How to avoid saving optimizer states when exporting a model in tensorflow?
0
I have written a tensorflow model, and when I export the model using simple_save, like this:
signature_def_map =
signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
signature_def_utils.predict_signature_def(inputs, outputs)
b = builder.SavedModelBuilder(export_dir)
b.add_meta_graph_and_variables(
session,
tags=[tag_constants.SERVING],
signature_def_map=signature_def_map,
assets_collection=ops.get_collection(ops.GraphKeys.ASSET_FILEPATHS),
legacy_init_op=legacy_init_op,
clear_devices=True)
b.save(as_text=True)I found that all the variables in Adagrad are also saved, according to the saved_model.pbtxt:
node {
name: "input/input_layer_1/context.match_type_info_x_MatchNum_embedding/embedding_weights/part_0/Adagrad"
op: "VariableV2"
attr
key: "_class"
value
list
s: "loc:@input/input_layer_1/context.match_type_info_x_MatchNum_embedding/embedding_weights/part_0"
attr
key: "_output_shapes"
value
list
shape
dim
size: 31
dim
size: 16
This causes the saved model to be twice as big as necessary. Is there a way to remove them? (The saved model is used for prediction only, so it does not need the optimizer states.)
Thanks!
tensorflow tensorflow-serving
asked Nov 15 '18 at 6:37
Chi ZhangChi Zhang
3861521
add a comment |
0
I have written a tensorflow model, and when I export the model using simple_save, like this:
signature_def_map =
signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
signature_def_utils.predict_signature_def(inputs, outputs)
b = builder.SavedModelBuilder(export_dir)
b.add_meta_graph_and_variables(
session,
tags=[tag_constants.SERVING],
signature_def_map=signature_def_map,
assets_collection=ops.get_collection(ops.GraphKeys.ASSET_FILEPATHS),
legacy_init_op=legacy_init_op,
clear_devices=True)
b.save(as_text=True)I found that all the variables in Adagrad are also saved, according to the saved_model.pbtxt:
node {
name: "input/input_layer_1/context.match_type_info_x_MatchNum_embedding/embedding_weights/part_0/Adagrad"
op: "VariableV2"
attr
key: "_class"
value
list
s: "loc:@input/input_layer_1/context.match_type_info_x_MatchNum_embedding/embedding_weights/part_0"
attr
key: "_output_shapes"
value
list
shape
dim
size: 31
dim
size: 16
This causes the saved model to be twice as big as necessary. Is there a way to remove them? (The saved model is used for prediction only, so it does not need the optimizer states.)
Thanks!
tensorflow tensorflow-serving
asked Nov 15 '18 at 6:37
Chi ZhangChi Zhang
3861521
add a comment |
0
0
0
I have written a tensorflow model, and when I export the model using simple_save, like this:
signature_def_map =
signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
signature_def_utils.predict_signature_def(inputs, outputs)
b = builder.SavedModelBuilder(export_dir)
b.add_meta_graph_and_variables(
session,
tags=[tag_constants.SERVING],
signature_def_map=signature_def_map,
assets_collection=ops.get_collection(ops.GraphKeys.ASSET_FILEPATHS),
legacy_init_op=legacy_init_op,
clear_devices=True)
b.save(as_text=True)I found that all the variables in Adagrad are also saved, according to the saved_model.pbtxt:
node {
name: "input/input_layer_1/context.match_type_info_x_MatchNum_embedding/embedding_weights/part_0/Adagrad"
op: "VariableV2"
attr
key: "_class"
value
list
s: "loc:@input/input_layer_1/context.match_type_info_x_MatchNum_embedding/embedding_weights/part_0"
attr
key: "_output_shapes"
value
list
shape
dim
size: 31
dim
size: 16
This causes the saved model to be twice as big as necessary. Is there a way to remove them? (The saved model is used for prediction only, so it does not need the optimizer states.)
