GitLab

This reverts commit 649e0374.

with serving signature that accepts JPEG image bytes instead
of a fixed size [HxWxC] image tensor.

Passing JPEG image bytes is easier for inference/serving use
cases. The model internally resizes/crops the JPEG image to
required [HxWxC] tensor before passing it on for actual model
inference.

This change aligns with Cloud TPU/ResNet-50 model that offers a
similar interface (jpeg bytes) for inferencing here:

https://github.com/tensorflow/tpu/tree/master/models/official/resnet

NOTE: This flag is set to `True` by default for ImageNet, and is
disallowed for CIFAR (as it does not apply to CIFAR).

* 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 .take() to dataset pipeline

* delint

* address PR comments

* Update benchmark logger to update the run status.

This is important for streaming upload to bigquery so that the
dashboard can ignore the 'running' benchmark at the moment since
its not finished yet.

* Move the run status into a separate table.

Also update the run status in the benchmark uploader and
BigqueryBenchmarkLogger.

* Insert instead of update for the benchmark status for file logger.

* Address review comments.

Update the logger to have benchmark context, which will update the
run status accordingly.

* Fix broken tests.

* Move the benchmark logger context to main function.

* Fix tests.

* Update the rest of the models to use the context in main.

* Delint.

* Remove one hot labels, Add drop_remainder to batch, Use parallel interleve in imagenet dataset.

* minor lint fix

* Don't try to read the files twice...

* Add explanation for cycle_length

* rename --version flag and fix tests to correctly specify version rather than verbosity

* rename version to resnet_version throughout

* fix bugs

* delint

* missed layer_test

* fix indent

* Add dataset info and hyper parameter logging for benchmark.

* Address review comments.

* Address the view comment for data schema name.

* Fix test cases.

* Lint fix.

* Revert 823da318. This restores distribution strategies for resnet.

This commit is not a direct revert due to significant merge conflict
resolution.

* fix flags test

* npc is no longer used in resnet

* fix treatment of main() and absl flags

* add mnist_eager, and delint

* add mnist_eager docstring

* squash of modular absl usage commits

* delint

* address PR comments

* change hooks to comma separated list, as absl behavior for space separated lists is not as expected

This reverts commit 32aa6563.

* begin transfer from contrib fork

more changes to resnet_run_loop

use AUTOTUNE in prefetch

first pass at resnet with functional distribution strategies

fix syntax error

delint

aesthetic tweaks

delint and fix typos

rip multi_gpu flag out of resnet entirely. Subject to saved model load verification

update cifar10 and imagenet tests to reflect that the model function no longer need to know about multi_gpu

fix imagenet test

start addressing PR comments

more PR response work

* misc tweaks

* add a comment

* final pr tweaks

* fix parsers

* Add fp16 support to resnet.

* address PR comments

* add dtype checking to model definition

* delint

* more PR comments

* few more tweaks

* update resnet checkpoints

* Adding export_dir and model saving for Resnet

* Moving to utils for tests

* Adding batch_size

* Adding multi-gpu export warning

* Responding to CR

* Py3 compliance

Set correct number of train_epochs for resnet on imagenet, and fix help interception caused by moving arg parsing into main functions for resnet. (#3653)

* Glint everything

* Adding rcfile and pylinting

* Extra newline

* Few last lints

Use util functions hooks_helper and parser in mnist and wide_deep, and rename epochs_between_eval (from epochs_per_eval) (#3650)

This commit adds a basic end to end test for resnet cifar10 and imagenet models to check for syntax errors outside of the core neural net code. 

* Adding logging utils

* restore utils

* delete old file

* update inputs and docstrings

* make /official a python module

* remove /utils directory

* Update readme for python path setting

* Change readme texts

* Adding option to run with synthetic data.

* Adding option to run with synthetic data.

Adding option to run with synthetic data.

Adding option to run with synthetic data.

Debugging

Debugging

Debugging

Removing dataset

Removing dataset

Updating comments

Updating tests

Updating tests

Clarifying name of fn

Tests

* Copy pasta

* Using dataset as recommended by mrry

* Updating tests to use datasets

* Refactor and use class-based model for Resnet

* Linting

* Cleanup

* Cleanup in lieu of MNIST changes

* Moving params to init function

* Making learning_rate function

* Testing remotely...

* Testing remotely...

* Testing remotely...

* Testing remotely...

* Testing remotely...

* Respond to CR pt 1

* Respond to CR pt 2

* Respond to CR pt 3

* Respond to CR pt 4

* Adding batch norm vars in

* Exclude batch norm vars as the default

* Fixing CIFAR-10 naming

* Adding multi-GPU code

* Git rewind

* Git add file

* Manual revert

* Fixing tests

* Allowing input thread specification

* Adding comments

* Allowing input thread specification

* Merging resnet files

* Merging resnet files

* Refactoring input methods to allow for Reed's improvements

* Adding comments

* Changing arg name

* Removing contrib shuffle_and_repeat

* Removing contrib shuffle_and_repeat

* Removing contrib shuffle_and_repeat

* Debugging

* Removing with dependency on update_op

* Updating comments.

* Returning dataset directly

* Adding newline

* Adding num_gpus flag

* Refining preprocessing, part 1

* Refinements to preprocessing resulting from multi-GPU tests

* Reviving one-hot labels

* Reviving one-hot labels

* Fixing label shapes

* Removing epoch leftovers

* Adding random flip back in

* Reverting unnecessary linting of test file

* Respond to CR

* Respond to CR

* Respond to CR

* Remove conversion to float

* Remove conversion to float- comment

* Making means full-scale

* Pulling data.take under multi_gpu flag

* Pulling data.take under multi_gpu flag- Cifar

* Pulling data.take under multi_gpu flag- Cifar

* Removing num_gpus

* Removing num_gpus

* Refactoring input function

* Updating name of variable