Train your own medical Q&A retrieval model

[KingsonSingh]

When I am trying to execute Train_Your_Own_Q_A_ModelsV0.2.0.ipynb file locally on my machine, I get the below error-

File "Train_Your_Own_Q_A_ModelsV0.2.0.ipynb", line 47, in medical_qa_model = MedicalQAModelwithBert(config_file=os.path.join(pretrained_path, 'bert_config.json'),checkpoint_file=os.path.join(pretrained_path, 'biobert_model.ckpt')) File "/docproduct/models.py", line 79, in init build=build) File "/docproduct/bert.py", line 214, in build_model_from_config model.build(input_shape=[(None, None), (None, None), (None, None)]) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/network.py", line 720, in build raise ValueError('You cannot build your model by calling build ' ValueError: You cannot build your model by calling build if your layers do not support float type inputs. Instead, in order to instantiate and build your model, call your model on real tensor data (of the correct dtype).

Please help me out!! Thanks !

[Santosh-Gupta]

It's hard to tell what the issue is without knowing your local machine, but common errors are trying to run it in tensorflow 1.0, or if the machine is windows.

[KingsonSingh]

I have ubuntu 18.04 machine. python 3.6.8

packages are installed in python

absl-py==0.7.1 astor==0.8.0 bert-serving-client==1.9.6 bert-serving-server==1.9.6 bleach==1.5.0 certifi==2019.6.16 chardet==3.0.4 cloudpickle==1.2.1 cycler==0.10.0 decorator==4.4.0 docproduct==0.2.0 faiss==1.5.3 faiss-cpu==1.5.3 gast==0.2.2 google-pasta==0.1.7 GPUtil==1.4.0 grpcio==1.22.0 h5py==2.9.0 html5lib==0.9999999 idna==2.8 intel-openmp==2019.0 joblib==0.13.2 Keras==2.2.4 Keras-Applications==1.0.8 keras-embed-sim==0.3.0 keras-layer-normalization==0.11.0 keras-multi-head==0.18.0 keras-pos-embd==0.9.0 keras-position-wise-feed-forward==0.4.0 Keras-Preprocessing==1.1.0 keras-self-attention==0.39.0 keras-transformer==0.21.0 kiwisolver==1.1.0 Markdown==3.1.1 matplotlib==3.1.1 mkl==2019.0 numpy==1.17.0 opencv-python==4.0.1.23 pandas==0.25.0 pkg-resources==0.0.0 protobuf==3.9.0 pyarrow==0.14.1 pycrypto==2.6.1 pycurl==7.43.0.3 pyparsing==2.4.2 python-dateutil==2.8.0 pytz==2019.2 PyYAML==5.1.2 pyzmq==18.0.2 requests==2.22.0 scikit-learn==0.21.3 scipy==1.3.0 six==1.12.0 sklearn==0.0 tb-nightly==1.14.0a20190301 tensorboard==1.14.0 tensorflow-estimator==1.14.0 tensorflow-gpu==2.0.0a0 tensorflow-probability==0.7.0 termcolor==1.1.0 tf-estimator-nightly==1.14.0.dev2019030115 tqdm==4.32.2 urllib3==1.25.3 Werkzeug==0.15.5 wrapt==1.11.2

thanks!

[Santosh-Gupta]

wait, are you trying to execute the .ipnb file? It's a notebook file, you need to convert it

[KingsonSingh]

Yes, I have converted .ipnb file into .py file.