def one_autofinetune(args, schema_labels, predict_data, predict_sents, id):
seq_label_task, reader = get_task(args, schema_labels, id)
# 加载PaddleHub 预训练模型ERNIE Tiny/RoBERTa large
# 更多预训练模型 https://www.paddlepaddle.org.cn/hublist?filter=en_category&value=SemanticModel
# model_name = "ernie_tiny"
# PaddleHub Finetune API
# 将自动训练、评测并保存模型
if args.do_train:
print("start finetune and eval process")
seq_label_task.finetune_and_eval()
write_log('./work/log/' + args.do_model + '.txt', args,
str(seq_label_task.best_score))
if args.do_predict:
print("start predict process")
ret = []
id2label = {val: key for key, val in reader.label_map.items()}
input_data = [[d] for d in predict_data]
run_states = seq_label_task.predict(data=input_data[1:])
results = []
for batch_states in run_states:
batch_results = batch_states.run_results
batch_infers = batch_results[0].reshape([-1]).astype(
np.int32).tolist()
seq_lens = batch_results[1].reshape([-1]).astype(np.int32).tolist()
current_id = 0
for length in seq_lens:
seq_infers = batch_infers[current_id:current_id + length]
seq_result = list(map(id2label.get, seq_infers[1:-1]))
current_id += length if args.add_crf else args.max_seq_len
results.append(seq_result)
ret = []
for sent, r_label in zip(predict_sents, results):
sent["labels"] = r_label
ret.append(json.dumps(sent, ensure_ascii=False))
write_by_lines(
"{}.{}.{}.pred".format(args.predict_data, args.do_model, id), ret)
# Load model from the defined model path or not
#
# seq_label_task.finetune_and_eval()
# run_states = seq_label_task.eval()
# eval_avg_score, eval_avg_loss, eval_run_speed =seq_label_task._calculate_metrics(
# run_states)
# Move ckpt/best_model to the defined saved parameters directory
best_model_dir = os.path.join(args.checkpoint_dir, "best_model")
if is_path_valid(args.saved_params_dir) and os.path.exists(best_model_dir):
shutil.copytree(best_model_dir, args.saved_params_dir)
shutil.rmtree(args.checkpoint_dir)
write_log('./work/log/' + args.do_model + '.txt', args,
id + ',' + str(seq_label_task.best_score))
print(seq_label_task.best_score)
hub.report_final_result(seq_label_task.best_score)
def one(args, schema_labels, id):
seq_label_task, reader = get_task(args, schema_labels, id)
# 加载PaddleHub 预训练模型ERNIE Tiny/RoBERTa large
# 更多预训练模型 https://www.paddlepaddle.org.cn/hublist?filter=en_category&value=SemanticModel
# model_name = "ernie_tiny"
# PaddleHub Finetune API
# 将自动训练、评测并保存模型
if args.do_train:
print("start finetune and eval process")
seq_label_task.finetune_and_eval()
write_log('./work/log/' + args.do_model + '.txt', args, id + ',' + str(seq_label_task.best_score))
def one(args, schema_labels, predict_data, predict_sents, id):
seq_label_task, reader = get_task(args, schema_labels, id)
# 加载PaddleHub 预训练模型ERNIE Tiny/RoBERTa large
# 更多预训练模型 https://www.paddlepaddle.org.cn/hublist?filter=en_category&value=SemanticModel
# model_name = "ernie_tiny"
# PaddleHub Finetune API
# 将自动训练、评测并保存模型
if args.do_train:
print("start finetune and eval process")
seq_label_task.finetune_and_eval()
write_log('./work/log/' + args.do_model + '.txt', args,
id + ',' + str(seq_label_task.best_score))
if args.do_predict:
print("start predict process")
ret = []
id2label = {val: key for key, val in reader.label_map.items()}
input_data = [[d] for d in predict_data]
# print(input_data[:10])
run_states = seq_label_task.predict(data=input_data)
results = []
for batch_states in run_states:
batch_results = batch_states.run_results
# print('batch_infers',batch_results )
batch_infers = batch_results[0].reshape([-1]).astype(
np.int32).tolist()
seq_lens = batch_results[1].reshape([-1]).astype(np.int32).tolist()
current_id = 0
for length in seq_lens:
seq_infers = batch_infers[current_id:current_id + length]
seq_result = list(map(id2label.get, seq_infers[1:-1]))
current_id += length if args.add_crf else args.max_seq_len
results.append(seq_result)
ret = []
for sent, input, r_label in zip(predict_sents, input_data, results):
sent["input"] = input
sent["labels"] = r_label
ret.append(json.dumps(sent, ensure_ascii=False))
write_by_lines(
"{}.{}.{}.pred".format(output_predict_data_path, args.do_model,
id), ret)
get_submit_postprocess(args, id)
get_submit_postprocess(args, id, check=True)
def one(args, schema_labels, predict_data, predict_sents, id):
seq_label_task, reader = get_task(args, schema_labels, id)
# 加载PaddleHub 预训练模型ERNIE Tiny/RoBERTa large
# 更多预训练模型 https://www.paddlepaddle.org.cn/hublist?filter=en_category&value=SemanticModel
# model_name = "ernie_tiny"
# PaddleHub Finetune API
# 将自动训练、评测并保存模型
if args.do_train:
print("start finetune and eval process")
seq_label_task.finetune_and_eval()
write_log('./work/log/' + args.do_model + '.txt', args,
id + ',' + str(seq_label_task.best_score))
if args.do_model == 'role' and args.do_predict:
print("start predict process")
ret = []
id2label = {val: key for key, val in reader.label_map.items()}
input_data = [[d] for d in predict_data]
# print(input_data[:10])
run_states = seq_label_task.predict(data=input_data)
results = []
for batch_states in run_states:
batch_results = batch_states.run_results
batch_infers = batch_results[0].reshape([-1]).astype(
np.int32).tolist()
# print(batch_results)
seq_lens = batch_results[1].reshape([-1]).astype(np.int32).tolist()
current_id = 0
for length in seq_lens:
seq_infers = batch_infers[current_id:current_id + length]
seq_result = list(map(id2label.get, seq_infers[1:-1]))
current_id += length if args.add_crf else args.max_seq_len
results.append(seq_result)
ret = []
for sent, input, r_label in zip(predict_sents, input_data, results):
sent["input"] = input
sent["labels"] = r_label
ret.append(json.dumps(sent, ensure_ascii=False))
write_by_lines(
"{}.{}.{}.pred".format(output_predict_data_path, args.do_model,
id), ret)
get_submit_postprocess(args, id)
get_submit_postprocess(args, id, check=True)
if args.do_model in ['mcls', "mcls_onlysentence"] and args.do_predict:
input_data = predict_data
result = seq_label_task.predict(data=input_data, return_result=True)
ret = []
submit = []
for s, r in zip(predict_sents, result):
s['labels'] = []
# print(r)
for r0 in r:
# print(r0)
for k, v in r0.items():
# print(k,v)
if (v == 1):
s['labels'].append(k)
if (args.do_model == 'mcls_onlysentence'):
submit.append('\t'.join([str(s["id"]), k]))
else:
submit.append('\t'.join(
[str(s["id"]), k, s["entity"]]))
ret.append(json.dumps(s, ensure_ascii=False))
write_by_lines(
"{}.{}.{}.40-55.pred".format(output_predict_data_path,
args.do_model, id), ret)
write_by_lines(
"{}{}.{}.40-55.ucas_valid_result.csv".format(
output_path, args.do_model, id), submit)