Files
ray/ci/jenkins_tests/run_tune_tests.sh
T
d192ef0611 [raysgd] Cleanup User API (#7384)
* Init fp16

* fp16 and schedulers

* scheduler linking and fp16

* to fp16

* loss scaling and documentation

* more documentation

* add tests, refactor config

* moredocs

* more docs

* fix logo, add test mode, add fp16 flag

* fix tests

* fix scheduler

* fix apex

* improve safety

* fix tests

* fix tests

* remove pin memory default

* rm

* fix

* Update doc/examples/doc_code/raysgd_torch_signatures.py

* fix

* migrate changes from other PR

* ok thanks

* pass

* signatures

* lint'

* Update python/ray/experimental/sgd/pytorch/utils.py

* Apply suggestions from code review

Co-Authored-By: Edward Oakes <ed.nmi.oakes@gmail.com>

* should address most comments

* comments

* fix this ci

* first_pass

* add overrides

* override

* fixing up operators

* format

* sgd

* constants

* rm

* revert

* save

* failures

* fixes

* trainer

* run test

* operator

* code

* op

* ok done

* operator

* sgd test fixes

* ok

* trainer

* format

* Apply suggestions from code review

Co-Authored-By: Edward Oakes <ed.nmi.oakes@gmail.com>

* Update doc/source/raysgd/raysgd_pytorch.rst

* docstring

* dcgan

* doc

* commits

* nit

* testing

* revert

* Start renaming pytorch to torch

* Rename PyTorchTrainer to TorchTrainer

* Rename PyTorch runners to Torch runners

* Finish renaming API

* Rename to torch in tests

* Finish renaming docs + tests

* Run format + fix DeprecationWarning

* fix

* move tests up

* benchmarks

* rename

* remove some args

* better metrics output

* fix up the benchmark

* benchmark-yaml

* horovod-benchmark

* benchmarks

* Remove benchmark code for cleanups

* makedatacreator

* relax

* metrics

* autosetsampler

* profile

* movements

* OK

* smoothen

* fix

* nitdocs

* loss

* comments

* fix

* fix

* runner_tests

* codes

* example

* fix_test

* fix

* tests

Co-authored-by: Edward Oakes <ed.nmi.oakes@gmail.com>
Co-authored-by: Maksim Smolin <maximsmol@gmail.com>
2020-03-10 08:41:42 -07:00

198 lines
9.8 KiB
Bash
Executable File

#!/usr/bin/env bash
# Cause the script to exit if a single command fails.
set -e
# Show explicitly which commands are currently running.
set -x
MEMORY_SIZE=$1
SHM_SIZE=$2
DOCKER_SHA=$3
ROOT_DIR=$(cd "$(dirname "${BASH_SOURCE:-$0}")"; pwd)
SUPPRESS_OUTPUT=$ROOT_DIR/../suppress_output
if [ "$MEMORY_SIZE" == "" ]; then
MEMORY_SIZE="20G"
fi
if [ "$SHM_SIZE" == "" ]; then
SHM_SIZE="20G"
fi
if [ "$DOCKER_SHA" == "" ]; then
echo "Building application docker."
docker build -q --no-cache -t ray-project/base-deps docker/base-deps
# Add Ray source
git rev-parse HEAD > ./docker/tune_test/git-rev
git archive -o ./docker/tune_test/ray.tar $(git rev-parse HEAD)
DOCKER_SHA=$(docker build --no-cache -q -t ray-project/tune_test docker/tune_test)
fi
echo "Using Docker image" $DOCKER_SHA
######################## SGD TESTS #################################
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python -m pytest /ray/python/ray/util/sgd/tests
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/torch/examples/raysgd_torch_signatures.py
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/torch/examples/train_example.py
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/torch/examples/train_example.py --num-workers=2
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/torch/examples/tune_example.py
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/torch/examples/tune_example.py --num-workers=2
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/torch/examples/cifar_pytorch_example.py --smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/torch/examples/cifar_pytorch_example.py --smoke-test --num-workers=2
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/torch/examples/cifar_pytorch_example.py --smoke-test --tune
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/torch/examples/dcgan.py --smoke-test --num-workers=2
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/tf/examples/tensorflow_train_example.py
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/tf/examples/tensorflow_train_example.py --num-replicas=2
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/tf/examples/tensorflow_train_example.py --tune
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/tf/examples/cifar_tf_example.py --smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/tf/examples/cifar_tf_example.py --num-replicas 2 --smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/util/sgd/tf/examples/cifar_tf_example.py --num-replicas 2 --smoke-test --augment-data
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
pytest /ray/python/ray/tune/tests/test_cluster.py
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
pytest /ray/python/ray/tune/tests/test_actor_reuse.py
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
pytest /ray/python/ray/tune/tests/test_tune_restore.py
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/tests/example.py
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
bash -c 'pip install -U tensorflow && python /ray/python/ray/tune/tests/test_logger.py'
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
bash -c 'pip install -U tensorflow==1.15 && python /ray/python/ray/tune/tests/test_logger.py'
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
bash -c 'pip install -U tensorflow==1.14 && python /ray/python/ray/tune/tests/test_logger.py'
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
bash -c 'pip install -U tensorflow==1.12 && python /ray/python/ray/tune/tests/test_logger.py'
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 -e MPLBACKEND=Agg $DOCKER_SHA \
python /ray/python/ray/tune/tests/tutorial.py
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/pbt_example.py \
--smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/hyperband_example.py \
--smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/async_hyperband_example.py \
--smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/tf_mnist_example.py --smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/lightgbm_example.py
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/xgboost_example.py
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/logging_example.py \
--smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/mlflow_example.py
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/bayesopt_example.py \
--smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/hyperopt_example.py \
--smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 -e SIGOPT_KEY $DOCKER_SHA \
python /ray/python/ray/tune/examples/sigopt_example.py \
--smoke-test
# Runs only on Python3
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/nevergrad_example.py \
--smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/tune_mnist_keras.py \
--smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/mnist_pytorch.py --smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/mnist_pytorch_trainable.py \
--smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/genetic_example.py \
--smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/skopt_example.py \
--smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/dragonfly_example.py \
--smoke-test
# Commenting out because flaky
# $SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
# python /ray/python/ray/tune/examples/pbt_memnn_example.py \
# --smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/pbt_convnet_example.py \
--smoke-test
$SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
python /ray/python/ray/tune/examples/pbt_dcgan_mnist/pbt_dcgan_mnist.py \
--smoke-test
# uncomment once statsmodels is updated.
# $SUPPRESS_OUTPUT docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} --memory-swap=-1 $DOCKER_SHA \
# python /ray/python/ray/tune/examples/bohb_example.py \
# --smoke-test