Skip to content

Load dataset from s3 #299

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 12 commits into from
Jul 30, 2020
Merged

Load dataset from s3 #299

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
9f4ce1e
load from s3 path
NihalHarish Jul 30, 2020
80b27aa
load from s3 path
NihalHarish Jul 30, 2020
09b914c
constants file
NihalHarish Jul 30, 2020
acf4990
import
NihalHarish Jul 30, 2020
4049e86
retrigger CI
NihalHarish Jul 30, 2020
7d8130e
rename variable
NihalHarish Jul 30, 2020
fba5837
check if s3 is accessible
NihalHarish Jul 30, 2020
8e613bf
merge master
NihalHarish Jul 30, 2020
6ee1a7d
Merge branch 'load_dataset_from_s3' of https://github.com/awslabs/sag…
NihalHarish Jul 30, 2020
5407187
Merge branch 'master' into load_dataset_from_s3
NihalHarish Jul 30, 2020
3501448
pythonic
NihalHarish Jul 30, 2020
2816c41
sanitize s3 path
NihalHarish Jul 30, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion tests/tensorflow/test_keras_to_estimator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
import tensorflow as tf
import tensorflow_datasets as tfds
from tests.constants import TEST_DATASET_S3_PATH
from tests.utils import use_s3_datasets

# First Party
from smdebug.tensorflow import EstimatorHook, modes
Expand All @@ -18,7 +19,8 @@ def test_keras_to_estimator(out_dir):

def input_fn():
split = tfds.Split.TRAIN
dataset = tfds.load("iris", data_dir=TEST_DATASET_S3_PATH, split=split, as_supervised=True)
data_dir = TEST_DATASET_S3_PATH if use_s3_datasets() else None
dataset = tfds.load("iris", data_dir=data_dir, split=split, as_supervised=True)
dataset = dataset.map(lambda features, labels: ({"dense_input": features}, labels))
dataset = dataset.batch(32).repeat()
return dataset
Expand Down
4 changes: 3 additions & 1 deletion tests/tensorflow2/test_keras.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@
from tests.constants import TEST_DATASET_S3_PATH
from tests.tensorflow2.utils import is_tf_2_2
from tests.tensorflow.utils import create_trial_fast_refresh
from tests.utils import use_s3_datasets

# First Party
import smdebug.tensorflow as smd
Expand Down Expand Up @@ -750,7 +751,8 @@ def test_keras_to_estimator(out_dir, tf_eager_mode):

def input_fn():
split = tfds.Split.TRAIN
dataset = tfds.load("iris", data_dir=TEST_DATASET_S3_PATH, split=split, as_supervised=True)
data_dir = TEST_DATASET_S3_PATH if use_s3_datasets() else None
dataset = tfds.load("iris", data_dir=data_dir, split=split, as_supervised=True)
dataset = dataset.map(lambda features, labels: ({"dense_input": features}, labels))
dataset = dataset.batch(32).repeat()
return dataset
Expand Down
16 changes: 15 additions & 1 deletion tests/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,14 +3,28 @@
import shutil
from pathlib import Path

# Third Party
import boto3
from tests.constants import TEST_DATASET_S3_PATH

# First Party
from smdebug.core.config_constants import (
CONFIG_FILE_PATH_ENV_STR,
DEFAULT_SAGEMAKER_OUTDIR,
DEFAULT_SAGEMAKER_TENSORBOARD_PATH,
TENSORBOARD_CONFIG_FILE_PATH_ENV_STR,
)
from smdebug.core.utils import remove_file_if_exists
from smdebug.core.utils import is_s3, remove_file_if_exists


def use_s3_datasets():
s3 = boto3.resource("s3")
_, bucket, _ = is_s3(TEST_DATASET_S3_PATH)
try:
s3.meta.client.head_bucket(Bucket=bucket)
return True
except Exception:
return False


class SagemakerSimulator(object):
Expand Down
6 changes: 3 additions & 3 deletions tests/zero_code_change/test_tensorflow_integration.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@
from tests.constants import TEST_DATASET_S3_PATH
from tests.tensorflow.hooks.test_mirrored_strategy import test_basic
from tests.tensorflow.keras.test_keras_mirrored import test_tf_keras
from tests.utils import use_s3_datasets
from tests.zero_code_change.tf_utils import (
get_data,
get_estimator,
Expand Down Expand Up @@ -422,9 +423,8 @@ def test_keras_to_estimator(script_mode):

def input_fn():
split = tfds.Split.TRAIN
dataset = tfds.load(
"iris", data_dir=TEST_DATASET_S3_PATH, split=split, as_supervised=True
)
data_dir = TEST_DATASET_S3_PATH if use_s3_datasets() else None
dataset = tfds.load("iris", data_dir=data_dir, split=split, as_supervised=True)
dataset = dataset.map(lambda features, labels: ({"dense_input": features}, labels))
dataset = dataset.batch(32).repeat()
return dataset
Expand Down