Thanks!
tensorflow tensorflow-serving
asked Nov 15 '18 at 6:37
Chi ZhangChi Zhang
3861521
I have written a tensorflow model, and when I export the model using simple_save, like this:
signature_def_map =
signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
signature_def_utils.predict_signature_def(inputs, outputs)
b = builder.SavedModelBuilder(export_dir)
b.add_meta_graph_and_variables(
session,
tags=[tag_constants.SERVING],
signature_def_map=signature_def_map,
assets_collection=ops.get_collection(ops.GraphKeys.ASSET_FILEPATHS),
legacy_init_op=legacy_init_op,
clear_devices=True)
b.save(as_text=True)I found that all the variables in Adagrad are also saved, according to the saved_model.pbtxt:
node {
name: "input/input_layer_1/context.match_type_info_x_MatchNum_embedding/embedding_weights/part_0/Adagrad"
op: "VariableV2"
attr
key: "_class"
value
list
s: "loc:@input/input_layer_1/context.match_type_info_x_MatchNum_embedding/embedding_weights/part_0"
attr
key: "_output_shapes"
value
list
shape
dim
size: 31
dim
size: 16
This causes the saved model to be twice as big as necessary. Is there a way to remove them? (The saved model is used for prediction only, so it does not need the optimizer states.)
Thanks!
signature_def_map =
signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
signature_def_utils.predict_signature_def(inputs, outputs)
b = builder.SavedModelBuilder(export_dir)
b.add_meta_graph_and_variables(
session,
tags=[tag_constants.SERVING],
signature_def_map=signature_def_map,
assets_collection=ops.get_collection(ops.GraphKeys.ASSET_FILEPATHS),
legacy_init_op=legacy_init_op,
clear_devices=True)
b.save(as_text=True)signature_def_map =
signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
signature_def_utils.predict_signature_def(inputs, outputs)
b = builder.SavedModelBuilder(export_dir)
b.add_meta_graph_and_variables(
session,
tags=[tag_constants.SERVING],
signature_def_map=signature_def_map,
assets_collection=ops.get_collection(ops.GraphKeys.ASSET_FILEPATHS),
legacy_init_op=legacy_init_op,
clear_devices=True)
b.save(as_text=True)node {
name: "input/input_layer_1/context.match_type_info_x_MatchNum_embedding/embedding_weights/part_0/Adagrad"
op: "VariableV2"
attr
key: "_class"
value
list
s: "loc:@input/input_layer_1/context.match_type_info_x_MatchNum_embedding/embedding_weights/part_0"
attr
key: "_output_shapes"
value
list
shape
dim
size: 31
dim
size: 16
node {
name: "input/input_layer_1/context.match_type_info_x_MatchNum_embedding/embedding_weights/part_0/Adagrad"
op: "VariableV2"
attr
key: "_class"
value
list
s: "loc:@input/input_layer_1/context.match_type_info_x_MatchNum_embedding/embedding_weights/part_0"
attr
key: "_output_shapes"
value
list
shape
dim
size: 31
dim
size: 16
tensorflow tensorflow-serving
tensorflow tensorflow-serving
asked Nov 15 '18 at 6:37
Chi ZhangChi Zhang
3861521
asked Nov 15 '18 at 6:37
Chi ZhangChi Zhang
3861521
asked Nov 15 '18 at 6:37
Chi ZhangChi Zhang
3861521
asked Nov 15 '18 at 6:37
Chi ZhangChi Zhang
3861521
asked Nov 15 '18 at 6:37
Chi ZhangChi Zhang
3861521
3861521
add a comment |
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function ()
StackExchange.using("externalEditor", function ()
StackExchange.using("snippets", function ()
StackExchange.snippets.init();
);
);
, "code-snippets");
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "1"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);
else
createEditor();
);
function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);
);
draft saved
draft discarded
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53313735%2fhow-to-avoid-saving-optimizer-states-when-exporting-a-model-in-tensorflow%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
draft saved
draft discarded
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
draft saved
draft discarded
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53313735%2fhow-to-avoid-saving-optimizer-states-when-exporting-a-model-in-tensorflow%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
