Embedding visualization with TensorFlow eager execution

Question

I am using TensorFlow's eager execution and I would like to visualize embeddings in TensorBoard. I use the following code to setup the visualization:

self._writer = tf.contrib.summary.create_file_writer('path')
embedding_config = projector.ProjectorConfig()
embedding = embedding_config.embeddings.add()
embedding.tensor_name = self._word_embeddings.name
embedding.metadata_path = 'metadata.tsv'
projector.visualize_embeddings(self._writer, embedding_config)

where self._word_embeddings is my variable for the embeddings. However, when executing this script TensorFlow throws the following error message:

logdir = summary_writer.get_logdir()
AttributeError: 'SummaryWriter' object has no attribute 'get_logdir'

Has anybody experienced something similar and has an idea how to get the embedding visualization to run in eager mode?

I am using TensorFlow 1.10.0.

Any kind of help is greatly appreciated!

My answer below assumes that you only care about visualizing the embeddings. — MAltakrori
Another comment: This doesn't work because here the embeddings are not saved. In Graph mode, the embeddings are saved as part of the graph (in the checkpoint). In the above code, you provide the variable name for the embeddings, and the metadata. The name is useless without a graph that has variables. — MAltakrori

MAltakrori MAltakrori · Accepted Answer · 2018-10-04T21:29:27

If you only care about visualization, and since you are working in eager mode, things can be much simpler.

As I can see, you already have your metadata.TSV file set. The only thing left, is to write your embedding matrix to a TSV file. Like, just a for loop over the matrix rows, with the values TAB separated.

Last step, you can load the tensorboard projector online, without installing it via: http://projector.tensorflow.org/ and upload your data. You have to upload the embedding file, and the metadata file separately, in two simple steps.

Embedding visualization with TensorFlow eager execution

1 Answers