tensorflow集线器无法加载BERT模型

Question

bert_layer = hub.KerasLayer("https://tfhub.dev/tensorflow/bert_en_uncased_L-12_H-768_A-12/1",trainable=False)
vocab_file = bert_layer.resolved_object.vocab_file.asset_path.numpy()
do_lower_case = bert_layer.resolved_object.do_lower_case.numpy()
tokenizer = FullTokenizer(vocab_file, do_lower_case)

然后，它不工作并报告错误：超时：

INFO:absl:Downloading TF-Hub Module 'https://tfhub.dev/tensorflow/bert_en_uncased_L-12_H-768_A-12/1'.
---------------------------------------------------------------------------
TimeoutError                              Traceback (most recent call last)
/usr/local/app/.pyenv/versions/3.6.8/lib/python3.6/urllib/request.py in do_open(self, http_class, req, **http_conn_args)
1317                 h.request(req.get_method(), req.selector, req.data, headers,
-> 1318                           encode_chunked=req.has_header('Transfer-encoding'))
1319             except OSError as err: # timeout error
TimeoutError: [Errno 110] Connection timed out
During handling of the above exception, another exception occurred:
/usr/local/app/.pyenv/versions/3.6.8/lib/python3.6/urllib/request.py in do_open(self, http_class, req, **http_conn_args)
1318                           encode_chunked=req.has_header('Transfer-encoding'))
1319             except OSError as err: # timeout error
-> 1320                 raise URLError(err)
1321             r = h.getresponse()
1322         except:
URLError: <urlopen error [Errno 110] Connection timed out>

我不知道为什么会这样，有人能帮我吗？

Answer 1

您可以尝试在中国使用镜像备份进行访问，特别是，假设您在访问时遇到问题

model = hub.load('https://tfhub.dev/google/yamnet/1')

你切换到镜像在中国，与以下：

model = hub.load('https://hub.tensorflow.google.cn/google/yamnet/1')