1score(Y, predict)) precisions.append(precsionscore(Y, predict)) recalls.append(recallscore(Y, predict)) accuracys.append(accuarcyscore(Y, predict)) print("Sentence", writer.convert_id_to_vocab(tf.reshape(X, [-1]).numpy())) print("Label", writer.convert_id_to_label(tf.reshape(predict, [-1]).numpy())) print("f1:{}\tprecision:{}\trecall:{}\taccuracy:{}\n".format( np.mean(f1s), np.mean(precisions), np.mean(recalls), np.mean(accuracys)))
model = BERT_NER(param) model.build(input_shape=(3, param.batch_size, param.maxlen)) model.summary() # 写入数据 通过check_exist=True参数控制仅在第一次调用时写入 writer = TFWriter(param.maxlen, vocab_file, modes=["valid"], check_exist=False) ner_load = TFLoader(param.maxlen, param.batch_size, epoch=3) # Metrics f1score = Metric.SparseF1Score(average="macro") precsionscore = Metric.SparsePrecisionScore(average="macro") recallscore = Metric.SparseRecallScore(average="macro") accuarcyscore = Metric.SparseAccuracy() # 保存模型 checkpoint = tf.train.Checkpoint(model=model) checkpoint.restore(tf.train.latest_checkpoint('./save')) # For test model Batch = 0 f1s = [] precisions = [] recalls = [] accuracys = [] for X, token_type_id, input_mask, Y in ner_load.load_valid(): predict = model.predict([X, token_type_id, input_mask]) # [batch_size, max_length,label_size] # predict = tf.argmax(output, -1)
model_path, param.num_hidden_layers, pooler=False) # 写入数据 通过check_exist=True参数控制仅在第一次调用时写入 writer = TFWriter(param.maxlen, vocab_file, modes=["train"], check_exist=False) ner_load = TFLoader(param.maxlen, param.batch_size, epoch=5) # 训练模型 # 使用tensorboard summary_writer = tf.summary.create_file_writer("./tensorboard") # Metrics f1score = Metric.SparseF1Score(average="macro", predict_sparse=True) precsionscore = Metric.SparsePrecisionScore(average="macro", predict_sparse=True) recallscore = Metric.SparseRecallScore(average="macro", predict_sparse=True) accuarcyscore = Metric.SparseAccuracy(predict_sparse=True) # 保存模型 checkpoint = tf.train.Checkpoint(model=model) manager = tf.train.CheckpointManager(checkpoint, directory="./save", checkpoint_name="model.ckpt", max_to_keep=3) # For train model Batch = 0 for X, token_type_id, input_mask, Y in ner_load.load_train(): with tf.GradientTape(persistent=True) as tape: loss, predict = model([X, token_type_id, input_mask, Y])
model = BERT_NER(param) model.build(input_shape=(param.batch_size, param.maxlen)) model.summary() # 写入数据 通过check_exist=True参数控制仅在第一次调用时写入 writer = TFWriter(param.maxlen, vocab_file, modes=["valid"], check_exist=True) ner_load = TFLoader(param.maxlen, param.batch_size) # Metrics f1score = Metric.SparseF1Score("macro") precsionscore = Metric.SparsePrecisionScore("macro") recallscore = Metric.SparseRecallScore("macro") accuarcyscore = Metric.SparseAccuracy() # 保存模型 checkpoint = tf.train.Checkpoint(model=model) checkpoint.restore(tf.train.latest_checkpoint('./save')) # For test model # print(dir(checkpoint)) Batch = 0 f1s = [] precisions = [] recalls = [] accuracys = [] for X, token_type_id, input_mask, Y in ner_load.load_valid(): predict = model.predict([X, token_type_id, input_mask
def main(_): model = BERT_NER(param) model.build(input_shape=(4, param.batch_size, param.maxlen)) model.summary() # 构建优化器 optimizer_bert = optim.AdamWarmup(learning_rate=2e-5, # 重要参数 decay_steps=10000, # 重要参数 warmup_steps=1000, ) optimizer_crf = optim.AdamWarmup(learning_rate=1e-3, decay_steps=10000, # 重要参数 warmup_steps=1000, ) # # 初始化参数 bert_init_weights_from_checkpoint(model, model_path, param.num_hidden_layers, pooler=False) # 写入数据 通过check_exist=True参数控制仅在第一次调用时写入 writer = TFWriter(param.maxlen, vocab_file, data_dir=FLAGS.data_dir, modes=["train"], check_exist=False) ner_load = TFLoader(param.maxlen, param.batch_size, data_dir=FLAGS.data_dir, epoch=5) # 训练模型 # 使用tensorboard summary_writer = tf.summary.create_file_writer("./tensorboard") # Metrics f1score = Metric.SparseF1Score(average="macro", predict_sparse=True) precsionscore = Metric.SparsePrecisionScore(average="macro", predict_sparse=True) recallscore = Metric.SparseRecallScore(average="macro", predict_sparse=True) accuarcyscore = Metric.SparseAccuracy(predict_sparse=True) # 保存模型 checkpoint = tf.train.Checkpoint(model=model) manager = tf.train.CheckpointManager(checkpoint, directory="./save", checkpoint_name="model.ckpt", max_to_keep=3) # For train model Batch = 0 for X, token_type_id, input_mask, Y in ner_load.load_train(): with tf.GradientTape(persistent=True) as tape: loss, predict = model([X, token_type_id, input_mask, Y]) f1 = f1score(Y, predict) precision = precsionscore(Y, predict) recall = recallscore(Y, predict) accuracy = accuarcyscore(Y, predict) if Batch % 101 == 0: print("Batch:{}\tloss:{:.4f}".format(Batch, loss.numpy())) print("Batch:{}\tacc:{:.4f}".format(Batch, accuracy)) print("Batch:{}\tprecision{:.4f}".format(Batch, precision)) print("Batch:{}\trecall:{:.4f}".format(Batch, recall)) print("Batch:{}\tf1score:{:.4f}".format(Batch, f1)) print("Sentence", writer.convert_id_to_vocab(tf.reshape(X, [-1]).numpy())) print("predict", writer.convert_id_to_label(tf.reshape(predict, [-1]).numpy())) print("label", writer.convert_id_to_label(tf.reshape(Y, [-1]).numpy())) manager.save(checkpoint_number=Batch) with summary_writer.as_default(): tf.summary.scalar("loss", loss, step=Batch) tf.summary.scalar("acc", accuracy, step=Batch) tf.summary.scalar("f1", f1, step=Batch) tf.summary.scalar("precision", precision, step=Batch) tf.summary.scalar("recall", recall, step=Batch) grads_bert = tape.gradient(loss, model.bert.variables + model.dense.variables) grads_crf = tape.gradient(loss, model.crf.variables) optimizer_bert.apply_gradients(grads_and_vars=zip(grads_bert, model.bert.variables + model.dense.variables)) optimizer_crf.apply_gradients(grads_and_vars=zip(grads_crf, model.crf.variables)) Batch += 1 model.save("model_save")