Trjtdtk

Modern Day Chaucer

Hostile work environment after whistle-blowing on coworker and our boss. What do I do?

Can I Retrieve Email Addresses from BCC?

Visiting the UK as unmarried couple

Could solar power be utilized and substitute coal in the 19th century?

What is the smallest body in which a sling shot maneuver can be performed?

What (else) happened July 1st 1858 in London?

Generators of the mapping class group for surfaces with punctures and boundaries

NIntegrate: How can I solve this integral numerically? NIntegrate fails while Integrate works

Are taller landing gear bad for aircraft, particulary large airliners?

How to deal with loss of decision making power over a change?

Why isn't KTEX's runway designation 10/28 instead of 9/27?

Simulating a probability of 1 of 2^N with less than N random bits

Did US corporations pay demonstrators in the German demonstrations against article 13?

Freedom of speech and where it applies

A car is moving at 40 km/h. A fly at 100 km/h, starts from wall towards the car(20 km away)flies to car and back. How many trips can it make?

Why does the compiler allow throws when the method will never throw the Exception

Can a Gentile theist be saved?

What does the "3am" section means in manpages?

Is it possible to build a CPA Secure encryption scheme which remains secure even when the encryption of secret key is given?

What is the opposite of 'gravitas'?

Make "apt-get update" show the exact output as `apt update`

JavaScript array of objects contains the same array data

Why is .bash_history periodically wiped?

Can I continue a machine learning process after shutdown?

Can we train a neural network to tell if an object is present or not in an Image?What exactly is a step in Tensorflow prebuilt architectures?Breaking captcha with a neural network - Learning deep learningWhat are differentiable modules used in deep learningHow to extract all information by using idIs there any work done on reconfigurable convolutional neural networks?How can I combine images for Matlab deep learning?Simple Object DetectionHow is Stochastic Gradient Descent done in Faster RCNN?What (and how) should I use for object detection in this case?

1

$begingroup$

I use Mask RCNN for object detection and instance segmentation.
I am new to neural networks, this is my first project.

I use jupyter notebook. Can I continue learning after shutdown?

I would like start learning from 6 epoch. How can I do it?
One epoch ~ 1h. I don't want to waste time, and continue this process. Is it possible?

deep-learning jupyter

share|improve this question

edited Mar 20 at 13:27

Blenzus

496

asked Mar 20 at 13:17

BadumBadum

113

$endgroup$

add a comment | 

1

$begingroup$

I use Mask RCNN for object detection and instance segmentation.
I am new to neural networks, this is my first project.

I use jupyter notebook. Can I continue learning after shutdown?

I would like start learning from 6 epoch. How can I do it?
One epoch ~ 1h. I don't want to waste time, and continue this process. Is it possible?

deep-learning jupyter

share|improve this question

edited Mar 20 at 13:27

Blenzus

496

asked Mar 20 at 13:17

BadumBadum

113

$endgroup$

add a comment | 

$begingroup$

I use Mask RCNN for object detection and instance segmentation.
I am new to neural networks, this is my first project.

I use jupyter notebook. Can I continue learning after shutdown?

I would like start learning from 6 epoch. How can I do it?
One epoch ~ 1h. I don't want to waste time, and continue this process. Is it possible?

deep-learning jupyter

share|improve this question

edited Mar 20 at 13:27

Blenzus

496

asked Mar 20 at 13:17

BadumBadum

113

$endgroup$

share|improve this question

edited Mar 20 at 13:27

Blenzus

496

asked Mar 20 at 13:17

BadumBadum

113

share|improve this question

edited Mar 20 at 13:27

Blenzus

496

asked Mar 20 at 13:17

BadumBadum

113

edited Mar 20 at 13:27

Blenzus

496

edited Mar 20 at 13:27

Blenzus

496

asked Mar 20 at 13:17

BadumBadum

113

asked Mar 20 at 13:17

BadumBadum

113

1 Answer
1

active

oldest

votes

1

$begingroup$

In order to continue the learning process, you will need to use checkpoints.

