GitLab

* PiperOrigin-RevId: 201234832

* PiperOrigin-RevId: 202507333

* PiperOrigin-RevId: 204320344

* Add PNASNet-5 mobile network model and cell structure.

PiperOrigin-RevId: 204735410

* Add option to customize individual projection layer activation.

PiperOrigin-RevId: 204776951

The following error doesn't occur with the above change in code.

Error: Argument must be a dense tensor: range(0, 3) - got shape [3], but wanted []

The range function on the vairable 'num_boundaries' should be a list! Please merge this request!

* Sentiment analysis implmenttion in pure Keras.

- This is an update for the sentiment analysis model's pure Keras version.
-- Converting it from the version using Tensorflow's estimator, as it has a issue that affects the accuracy of the model negatively.
- The implementation is with the reference to paddle version.
-- Adjustment of the hyperparameters was done to achieve the accuracy of ~90%

* addressing comments

* addressig comments

also adding

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

for each module as it seemingly is a standard in the repo.

* addressing the final comment.

Correcting comments

processes all crystal growth images in directory and  sub directories and prints results to console, and a comma seperated file. Removes dependencies of google SDK(only dependent on tensorflow and python 2.7)

204489224  by Zhichao Lu:

    Modify ssd mobilenet v1 fpn config to be a bit more tolerant to OOM failure by bumping down the batch size to 64 and doubling the number of iterations to 25k. It now converges in 2.5 hours.

--
204488942  by Zhichao Lu:

    Internal change

204480631  by Zhichao Lu:

    This CL makes sure that num_steps parameter are not updated to 0 if num_steps field is not mentioned in config.

    The default behavior for number of steps parameter for training is infinite (train forever). The default value num_steps in train.proto is 0 (for training indefinitely). However the estimator/training function expects the num_steps to be set to None to train indefinitely.

--
204437217  by Zhichao Lu:

    Create a Docker image to support TensorFlow Lite / Object Detection blog post.

--
204317570  by Zhichao Lu:

    Internal change

PiperOrigin-RevId: 204489224

github-release, in case the distribution version is not working (or the user
is not on an ubuntu system)