Support MXNet 1.3 with its training script format changes#446

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
laurenyu merged 23 commits into from
Nov 5, 2018
Merged

Support MXNet 1.3 with its training script format changes #446

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
23 commits
Select commit Hold shift + click to select a range
b7db5a0
Document script mode format
laurenyu Oct 25, 2018
fe2e9bf
Update MXNet estimator for changes with 1.3
laurenyu Oct 26, 2018
2008468
Fix unit tests
laurenyu Oct 27, 2018
f34b128
update integ tests
laurenyu Oct 29, 2018
ca21338
update changelog
laurenyu Oct 29, 2018
ffd20f6
bump SDK version
laurenyu Oct 29, 2018
51fe929
update integ tests
laurenyu Oct 29, 2018
9e9a3be
Merge branch 'master' into mx-13
laurenyu Oct 29, 2018
fe7bab3
undo unnecessary docstring change
laurenyu Oct 29, 2018
1fddc2e
Fix unit tests
laurenyu Oct 29, 2018
072f19f
Address PR feedback
laurenyu Oct 29, 2018
7175165
update info about dependencies
laurenyu Oct 29, 2018
623c722
add documentation about parameter server
laurenyu Oct 29, 2018
3e2ab64
fix lowest script mode version
laurenyu Oct 30, 2018
82257f2
fix integ tests
laurenyu Nov 2, 2018
eaac852
update integ tests
laurenyu Nov 2, 2018
faec731
update integ tests
laurenyu Nov 2, 2018
9d69562
change launch_parameter_server to distributions
laurenyu Nov 3, 2018
e018f42
change launch_parameter_server to distributions
laurenyu Nov 3, 2018
01dcb9d
Merge branch 'master' into mx-13
laurenyu Nov 5, 2018
1ff9836
update changelog
laurenyu Nov 5, 2018
6a44d88
address PR comment
laurenyu Nov 5, 2018
c9ef5dc
Merge branch 'master' into mx-13
laurenyu Nov 5, 2018
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
6 changes: 4 additions & 2 deletions CHANGELOG.rst
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -2,14 +2,16 @@
CHANGELOG
=========

========
1.13.0
========
======

* feature: Estimator: add input mode to training channels
* feature: Estimator: add model_uri and model_channel_name parameters
* enhancement: Local Mode: support output_path. Can be either file:// or s3://
* enhancement: Added image uris for SageMaker built-in algorithms for SIN/LHR/BOM/SFO/YUL
* feature: Estimators: add support for MXNet 1.3.0, which introduces a new training script format
* feature: Documentation: add explanation for the new training script format used with MXNet
* feature: Estimators: add ``distributions`` for customizing distributed training with the new training script format

1.12.0
======
Expand Down
8 changes: 4 additions & 4 deletions src/sagemaker/chainer/estimator.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
custom-image:latest.
**kwargs: Additional kwargs passed to the :class:`~sagemaker.estimator.Framework` constructor.
"""
if framework_version is None:
logger.warning(empty_framework_version_warning(CHAINER_VERSION))
self.framework_version = framework_version or CHAINER_VERSION

super(Chainer, self).__init__(entry_point, source_dir, hyperparameters,
image_name=image_name, **kwargs)
self.py_version = py_version
Expand All@@ -89,10 +93,6 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
self.process_slots_per_host = process_slots_per_host
self.additional_mpi_options = additional_mpi_options

if framework_version is None:
logger.warning(empty_framework_version_warning(CHAINER_VERSION))
self.framework_version = framework_version or CHAINER_VERSION

def hyperparameters(self):
"""Return hyperparameters used by your custom Chainer code during training."""
hyperparameters = super(Chainer, self).hyperparameters()
Expand Down
27 changes: 25 additions & 2 deletions src/sagemaker/estimator.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -627,8 +627,12 @@ class Framework(EstimatorBase):
such as training/deployment images and predictor instances.
"""

_DISTRIBUTION_SUPPORTED_FRAMEWORKS = ('mxnet',)
LAUNCH_PS_ENV_NAME = 'sagemaker_parameter_server_enabled'

def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cloudwatch_metrics=False,
container_log_level=logging.INFO, code_location=None, image_name=None, **kwargs):
container_log_level=logging.INFO, code_location=None, image_name=None,
distributions=None, **kwargs):
"""Base class initializer. Subclasses which override ``__init__`` should invoke ``super()``

Args:
Expand All@@ -650,6 +654,8 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
image_name (str): An alternate image name to use instead of the official Sagemaker image
for the framework. This is useful to run one of the Sagemaker supported frameworks
with an image containing custom dependencies.
distributions (dict): A dictionary with information on how to run distributed training
(default: None).
**kwargs: Additional kwargs passed to the ``EstimatorBase`` constructor.
"""
super(Framework, self).__init__(**kwargs)
Expand All@@ -660,10 +666,27 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
DeprecationWarning)
self.enable_cloudwatch_metrics = False
self.container_log_level = container_log_level
self._hyperparameters = hyperparameters or {}
self.code_location = code_location
self.image_name = image_name

self._hyperparameters = hyperparameters or {}
self._configure_distributions(distributions)

def _configure_distributions(self, distributions):
if distributions is None:
return

if self.__framework_name__ not in self._DISTRIBUTION_SUPPORTED_FRAMEWORKS:
raise ValueError('This framework does not support the distributions option.')

if self.framework_version.split('.') < self._LOWEST_SCRIPT_MODE_VERSION:
raise ValueError('The distributions option is valid for only versions {} and higher'
.format('.'.join(self._LOWEST_SCRIPT_MODE_VERSION)))

if 'parameter_server' in distributions:
enabled = distributions['parameter_server'].get('enabled', False)
self._hyperparameters[self.LAUNCH_PS_ENV_NAME] = enabled

def _prepare_for_training(self, job_name=None):
"""Set hyperparameters needed for training. This method will also validate ``source_dir``.