# source: https://stackoverflow.com/questions/36356004/continue-training-from-a-specific-epoch
weight_save_callback = ModelCheckpoint('/path/to/weights.epoch:02d-val_loss:.2f.hdf5', monitor='val_loss', verbose=0, save_best_only=False, mode='auto')
model.fit(X_train,y_train,batch_size=batch_size,nb_epoch=nb_epoch,callbacks=[weight_save_callback])

# load model
model = Sequential()
model.add(...)
model.load('path/to/weights.hf5')

# use model.fit to continue training.

share|improve this answer

answered Mar 20 at 13:23

MachineLearnerMachineLearner

32410

New contributor

MachineLearner is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

Your Answer

StackExchange.ifUsing("editor", function ()
return StackExchange.using("mathjaxEditing", function ()
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix)
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
);
);
, "mathjax-editing");

StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "557"
;
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: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
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

Name

Email

Required, but never shown

StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47672%2fcan-i-continue-a-machine-learning-process-after-shutdown%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

1

$begingroup$

In order to continue the learning process, you will need to use checkpoints.

# source: https://stackoverflow.com/questions/36356004/continue-training-from-a-specific-epoch
weight_save_callback = ModelCheckpoint('/path/to/weights.epoch:02d-val_loss:.2f.hdf5', monitor='val_loss', verbose=0, save_best_only=False, mode='auto')
model.fit(X_train,y_train,batch_size=batch_size,nb_epoch=nb_epoch,callbacks=[weight_save_callback])

# load model
model = Sequential()
model.add(...)
model.load('path/to/weights.hf5')

# use model.fit to continue training.

share|improve this answer

answered Mar 20 at 13:23

MachineLearnerMachineLearner

32410

New contributor

MachineLearner is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

1

$begingroup$

In order to continue the learning process, you will need to use checkpoints.

# source: https://stackoverflow.com/questions/36356004/continue-training-from-a-specific-epoch
weight_save_callback = ModelCheckpoint('/path/to/weights.epoch:02d-val_loss:.2f.hdf5', monitor='val_loss', verbose=0, save_best_only=False, mode='auto')
model.fit(X_train,y_train,batch_size=batch_size,nb_epoch=nb_epoch,callbacks=[weight_save_callback])

# load model
model = Sequential()
model.add(...)
model.load('path/to/weights.hf5')

# use model.fit to continue training.

share|improve this answer

answered Mar 20 at 13:23

MachineLearnerMachineLearner

32410

New contributor

MachineLearner is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

$begingroup$

In order to continue the learning process, you will need to use checkpoints.

# source: https://stackoverflow.com/questions/36356004/continue-training-from-a-specific-epoch
weight_save_callback = ModelCheckpoint('/path/to/weights.epoch:02d-val_loss:.2f.hdf5', monitor='val_loss', verbose=0, save_best_only=False, mode='auto')
model.fit(X_train,y_train,batch_size=batch_size,nb_epoch=nb_epoch,callbacks=[weight_save_callback])

# load model
model = Sequential()
model.add(...)
model.load('path/to/weights.hf5')

# use model.fit to continue training.

share|improve this answer

answered Mar 20 at 13:23

MachineLearnerMachineLearner

32410

New contributor

MachineLearner is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

# source: https://stackoverflow.com/questions/36356004/continue-training-from-a-specific-epoch
weight_save_callback = ModelCheckpoint('/path/to/weights.epoch:02d-val_loss:.2f.hdf5', monitor='val_loss', verbose=0, save_best_only=False, mode='auto')
model.fit(X_train,y_train,batch_size=batch_size,nb_epoch=nb_epoch,callbacks=[weight_save_callback])

# load model
model = Sequential()
model.add(...)
model.load('path/to/weights.hf5')

# use model.fit to continue training.

share|improve this answer

answered Mar 20 at 13:23

MachineLearnerMachineLearner

32410

New contributor

MachineLearner is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

answered Mar 20 at 13:23

MachineLearnerMachineLearner

32410

New contributor

MachineLearner is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

answered Mar 20 at 13:23

MachineLearnerMachineLearner

32410