Niraj Singh

@modbender, You can save your model using `tf.keras.models.save_model` function to generate saved_model.pb and keras_metadata.pb files. You can refer to [guide](https://www.tensorflow.org/tfx/tutorials/serving/rest_simple) for detailed explanation with example to serve your model with...

@modbender, A [PR](https://github.com/tensorflow/tfx/pull/5247) has been created to fix this. Meanwhile please refer to [signature_defs documentation](https://www.tensorflow.org/tfx/serving/signature_defs) here. Thank you!

@modbender, Please refer [here](https://colab.research.google.com/github/pair-code/what-if-tool/blob/master/What_If_Tool_Notebook_Usage.ipynb) for complete code to setup what-if tool on UCI Census data. For more info, please refer to [what-if-tool](https://github.com/PAIR-code/what-if-tool) github repo. Thank you!

@Joeyzhouqihui, Kindly take a look into [batching guide](https://github.com/tensorflow/serving/blob/master/tensorflow_serving/batching/README.md) for TF serving. You can also refer to our official [documentation ](https://www.tensorflow.org/tfx/guide/serving)for more details.

Closing this due to inactivity. Please take a look into the answers provided above, feel free to reopen and post your comments(if you still have queries on this). Thank you!

@caveness, Kindly review this PR and approve it. Older version of joblib is blocking users because of security vulnerability. #226 Thank you!

Hi @rclough, Please go through these links [1](https://www.tensorflow.org/tfx/data_validation/get_started#checking_data_skew_and_drift) and [2](https://www.tensorflow.org/tfx/tutorials/data_validation/tfdv_basic#check_for_drift_and_skew) for thresholding the difference in numeric distribution using `jensen_shannon_divergence` and `L-infinity distance`. Let us know if this helps. Thank you!

@caveness, Thank you for the clarification. @rclough, I will make this a feature request as commented by @caveness. Thank you for reporting this issue.

@swaticolab, Could you please share the minimal code to reproduce the error you are getting. In meantime, please go through [tfdv.visualize_statistics](https://www.tensorflow.org/tfx/data_validation/api_docs/python/tfdv/visualize_statistics) which visualizes the input statistics using Facets. Also please...

@mukeshmithrakumar, In the [official website](https://www.tensorflow.org/tfx/data_validation/install), it is recommended to install data validation using PyPI, or build from docker (if using Linux) or build from source. You can also refer to...