Expand Down
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
Support MXNet 1.3 with its training script format changes#446

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

laurenyu
merged 23 commits into

from

Nov 5, 2018
 Merged


Support MXNet 1.3 with its training script format changes
#446
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


23 commits


Select commit
Hold shift + click to select a range
b7db5a0

Document script mode format


laurenyu Oct 25, 2018
fe2e9bf

Update MXNet estimator for changes with 1.3


laurenyu Oct 26, 2018
2008468

Fix unit tests


laurenyu Oct 27, 2018
f34b128

update integ tests


laurenyu Oct 29, 2018
ca21338

update changelog


laurenyu Oct 29, 2018
ffd20f6

bump SDK version


laurenyu Oct 29, 2018
51fe929

update integ tests


laurenyu Oct 29, 2018
9e9a3be

Merge branch 'master' into mx-13


laurenyu Oct 29, 2018
fe7bab3

undo unnecessary docstring change


laurenyu Oct 29, 2018
1fddc2e

Fix unit tests


laurenyu Oct 29, 2018
072f19f

Address PR feedback


laurenyu Oct 29, 2018
7175165

update info about dependencies


laurenyu Oct 29, 2018
623c722

add documentation about parameter server


laurenyu Oct 29, 2018
3e2ab64

fix lowest script mode version


laurenyu Oct 30, 2018
82257f2

fix integ tests


laurenyu Nov 2, 2018
eaac852

update integ tests


laurenyu Nov 2, 2018
faec731

update integ tests


laurenyu Nov 2, 2018
9d69562

change launch_parameter_server to distributions


laurenyu Nov 3, 2018
e018f42

change launch_parameter_server to distributions


laurenyu Nov 3, 2018
01dcb9d

Merge branch 'master' into mx-13


laurenyu Nov 5, 2018
1ff9836

update changelog


laurenyu Nov 5, 2018
6a44d88

address PR comment


laurenyu Nov 5, 2018
c9ef5dc

Merge branch 'master' into mx-13


laurenyu Nov 5, 2018

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


6 changes: 4 additions & 2 deletions
CHANGELOG.rst

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -2,14 +2,16 @@
CHANGELOG
=========

========
1.13.0
========
======

* feature: Estimator: add input mode to training channels
* feature: Estimator: add model_uri and model_channel_name parameters
* enhancement: Local Mode: support output_path. Can be either file:// or s3://
* enhancement: Added image uris for SageMaker built-in algorithms for SIN/LHR/BOM/SFO/YUL
* feature: Estimators: add support for MXNet 1.3.0, which introduces a new training script format
* feature: Documentation: add explanation for the new training script format used with MXNet
* feature: Estimators: add ``distributions`` for customizing distributed training with the new training script format

1.12.0
======
Expand Down

8 changes: 4 additions & 4 deletions
src/sagemaker/chainer/estimator.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
 custom-image:latest.
 **kwargs: Additional kwargs passed to the :class:`~sagemaker.estimator.Framework` constructor.
 """
 if framework_version is None:
 logger.warning(empty_framework_version_warning(CHAINER_VERSION))
 self.framework_version = framework_version or CHAINER_VERSION

 super(Chainer, self).__init__(entry_point, source_dir, hyperparameters,
 image_name=image_name, **kwargs)
 self.py_version = py_version
Expand All@@ -89,10 +93,6 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
 self.process_slots_per_host = process_slots_per_host
 self.additional_mpi_options = additional_mpi_options

 if framework_version is None:
 logger.warning(empty_framework_version_warning(CHAINER_VERSION))
 self.framework_version = framework_version or CHAINER_VERSION

 def hyperparameters(self):
 """Return hyperparameters used by your custom Chainer code during training."""
 hyperparameters = super(Chainer, self).hyperparameters()
Expand Down

27 changes: 25 additions & 2 deletions
src/sagemaker/estimator.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -627,8 +627,12 @@ class Framework(EstimatorBase):
 such as training/deployment images and predictor instances.
 """

 _DISTRIBUTION_SUPPORTED_FRAMEWORKS = ('mxnet',)
 LAUNCH_PS_ENV_NAME = 'sagemaker_parameter_server_enabled'

 def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cloudwatch_metrics=False,
 container_log_level=logging.INFO, code_location=None, image_name=None, **kwargs):
 container_log_level=logging.INFO, code_location=None, image_name=None,
 distributions=None, **kwargs):
 """Base class initializer. Subclasses which override ``__init__`` should invoke ``super()``

 Args:
Expand All@@ -650,6 +654,8 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
 image_name (str): An alternate image name to use instead of the official Sagemaker image
 for the framework. This is useful to run one of the Sagemaker supported frameworks
 with an image containing custom dependencies.
 distributions (dict): A dictionary with information on how to run distributed training
 (default: None).
 **kwargs: Additional kwargs passed to the ``EstimatorBase`` constructor.
 """
 super(Framework, self).__init__(**kwargs)
Expand All@@ -660,10 +666,27 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
 DeprecationWarning)
 self.enable_cloudwatch_metrics = False
 self.container_log_level = container_log_level
 self._hyperparameters = hyperparameters or {}
 self.code_location = code_location
 self.image_name = image_name

 self._hyperparameters = hyperparameters or {}
 self._configure_distributions(distributions)

 def _configure_distributions(self, distributions):
 if distributions is None:
 return

 if self.__framework_name__ not in self._DISTRIBUTION_SUPPORTED_FRAMEWORKS:
 raise ValueError('This framework does not support the distributions option.')

 if self.framework_version.split('.') < self._LOWEST_SCRIPT_MODE_VERSION:
 raise ValueError('The distributions option is valid for only versions {} and higher'
 .format('.'.join(self._LOWEST_SCRIPT_MODE_VERSION)))

 if 'parameter_server' in distributions:
 enabled = distributions['parameter_server'].get('enabled', False)
 self._hyperparameters[self.LAUNCH_PS_ENV_NAME] = enabled

 def _prepare_for_training(self, job_name=None):
 """Set hyperparameters needed for training. This method will also validate ``source_dir``.

Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Support MXNet 1.3 with its training script format changes#446

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

laurenyu
merged 23 commits into

from

Nov 5, 2018
 Merged


Support MXNet 1.3 with its training script format changes
#446
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


23 commits


Select commit
Hold shift + click to select a range
b7db5a0

Document script mode format


laurenyu Oct 25, 2018
fe2e9bf

Update MXNet estimator for changes with 1.3


laurenyu Oct 26, 2018
2008468

Fix unit tests


laurenyu Oct 27, 2018
f34b128

update integ tests


laurenyu Oct 29, 2018
ca21338

update changelog


laurenyu Oct 29, 2018
ffd20f6

bump SDK version


laurenyu Oct 29, 2018
51fe929

update integ tests


laurenyu Oct 29, 2018
9e9a3be

Merge branch 'master' into mx-13


laurenyu Oct 29, 2018
fe7bab3

undo unnecessary docstring change


laurenyu Oct 29, 2018
1fddc2e

Fix unit tests


laurenyu Oct 29, 2018
072f19f

Address PR feedback


laurenyu Oct 29, 2018
7175165

update info about dependencies


laurenyu Oct 29, 2018
623c722

add documentation about parameter server


laurenyu Oct 29, 2018
3e2ab64

fix lowest script mode version


laurenyu Oct 30, 2018
82257f2

fix integ tests


laurenyu Nov 2, 2018
eaac852

update integ tests


laurenyu Nov 2, 2018
faec731

update integ tests


laurenyu Nov 2, 2018
9d69562

change launch_parameter_server to distributions


laurenyu Nov 3, 2018
e018f42

change launch_parameter_server to distributions


laurenyu Nov 3, 2018
01dcb9d

Merge branch 'master' into mx-13


laurenyu Nov 5, 2018
1ff9836

update changelog


laurenyu Nov 5, 2018
6a44d88

address PR comment


laurenyu Nov 5, 2018
c9ef5dc

Merge branch 'master' into mx-13


laurenyu Nov 5, 2018

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


6 changes: 4 additions & 2 deletions
CHANGELOG.rst

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -2,14 +2,16 @@
CHANGELOG
=========

========
1.13.0
========
======

* feature: Estimator: add input mode to training channels
* feature: Estimator: add model_uri and model_channel_name parameters
* enhancement: Local Mode: support output_path. Can be either file:// or s3://
* enhancement: Added image uris for SageMaker built-in algorithms for SIN/LHR/BOM/SFO/YUL
* feature: Estimators: add support for MXNet 1.3.0, which introduces a new training script format
* feature: Documentation: add explanation for the new training script format used with MXNet
* feature: Estimators: add ``distributions`` for customizing distributed training with the new training script format

1.12.0
======
Expand Down

8 changes: 4 additions & 4 deletions
src/sagemaker/chainer/estimator.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
 custom-image:latest.
 **kwargs: Additional kwargs passed to the :class:`~sagemaker.estimator.Framework` constructor.
 """
 if framework_version is None:
 logger.warning(empty_framework_version_warning(CHAINER_VERSION))
 self.framework_version = framework_version or CHAINER_VERSION

 super(Chainer, self).__init__(entry_point, source_dir, hyperparameters,
 image_name=image_name, **kwargs)
 self.py_version = py_version
Expand All@@ -89,10 +93,6 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
 self.process_slots_per_host = process_slots_per_host
 self.additional_mpi_options = additional_mpi_options

 if framework_version is None:
 logger.warning(empty_framework_version_warning(CHAINER_VERSION))
 self.framework_version = framework_version or CHAINER_VERSION

 def hyperparameters(self):
 """Return hyperparameters used by your custom Chainer code during training."""
 hyperparameters = super(Chainer, self).hyperparameters()
Expand Down

27 changes: 25 additions & 2 deletions
src/sagemaker/estimator.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -627,8 +627,12 @@ class Framework(EstimatorBase):
 such as training/deployment images and predictor instances.
 """

 _DISTRIBUTION_SUPPORTED_FRAMEWORKS = ('mxnet',)
 LAUNCH_PS_ENV_NAME = 'sagemaker_parameter_server_enabled'

 def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cloudwatch_metrics=False,
 container_log_level=logging.INFO, code_location=None, image_name=None, **kwargs):
 container_log_level=logging.INFO, code_location=None, image_name=None,
 distributions=None, **kwargs):
 """Base class initializer. Subclasses which override ``__init__`` should invoke ``super()``

 Args:
Expand All@@ -650,6 +654,8 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
 image_name (str): An alternate image name to use instead of the official Sagemaker image
 for the framework. This is useful to run one of the Sagemaker supported frameworks
 with an image containing custom dependencies.
 distributions (dict): A dictionary with information on how to run distributed training
 (default: None).
 **kwargs: Additional kwargs passed to the ``EstimatorBase`` constructor.
 """
 super(Framework, self).__init__(**kwargs)
Expand All@@ -660,10 +666,27 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
 DeprecationWarning)
 self.enable_cloudwatch_metrics = False
 self.container_log_level = container_log_level
 self._hyperparameters = hyperparameters or {}
 self.code_location = code_location
 self.image_name = image_name

 self._hyperparameters = hyperparameters or {}
 self._configure_distributions(distributions)

 def _configure_distributions(self, distributions):
 if distributions is None:
 return

 if self.__framework_name__ not in self._DISTRIBUTION_SUPPORTED_FRAMEWORKS:
 raise ValueError('This framework does not support the distributions option.')

 if self.framework_version.split('.') < self._LOWEST_SCRIPT_MODE_VERSION:
 raise ValueError('The distributions option is valid for only versions {} and higher'
 .format('.'.join(self._LOWEST_SCRIPT_MODE_VERSION)))

 if 'parameter_server' in distributions:
 enabled = distributions['parameter_server'].get('enabled', False)
 self._hyperparameters[self.LAUNCH_PS_ENV_NAME] = enabled

 def _prepare_for_training(self, job_name=None):
 """Set hyperparameters needed for training. This method will also validate ``source_dir``.

Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Support MXNet 1.3 with its training script format changes#446

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

laurenyu
merged 23 commits into

from

Nov 5, 2018
 Merged


Support MXNet 1.3 with its training script format changes
#446
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


23 commits


Select commit
Hold shift + click to select a range
b7db5a0

Document script mode format


laurenyu Oct 25, 2018
fe2e9bf

Update MXNet estimator for changes with 1.3


laurenyu Oct 26, 2018
2008468

Fix unit tests


laurenyu Oct 27, 2018
f34b128

update integ tests


laurenyu Oct 29, 2018
ca21338

update changelog


laurenyu Oct 29, 2018
ffd20f6

bump SDK version


laurenyu Oct 29, 2018
51fe929

update integ tests


laurenyu Oct 29, 2018
9e9a3be

Merge branch 'master' into mx-13


laurenyu Oct 29, 2018
fe7bab3

undo unnecessary docstring change


laurenyu Oct 29, 2018
1fddc2e

Fix unit tests


laurenyu Oct 29, 2018
072f19f

Address PR feedback


laurenyu Oct 29, 2018
7175165

update info about dependencies


laurenyu Oct 29, 2018
623c722

add documentation about parameter server


laurenyu Oct 29, 2018
3e2ab64

fix lowest script mode version


laurenyu Oct 30, 2018
82257f2

fix integ tests


laurenyu Nov 2, 2018
eaac852

update integ tests


laurenyu Nov 2, 2018
faec731

update integ tests


laurenyu Nov 2, 2018
9d69562

change launch_parameter_server to distributions


laurenyu Nov 3, 2018
e018f42

change launch_parameter_server to distributions


laurenyu Nov 3, 2018
01dcb9d

Merge branch 'master' into mx-13


laurenyu Nov 5, 2018
1ff9836

update changelog


laurenyu Nov 5, 2018
6a44d88

address PR comment


laurenyu Nov 5, 2018
c9ef5dc

Merge branch 'master' into mx-13


laurenyu Nov 5, 2018

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


6 changes: 4 additions & 2 deletions
CHANGELOG.rst

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -2,14 +2,16 @@
CHANGELOG
=========

========
1.13.0
========
======

* feature: Estimator: add input mode to training channels
* feature: Estimator: add model_uri and model_channel_name parameters
* enhancement: Local Mode: support output_path. Can be either file:// or s3://
* enhancement: Added image uris for SageMaker built-in algorithms for SIN/LHR/BOM/SFO/YUL
* feature: Estimators: add support for MXNet 1.3.0, which introduces a new training script format
* feature: Documentation: add explanation for the new training script format used with MXNet
* feature: Estimators: add ``distributions`` for customizing distributed training with the new training script format

1.12.0
======
Expand Down

8 changes: 4 additions & 4 deletions
src/sagemaker/chainer/estimator.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
 custom-image:latest.
 **kwargs: Additional kwargs passed to the :class:`~sagemaker.estimator.Framework` constructor.
 """
 if framework_version is None:
 logger.warning(empty_framework_version_warning(CHAINER_VERSION))
 self.framework_version = framework_version or CHAINER_VERSION

 super(Chainer, self).__init__(entry_point, source_dir, hyperparameters,
 image_name=image_name, **kwargs)
 self.py_version = py_version
Expand All@@ -89,10 +93,6 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
 self.process_slots_per_host = process_slots_per_host
 self.additional_mpi_options = additional_mpi_options

 if framework_version is None:
 logger.warning(empty_framework_version_warning(CHAINER_VERSION))
 self.framework_version = framework_version or CHAINER_VERSION

 def hyperparameters(self):
 """Return hyperparameters used by your custom Chainer code during training."""
 hyperparameters = super(Chainer, self).hyperparameters()
Expand Down

27 changes: 25 additions & 2 deletions
src/sagemaker/estimator.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -627,8 +627,12 @@ class Framework(EstimatorBase):
 such as training/deployment images and predictor instances.
 """

 _DISTRIBUTION_SUPPORTED_FRAMEWORKS = ('mxnet',)
 LAUNCH_PS_ENV_NAME = 'sagemaker_parameter_server_enabled'

 def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cloudwatch_metrics=False,
 container_log_level=logging.INFO, code_location=None, image_name=None, **kwargs):
 container_log_level=logging.INFO, code_location=None, image_name=None,
 distributions=None, **kwargs):
 """Base class initializer. Subclasses which override ``__init__`` should invoke ``super()``

 Args:
Expand All@@ -650,6 +654,8 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
 image_name (str): An alternate image name to use instead of the official Sagemaker image
 for the framework. This is useful to run one of the Sagemaker supported frameworks
 with an image containing custom dependencies.
 distributions (dict): A dictionary with information on how to run distributed training
 (default: None).
 **kwargs: Additional kwargs passed to the ``EstimatorBase`` constructor.
 """
 super(Framework, self).__init__(**kwargs)
Expand All@@ -660,10 +666,27 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
 DeprecationWarning)
 self.enable_cloudwatch_metrics = False
 self.container_log_level = container_log_level
 self._hyperparameters = hyperparameters or {}
 self.code_location = code_location
 self.image_name = image_name

 self._hyperparameters = hyperparameters or {}
 self._configure_distributions(distributions)

 def _configure_distributions(self, distributions):
 if distributions is None:
 return

 if self.__framework_name__ not in self._DISTRIBUTION_SUPPORTED_FRAMEWORKS:
 raise ValueError('This framework does not support the distributions option.')

 if self.framework_version.split('.') < self._LOWEST_SCRIPT_MODE_VERSION:
 raise ValueError('The distributions option is valid for only versions {} and higher'
 .format('.'.join(self._LOWEST_SCRIPT_MODE_VERSION)))

 if 'parameter_server' in distributions:
 enabled = distributions['parameter_server'].get('enabled', False)
 self._hyperparameters[self.LAUNCH_PS_ENV_NAME] = enabled

 def _prepare_for_training(self, job_name=None):
 """Set hyperparameters needed for training. This method will also validate ``source_dir``.

Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
Support MXNet 1.3 with its training script format changes#446

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

laurenyu
merged 23 commits into

from

Nov 5, 2018
 Merged


Support MXNet 1.3 with its training script format changes
#446
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


23 commits


Select commit
Hold shift + click to select a range
b7db5a0

Document script mode format


laurenyu Oct 25, 2018
fe2e9bf

Update MXNet estimator for changes with 1.3


laurenyu Oct 26, 2018
2008468

Fix unit tests


laurenyu Oct 27, 2018
f34b128

update integ tests


laurenyu Oct 29, 2018
ca21338

update changelog


laurenyu Oct 29, 2018
ffd20f6

bump SDK version


laurenyu Oct 29, 2018
51fe929

update integ tests


laurenyu Oct 29, 2018
9e9a3be

Merge branch 'master' into mx-13


laurenyu Oct 29, 2018
fe7bab3

undo unnecessary docstring change


laurenyu Oct 29, 2018
1fddc2e

Fix unit tests


laurenyu Oct 29, 2018
072f19f

Address PR feedback


laurenyu Oct 29, 2018
7175165

update info about dependencies


laurenyu Oct 29, 2018
623c722

add documentation about parameter server


laurenyu Oct 29, 2018
3e2ab64

fix lowest script mode version


laurenyu Oct 30, 2018
82257f2

fix integ tests


laurenyu Nov 2, 2018
eaac852

update integ tests


laurenyu Nov 2, 2018
faec731

update integ tests


laurenyu Nov 2, 2018
9d69562

change launch_parameter_server to distributions


laurenyu Nov 3, 2018
e018f42

change launch_parameter_server to distributions


laurenyu Nov 3, 2018
01dcb9d

Merge branch 'master' into mx-13


laurenyu Nov 5, 2018
1ff9836

update changelog


laurenyu Nov 5, 2018
6a44d88

address PR comment


laurenyu Nov 5, 2018
c9ef5dc

Merge branch 'master' into mx-13


laurenyu Nov 5, 2018

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


6 changes: 4 additions & 2 deletions
CHANGELOG.rst

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -2,14 +2,16 @@
CHANGELOG
=========

========
1.13.0
========
======

* feature: Estimator: add input mode to training channels
* feature: Estimator: add model_uri and model_channel_name parameters
* enhancement: Local Mode: support output_path. Can be either file:// or s3://
* enhancement: Added image uris for SageMaker built-in algorithms for SIN/LHR/BOM/SFO/YUL
* feature: Estimators: add support for MXNet 1.3.0, which introduces a new training script format
* feature: Documentation: add explanation for the new training script format used with MXNet
* feature: Estimators: add ``distributions`` for customizing distributed training with the new training script format

1.12.0
======
Expand Down

8 changes: 4 additions & 4 deletions
src/sagemaker/chainer/estimator.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
 custom-image:latest.
 **kwargs: Additional kwargs passed to the :class:`~sagemaker.estimator.Framework` constructor.
 """
 if framework_version is None:
 logger.warning(empty_framework_version_warning(CHAINER_VERSION))
 self.framework_version = framework_version or CHAINER_VERSION

 super(Chainer, self).__init__(entry_point, source_dir, hyperparameters,
 image_name=image_name, **kwargs)
 self.py_version = py_version
Expand All@@ -89,10 +93,6 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
 self.process_slots_per_host = process_slots_per_host
 self.additional_mpi_options = additional_mpi_options

 if framework_version is None:
 logger.warning(empty_framework_version_warning(CHAINER_VERSION))
 self.framework_version = framework_version or CHAINER_VERSION

 def hyperparameters(self):
 """Return hyperparameters used by your custom Chainer code during training."""
 hyperparameters = super(Chainer, self).hyperparameters()
Expand Down

27 changes: 25 additions & 2 deletions
src/sagemaker/estimator.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -627,8 +627,12 @@ class Framework(EstimatorBase):
 such as training/deployment images and predictor instances.
 """

 _DISTRIBUTION_SUPPORTED_FRAMEWORKS = ('mxnet',)
 LAUNCH_PS_ENV_NAME = 'sagemaker_parameter_server_enabled'

 def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cloudwatch_metrics=False,
 container_log_level=logging.INFO, code_location=None, image_name=None, **kwargs):
 container_log_level=logging.INFO, code_location=None, image_name=None,
 distributions=None, **kwargs):
 """Base class initializer. Subclasses which override ``__init__`` should invoke ``super()``

 Args:
Expand All@@ -650,6 +654,8 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
 image_name (str): An alternate image name to use instead of the official Sagemaker image
 for the framework. This is useful to run one of the Sagemaker supported frameworks
 with an image containing custom dependencies.
 distributions (dict): A dictionary with information on how to run distributed training
 (default: None).
 **kwargs: Additional kwargs passed to the ``EstimatorBase`` constructor.
 """
 super(Framework, self).__init__(**kwargs)
Expand All@@ -660,10 +666,27 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
 DeprecationWarning)
 self.enable_cloudwatch_metrics = False
 self.container_log_level = container_log_level
 self._hyperparameters = hyperparameters or {}
 self.code_location = code_location
 self.image_name = image_name

 self._hyperparameters = hyperparameters or {}
 self._configure_distributions(distributions)

 def _configure_distributions(self, distributions):
 if distributions is None:
 return

 if self.__framework_name__ not in self._DISTRIBUTION_SUPPORTED_FRAMEWORKS:
 raise ValueError('This framework does not support the distributions option.')

 if self.framework_version.split('.') < self._LOWEST_SCRIPT_MODE_VERSION:
 raise ValueError('The distributions option is valid for only versions {} and higher'
 .format('.'.join(self._LOWEST_SCRIPT_MODE_VERSION)))

 if 'parameter_server' in distributions:
 enabled = distributions['parameter_server'].get('enabled', False)
 self._hyperparameters[self.LAUNCH_PS_ENV_NAME] = enabled

 def _prepare_for_training(self, job_name=None):
 """Set hyperparameters needed for training. This method will also validate ``source_dir``.

Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Support MXNet 1.3 with its training script format changes#446

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

laurenyu
merged 23 commits into

from

Nov 5, 2018
 Merged


Support MXNet 1.3 with its training script format changes
#446
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


23 commits


Select commit
Hold shift + click to select a range
b7db5a0

Document script mode format


laurenyu Oct 25, 2018
fe2e9bf

Update MXNet estimator for changes with 1.3


laurenyu Oct 26, 2018
2008468

Fix unit tests


laurenyu Oct 27, 2018
f34b128

update integ tests


laurenyu Oct 29, 2018
ca21338

update changelog


laurenyu Oct 29, 2018
ffd20f6

bump SDK version


laurenyu Oct 29, 2018
51fe929

update integ tests


laurenyu Oct 29, 2018
9e9a3be

Merge branch 'master' into mx-13


laurenyu Oct 29, 2018
fe7bab3

undo unnecessary docstring change


laurenyu Oct 29, 2018
1fddc2e

Fix unit tests


laurenyu Oct 29, 2018
072f19f

Address PR feedback


laurenyu Oct 29, 2018
7175165

update info about dependencies


laurenyu Oct 29, 2018
623c722

add documentation about parameter server


laurenyu Oct 29, 2018
3e2ab64

fix lowest script mode version


laurenyu Oct 30, 2018
82257f2

fix integ tests


laurenyu Nov 2, 2018
eaac852

update integ tests


laurenyu Nov 2, 2018
faec731

update integ tests


laurenyu Nov 2, 2018
9d69562

change launch_parameter_server to distributions


laurenyu Nov 3, 2018
e018f42

change launch_parameter_server to distributions


laurenyu Nov 3, 2018
01dcb9d

Merge branch 'master' into mx-13


laurenyu Nov 5, 2018
1ff9836

update changelog


laurenyu Nov 5, 2018
6a44d88

address PR comment


laurenyu Nov 5, 2018
c9ef5dc

Merge branch 'master' into mx-13


laurenyu Nov 5, 2018

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


6 changes: 4 additions & 2 deletions
CHANGELOG.rst

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -2,14 +2,16 @@
CHANGELOG
=========

========
1.13.0
========
======

* feature: Estimator: add input mode to training channels
* feature: Estimator: add model_uri and model_channel_name parameters
* enhancement: Local Mode: support output_path. Can be either file:// or s3://
* enhancement: Added image uris for SageMaker built-in algorithms for SIN/LHR/BOM/SFO/YUL
* feature: Estimators: add support for MXNet 1.3.0, which introduces a new training script format
* feature: Documentation: add explanation for the new training script format used with MXNet
* feature: Estimators: add ``distributions`` for customizing distributed training with the new training script format

1.12.0
======
Expand Down

8 changes: 4 additions & 4 deletions
src/sagemaker/chainer/estimator.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
 custom-image:latest.
 **kwargs: Additional kwargs passed to the :class:`~sagemaker.estimator.Framework` constructor.
 """
 if framework_version is None:
 logger.warning(empty_framework_version_warning(CHAINER_VERSION))
 self.framework_version = framework_version or CHAINER_VERSION

 super(Chainer, self).__init__(entry_point, source_dir, hyperparameters,
 image_name=image_name, **kwargs)
 self.py_version = py_version
Expand All@@ -89,10 +93,6 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
 self.process_slots_per_host = process_slots_per_host
 self.additional_mpi_options = additional_mpi_options

 if framework_version is None:
 logger.warning(empty_framework_version_warning(CHAINER_VERSION))
 self.framework_version = framework_version or CHAINER_VERSION

 def hyperparameters(self):
 """Return hyperparameters used by your custom Chainer code during training."""
 hyperparameters = super(Chainer, self).hyperparameters()
Expand Down

27 changes: 25 additions & 2 deletions
src/sagemaker/estimator.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -627,8 +627,12 @@ class Framework(EstimatorBase):
 such as training/deployment images and predictor instances.
 """

 _DISTRIBUTION_SUPPORTED_FRAMEWORKS = ('mxnet',)
 LAUNCH_PS_ENV_NAME = 'sagemaker_parameter_server_enabled'

 def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cloudwatch_metrics=False,
 container_log_level=logging.INFO, code_location=None, image_name=None, **kwargs):
 container_log_level=logging.INFO, code_location=None, image_name=None,
 distributions=None, **kwargs):
 """Base class initializer. Subclasses which override ``__init__`` should invoke ``super()``

 Args:
Expand All@@ -650,6 +654,8 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
 image_name (str): An alternate image name to use instead of the official Sagemaker image
 for the framework. This is useful to run one of the Sagemaker supported frameworks
 with an image containing custom dependencies.
 distributions (dict): A dictionary with information on how to run distributed training
 (default: None).
 **kwargs: Additional kwargs passed to the ``EstimatorBase`` constructor.
 """
 super(Framework, self).__init__(**kwargs)
Expand All@@ -660,10 +666,27 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
 DeprecationWarning)
 self.enable_cloudwatch_metrics = False
 self.container_log_level = container_log_level
 self._hyperparameters = hyperparameters or {}
 self.code_location = code_location
 self.image_name = image_name

 self._hyperparameters = hyperparameters or {}
 self._configure_distributions(distributions)

 def _configure_distributions(self, distributions):
 if distributions is None:
 return

 if self.__framework_name__ not in self._DISTRIBUTION_SUPPORTED_FRAMEWORKS:
 raise ValueError('This framework does not support the distributions option.')

 if self.framework_version.split('.') < self._LOWEST_SCRIPT_MODE_VERSION:
 raise ValueError('The distributions option is valid for only versions {} and higher'
 .format('.'.join(self._LOWEST_SCRIPT_MODE_VERSION)))

 if 'parameter_server' in distributions:
 enabled = distributions['parameter_server'].get('enabled', False)
 self._hyperparameters[self.LAUNCH_PS_ENV_NAME] = enabled

 def _prepare_for_training(self, job_name=None):
 """Set hyperparameters needed for training. This method will also validate ``source_dir``.

Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Support MXNet 1.3 with its training script format changes#446

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

laurenyu
merged 23 commits into

from

Nov 5, 2018
 Merged


Support MXNet 1.3 with its training script format changes
#446
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


23 commits


Select commit
Hold shift + click to select a range
b7db5a0

Document script mode format


laurenyu Oct 25, 2018
fe2e9bf

Update MXNet estimator for changes with 1.3


laurenyu Oct 26, 2018
2008468

Fix unit tests


laurenyu Oct 27, 2018
f34b128

update integ tests


laurenyu Oct 29, 2018
ca21338

update changelog


laurenyu Oct 29, 2018
ffd20f6

bump SDK version


laurenyu Oct 29, 2018
51fe929

update integ tests


laurenyu Oct 29, 2018
9e9a3be

Merge branch 'master' into mx-13


laurenyu Oct 29, 2018
fe7bab3

undo unnecessary docstring change


laurenyu Oct 29, 2018
1fddc2e

Fix unit tests


laurenyu Oct 29, 2018
072f19f

Address PR feedback


laurenyu Oct 29, 2018
7175165

update info about dependencies


laurenyu Oct 29, 2018
623c722

add documentation about parameter server


laurenyu Oct 29, 2018
3e2ab64

fix lowest script mode version


laurenyu Oct 30, 2018
82257f2

fix integ tests


laurenyu Nov 2, 2018
eaac852

update integ tests


laurenyu Nov 2, 2018
faec731

update integ tests


laurenyu Nov 2, 2018
9d69562

change launch_parameter_server to distributions


laurenyu Nov 3, 2018
e018f42

change launch_parameter_server to distributions


laurenyu Nov 3, 2018
01dcb9d

Merge branch 'master' into mx-13


laurenyu Nov 5, 2018
1ff9836

update changelog


laurenyu Nov 5, 2018
6a44d88

address PR comment


laurenyu Nov 5, 2018
c9ef5dc

Merge branch 'master' into mx-13


laurenyu Nov 5, 2018

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


6 changes: 4 additions & 2 deletions
CHANGELOG.rst

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -2,14 +2,16 @@
CHANGELOG
=========

========
1.13.0
========
======

* feature: Estimator: add input mode to training channels
* feature: Estimator: add model_uri and model_channel_name parameters
* enhancement: Local Mode: support output_path. Can be either file:// or s3://
* enhancement: Added image uris for SageMaker built-in algorithms for SIN/LHR/BOM/SFO/YUL
* feature: Estimators: add support for MXNet 1.3.0, which introduces a new training script format
* feature: Documentation: add explanation for the new training script format used with MXNet
* feature: Estimators: add ``distributions`` for customizing distributed training with the new training script format

1.12.0
======
Expand Down

8 changes: 4 additions & 4 deletions
src/sagemaker/chainer/estimator.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
 custom-image:latest.
 **kwargs: Additional kwargs passed to the :class:`~sagemaker.estimator.Framework` constructor.
 """
 if framework_version is None:
 logger.warning(empty_framework_version_warning(CHAINER_VERSION))
 self.framework_version = framework_version or CHAINER_VERSION

 super(Chainer, self).__init__(entry_point, source_dir, hyperparameters,
 image_name=image_name, **kwargs)
 self.py_version = py_version
Expand All@@ -89,10 +93,6 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
 self.process_slots_per_host = process_slots_per_host
 self.additional_mpi_options = additional_mpi_options

 if framework_version is None:
 logger.warning(empty_framework_version_warning(CHAINER_VERSION))
 self.framework_version = framework_version or CHAINER_VERSION

 def hyperparameters(self):
 """Return hyperparameters used by your custom Chainer code during training."""
 hyperparameters = super(Chainer, self).hyperparameters()
Expand Down

27 changes: 25 additions & 2 deletions
src/sagemaker/estimator.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -627,8 +627,12 @@ class Framework(EstimatorBase):
 such as training/deployment images and predictor instances.
 """

 _DISTRIBUTION_SUPPORTED_FRAMEWORKS = ('mxnet',)
 LAUNCH_PS_ENV_NAME = 'sagemaker_parameter_server_enabled'

 def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cloudwatch_metrics=False,
 container_log_level=logging.INFO, code_location=None, image_name=None, **kwargs):
 container_log_level=logging.INFO, code_location=None, image_name=None,
 distributions=None, **kwargs):
 """Base class initializer. Subclasses which override ``__init__`` should invoke ``super()``

 Args:
Expand All@@ -650,6 +654,8 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
 image_name (str): An alternate image name to use instead of the official Sagemaker image
 for the framework. This is useful to run one of the Sagemaker supported frameworks
 with an image containing custom dependencies.
 distributions (dict): A dictionary with information on how to run distributed training
 (default: None).
 **kwargs: Additional kwargs passed to the ``EstimatorBase`` constructor.
 """
 super(Framework, self).__init__(**kwargs)
Expand All@@ -660,10 +666,27 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
 DeprecationWarning)
 self.enable_cloudwatch_metrics = False
 self.container_log_level = container_log_level
 self._hyperparameters = hyperparameters or {}
 self.code_location = code_location
 self.image_name = image_name

 self._hyperparameters = hyperparameters or {}
 self._configure_distributions(distributions)

 def _configure_distributions(self, distributions):
 if distributions is None:
 return

 if self.__framework_name__ not in self._DISTRIBUTION_SUPPORTED_FRAMEWORKS:
 raise ValueError('This framework does not support the distributions option.')

 if self.framework_version.split('.') < self._LOWEST_SCRIPT_MODE_VERSION:
 raise ValueError('The distributions option is valid for only versions {} and higher'
 .format('.'.join(self._LOWEST_SCRIPT_MODE_VERSION)))

 if 'parameter_server' in distributions:
 enabled = distributions['parameter_server'].get('enabled', False)
 self._hyperparameters[self.LAUNCH_PS_ENV_NAME] = enabled

 def _prepare_for_training(self, job_name=None):
 """Set hyperparameters needed for training. This method will also validate ``source_dir``.

Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
Support MXNet 1.3 with its training script format changes#446

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

laurenyu
merged 23 commits into

from

Nov 5, 2018
 Merged


Support MXNet 1.3 with its training script format changes
#446
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


23 commits


Select commit
Hold shift + click to select a range
b7db5a0

Document script mode format


laurenyu Oct 25, 2018
fe2e9bf

Update MXNet estimator for changes with 1.3


laurenyu Oct 26, 2018
2008468

Fix unit tests


laurenyu Oct 27, 2018
f34b128

update integ tests


laurenyu Oct 29, 2018
ca21338

update changelog


laurenyu Oct 29, 2018
ffd20f6

bump SDK version


laurenyu Oct 29, 2018
51fe929

update integ tests


laurenyu Oct 29, 2018
9e9a3be

Merge branch 'master' into mx-13


laurenyu Oct 29, 2018
fe7bab3

undo unnecessary docstring change


laurenyu Oct 29, 2018
1fddc2e

Fix unit tests


laurenyu Oct 29, 2018
072f19f

Address PR feedback


laurenyu Oct 29, 2018
7175165

update info about dependencies


laurenyu Oct 29, 2018
623c722

add documentation about parameter server


laurenyu Oct 29, 2018
3e2ab64

fix lowest script mode version


laurenyu Oct 30, 2018
82257f2

fix integ tests


laurenyu Nov 2, 2018
eaac852

update integ tests


laurenyu Nov 2, 2018
faec731

update integ tests


laurenyu Nov 2, 2018
9d69562

change launch_parameter_server to distributions


laurenyu Nov 3, 2018
e018f42

change launch_parameter_server to distributions


laurenyu Nov 3, 2018
01dcb9d

Merge branch 'master' into mx-13


laurenyu Nov 5, 2018
1ff9836

update changelog


laurenyu Nov 5, 2018
6a44d88

address PR comment


laurenyu Nov 5, 2018
c9ef5dc

Merge branch 'master' into mx-13


laurenyu Nov 5, 2018

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


6 changes: 4 additions & 2 deletions
CHANGELOG.rst

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -2,14 +2,16 @@
CHANGELOG
=========

========
1.13.0
========
======

* feature: Estimator: add input mode to training channels
* feature: Estimator: add model_uri and model_channel_name parameters
* enhancement: Local Mode: support output_path. Can be either file:// or s3://
* enhancement: Added image uris for SageMaker built-in algorithms for SIN/LHR/BOM/SFO/YUL
* feature: Estimators: add support for MXNet 1.3.0, which introduces a new training script format
* feature: Documentation: add explanation for the new training script format used with MXNet
* feature: Estimators: add ``distributions`` for customizing distributed training with the new training script format

1.12.0
======
Expand Down

8 changes: 4 additions & 4 deletions
src/sagemaker/chainer/estimator.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -81,6 +81,10 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
 custom-image:latest.
 **kwargs: Additional kwargs passed to the :class:`~sagemaker.estimator.Framework` constructor.
 """
 if framework_version is None:
 logger.warning(empty_framework_version_warning(CHAINER_VERSION))
 self.framework_version = framework_version or CHAINER_VERSION

 super(Chainer, self).__init__(entry_point, source_dir, hyperparameters,
 image_name=image_name, **kwargs)
 self.py_version = py_version
Expand All@@ -89,10 +93,6 @@ def __init__(self, entry_point, use_mpi=None, num_processes=None, process_slots_
 self.process_slots_per_host = process_slots_per_host
 self.additional_mpi_options = additional_mpi_options

 if framework_version is None:
 logger.warning(empty_framework_version_warning(CHAINER_VERSION))
 self.framework_version = framework_version or CHAINER_VERSION

 def hyperparameters(self):
 """Return hyperparameters used by your custom Chainer code during training."""
 hyperparameters = super(Chainer, self).hyperparameters()
Expand Down

27 changes: 25 additions & 2 deletions
src/sagemaker/estimator.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -627,8 +627,12 @@ class Framework(EstimatorBase):
 such as training/deployment images and predictor instances.
 """

 _DISTRIBUTION_SUPPORTED_FRAMEWORKS = ('mxnet',)
 LAUNCH_PS_ENV_NAME = 'sagemaker_parameter_server_enabled'

 def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cloudwatch_metrics=False,
 container_log_level=logging.INFO, code_location=None, image_name=None, **kwargs):
 container_log_level=logging.INFO, code_location=None, image_name=None,
 distributions=None, **kwargs):
 """Base class initializer. Subclasses which override ``__init__`` should invoke ``super()``

 Args:
Expand All@@ -650,6 +654,8 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
 image_name (str): An alternate image name to use instead of the official Sagemaker image
 for the framework. This is useful to run one of the Sagemaker supported frameworks
 with an image containing custom dependencies.
 distributions (dict): A dictionary with information on how to run distributed training
 (default: None).
 **kwargs: Additional kwargs passed to the ``EstimatorBase`` constructor.
 """
 super(Framework, self).__init__(**kwargs)
Expand All@@ -660,10 +666,27 @@ def __init__(self, entry_point, source_dir=None, hyperparameters=None, enable_cl
 DeprecationWarning)
 self.enable_cloudwatch_metrics = False
 self.container_log_level = container_log_level
 self._hyperparameters = hyperparameters or {}
 self.code_location = code_location
 self.image_name = image_name

 self._hyperparameters = hyperparameters or {}
 self._configure_distributions(distributions)

 def _configure_distributions(self, distributions):
 if distributions is None:
 return

 if self.__framework_name__ not in self._DISTRIBUTION_SUPPORTED_FRAMEWORKS:
 raise ValueError('This framework does not support the distributions option.')

 if self.framework_version.split('.') < self._LOWEST_SCRIPT_MODE_VERSION:
 raise ValueError('The distributions option is valid for only versions {} and higher'
 .format('.'.join(self._LOWEST_SCRIPT_MODE_VERSION)))

 if 'parameter_server' in distributions:
 enabled = distributions['parameter_server'].get('enabled', False)
 self._hyperparameters[self.LAUNCH_PS_ENV_NAME] = enabled

 def _prepare_for_training(self, job_name=None):
 """Set hyperparameters needed for training. This method will also validate ``source_dir``.

Expand Down
Loading