提交 4e9d1948 编写于 作者: C Chen Chen 提交者: A. Unique TensorFlower

Fix the hub_module_name URL in fine_tuning_bert.ipynb

PiperOrigin-RevId: 338740954
上级 82c09890
......@@ -64,6 +64,9 @@
" \u003ctd\u003e\n",
" \u003ca href=\"https://storage.googleapis.com/tensorflow_docs/models/official/colab/fine_tuning_bert.ipynb\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/download_logo_32px.png\" /\u003eDownload notebook\u003c/a\u003e\n",
" \u003c/td\u003e\n",
" \u003ctd\u003e\n",
" \u003ca href=\"https://tfhub.dev/tensorflow/bert_en_uncased_L-12_H-768_A-12/2\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/hub_logo_32px.png\" /\u003eSee TF Hub model\u003c/a\u003e\n",
" \u003c/td\u003e\n",
"\u003c/table\u003e"
]
},
......@@ -1442,7 +1445,7 @@
},
"outputs": [],
"source": [
"hub_encoder = hub.KerasLayer(f\"https://tfhub.dev/tensorflow/{hub_model_name}\",\n",
"hub_encoder = hub.KerasLayer(f\"https://tfhub.dev/tensorflow/{hub_model_name}/2\",\n",
" trainable=True)\n",
"\n",
"print(f\"The Hub encoder has {len(hub_encoder.trainable_variables)} trainable variables\")"
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册