How to use bert-as-service with BioBERT?

[alexferrari88]

Prerequisites

Please fill in by replacing [ ] with [x].

• [X ] Are you running the latest bert-as-service?
• [X ] Did you follow the installation and the usage instructions in README.md?
• [X ] Did you check the FAQ list in README.md?
• [X ] Did you perform a cursory search on existing issues?

System information

Some of this information can be collected via this script.

• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Windows 10
• TensorFlow installed from (source or binary): binary
• TensorFlow version: 1.13.1
• Python version: 3.7.3
• bert-as-service version: 1.8.9
• GPU model and memory: NVIDIA GeForce GTX 1050 -- 4GB
• CPU model and memory: Intel Core i7-7700HQ CPU @ 2.80GHz --16GB

---

Description

I downloaded from here https://github.com/naver/biobert-pretrained the BioBERT pre-trained weights, then I tried to load them in bert-as-service but I have problems.

I'm using this command to start the server:

bert-serving-start -model_dir=C:\ML\BERT\uncased_L-24_H-1024_A-16 -tuned_model_dir=C:\ML\BERT\BioBERT\pubmed_pmc_470k -ckpt_name=biobert_model.ckpt -max_seq_len=NONE

Then this issue shows up:

Traceback (most recent call last): File "c:\program files\python37\lib\runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "c:\program files\python37\lib\runpy.py", line 85, in _run_code exec(code, run_globals) File "C:\Program Files\Python37\Scripts\bert-serving-start.exe__main.py", line 9, in File "c:\program files\python37\lib\site-packages\bert_serving\server\cli__init__.py", line 4, in main with BertServer(get_run_args()) as server: File "c:\program files\python37\lib\site-packages\bert_serving\server\init.py", line 70, in init__ self.graph_path, self.bert_config = pool.apply(optimize_graph, (self.args,)) TypeError: cannot unpack non-iterable NoneType object

[mztkenan]

the same problem： File "c:\programdata\anaconda3\lib\site-packages\bert_serving\server__init.py", line 70, in init__ self.graph_path, self.bert_config = pool.apply(optimize_graph, (self.args,)) TypeError: cannot unpack non-iterable NoneType object。

possible reason：the model file has been damaged the solution is：downlaod the model from the readme, change the model file

[MarvinMogab]

@alexferrari88 same problem.. did you find any solution ?

[kaustv-datta]

Facing same issue as @alexferrari88

[lagatorc]

I specified the -model_dir as the directory that contained the bioBert files and also renamed them made sure the model name and config.json matched the -ckpt_name and -config_name flags. The default of -ckpt_name is 'bert_model.ckpt" and the default of config_name is "bert_config.json"

[bevankoopman]

I specified the -model_dir as the directory that contained the bioBert files and also renamed them made sure the model name and config.json matched the -ckpt_name and -config_name flags. The default of -ckpt_name is 'bert_model.ckpt" and the default of config_name is "bert_config.json"

And did that get it working for you?

[lagatorc]

@bevankoopman Yes it did. I recommend using the HuggingFace transformers library to use Bert. It is more up to date with the current releases.