这是我第一次使用 Tensorflow 和 Bert-as-service。使用 VS 代码作为编辑器,我无法启动 Bert-as-service 服务器端。同时,位于 Jupyter Notebook 上的 Bert-as-service 客户端也失败了,如下图所示。
我只想启动 BERT 服务并使用客户端获取句子编码,如此处的示例。请帮我。
环境:Windows 7 RAM 4G/Anaconda 2019.07/Python 3.7.3/tensorflow 1.14/Bert-as-Service CPU 版本
(base) C:\Users\lee>bert-serving-start -model_dir E:/MyDownloads/uncased_L-12_H-768_A-12 -cpu -http_port 80 -max_seq_len 20
usage: D:\MyPrograms\Anaconda\Scripts\bert-serving-start -model_dir E:/MyDownloads/uncased_L-12_H-768_A-12 -cpu -http_port 80 -max_seq_len 20
ARG VALUE
__________________________________________________
ckpt_name = bert_model.ckpt
config_name = bert_config.json
cors = *
cpu = True
device_map = []
do_lower_case = True
fixed_embed_length = False
fp16 = False
gpu_memory_fraction = 0.5
graph_tmp_dir = None
http_max_connect = 10
http_port = 80
mask_cls_sep = False
max_batch_size = 256
max_seq_len = 20
model_dir = E:/MyDownloads/uncased_L-12_H-768_A-12
num_worker = 1
pooling_layer = [-2]
pooling_strategy = REDUCE_MEAN
port = 5555
port_out = 5556
prefetch_size = 10
priority_batch_size = 16
show_tokens_to_client = False
tuned_model_dir = None
verbose = False
xla = False
I:?[35mVENTILATOR?[0m:freeze, optimize and export graph, could take a while...
WARNING:tensorflow:From d:\myprograms\anaconda\lib\site-packages\bert_serving\server\helper.py:180: The name tf.logging.set_verbosity is deprecated. Please use tf.compat.v1.logging.set_verbosity instead.
WARNING:tensorflow:From d:\myprograms\anaconda\lib\site-packages\bert_serving\server\helper.py:180: The name tf.logging.ERROR is deprecated. Please use tf.compat.v1.logging.ERROR instead.
I:?[36mGRAPHOPT?[0m:model config: E:/MyDownloads/uncased_L-12_H-768_A-12\bert_config.json
I:?[36mGRAPHOPT?[0m:checkpoint: E:/MyDownloads/uncased_L-12_H-768_A-12\bert_model.ckpt
(Then it stopped here and nothing happened that seemed to clash.)