GitLab

Updated model_lib to use min_score_threshold and max_num_boxes_to_visualize from the eval config.

Text classification tutorial clarification

Rename "num_examples" to "num_reviews" to be consistent with the "one-hot-encode" size description: "num_words * num_reviews".

* Fix convergence issues for MLPerf.

Thank you to @robieta for helping me find these issues, and for providng an algorithm for the `get_hit_rate_and_ndcg_mlperf` function.

This change causes every forked process to set a new seed, so that forked processes do not generate the same set of random numbers. This improves evaluation hit rates.

Additionally, it adds a flag, --ml_perf, that makes further changes so that the evaluation hit rate can match the MLPerf reference implementation.

I ran 4 times with --ml_perf and 4 times without. Without --ml_perf, the highest hit rates achieved by each run were 0.6278, 0.6287, 0.6289, and 0.6241. With --ml_perf, the highest hit rates were 0.6353, 0.6356, 0.6367, and 0.6353.

* fix lint error

* Fix failing test

* Address @robieta's feedback

* Address more feedback

Basic_Regression notebook: Python2 compatibility

Docs: Grammar fix

* perform a codecs check and remove unicode \ufeff if utf-8 is not present

* delint

Docs: fix iteration count

Update the epoc/iteration count noted to match the code.

Update plt.grid args to avoid deprecation message

This is done by using a higher Pickle protocol version, which the Python docs describe as being "slightly more efficient". This reduces the file write time at the beginning from 2 1/2 minutes to 5 seconds.

Modify flag name for the checkpoint path

* Deterministic dataset order fix

In order for the order of the files to be deterministic, in `tf.data.Dataset.list_files(..., shuffle)`, shuffle needs to be True, otherwise different iterator inits will yield different file orders

* removed unnecessary shuffle of filenames

* Removed the `_FILE_SHUFFLE_BUFFER` definition

Adding illustrative charts to basic classification tutorial

Nits in basic_regression.ipynb

* Remove trailing spaces
* Fix "dependant" spelling error
* Remove periods at the end of comments*
* Add spaces after commas*

\* For internal consistency and consistency with PEP8 examples

Add a pointer to a Colab for the embeddings

Added a pointer to a Colab that illustrates how to use the public AudioSet models to generate embeddings for user-specified sounds.

* Fix Transformer TPU crash in Python 2.X.

- Tensorflow raises an error when tf_inspect.getfullargspec is called on
a functools.partial in Python 2.X. This issue would be hit during the
eval stage of the Transformer TPU model. This change replaces the call
to functools.partial with a lambda to work around the issue.

* Remove unused import from transformer_main.

* Fix lint error.

* warm start a resent with all but the dense layer and only update the final layer weights when fine tuning

* Update README for Transfer Learning

* make lint happy and variable naming error related to scaled gradients

* edit the test cases for cifar10 and imagenet to reflect the default case of no fine tuning

Add intra/inter op support for dcgan model

change flag name to checkpoint_dir according to the variable name
used by the checkpoint_utils within tensorflow python framework.

The important point is that when run the run_eval script, an error
occurs due to the different flag name.
Signed-off-by: MyungSung Kwak <yesmung@gmail.com>

Add plots to regression notebook.

Fixes for Style transfer tutorial.