AnandInguva commented on code in PR #26494: URL: https://github.com/apache/beam/pull/26494#discussion_r1188616653
########## sdks/python/apache_beam/examples/inference/README.md: ########## @@ -536,9 +536,9 @@ The pipeline reads rows of pixels corresponding to a digit, performs basic prepr The model is loaded from the saved model weights. This can be done by passing a function which creates the model and setting the model type as `ModelType.SAVED_WEIGHTS` to the `TFModelHandler`. The path to saved weights saved using `model.save_weights(path)` should be passed to the `model_path` argument. -### Dataset and model for language modeling +### Dataset and model for digit classification -To use this transform, you need a dataset and model for language modeling. +To use this transform, you need a dataset and model for digit classification. Review Comment: ```suggestion To use this transform, you need a dataset and model for MNIST digit classification. ``` -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
