Hfrxdjt

Aggressive Under-Indexing and no data for missing index

What flight has the highest ratio of timezone difference to flight time?

Which one is the true statement?

Is there an equivalent of cd - for cp or mv

Can I calculate next year's exemptions based on this year's refund/amount owed?

Is there a reasonable and studied concept of reduction between regular languages?

Purpose of level-shifter with same in and out voltages

Point distance program written without a framework

Film where the government was corrupt with aliens, people sent to kill aliens are given rigged visors not showing the right aliens

Calculate the Mean mean of two numbers

What CSS properties can the br tag have?

free fall ellipse or parabola?

Getting Stale Gas Out of a Gas Tank w/out Dropping the Tank

Do scriptures give a method to recognize a truly self-realized person/jivanmukta?

Traveling with my 5 year old daughter (as the father) without the mother from Germany to Mexico

Is it convenient to ask the journal's editor for two additional days to complete a review?

TikZ: How to fill area with a special pattern?

IC has pull-down resistors on SMBus lines?

What is the difference between "hamstring tendon" and "common hamstring tendon"?

What would be the main consequences for a country leaving the WTO?

Players Circumventing the limitations of Wish

Can Sneak Attack be used when hitting with an improvised weapon?

Expressing the idea of having a very busy time

Help understanding this unsettling image of Titan, Epimetheus, and Saturn's rings?

Why do I need pre-trained weights in transfer learning?

0

$begingroup$

I am using a Mask-RCNN. I first chose the resnet50 backbone then downloaded COCO pre-trained weights.

Why do I need pre-trained weights for transfer learning?

The transfer learning approach is to train a base network and then copy its first layers of the target. My base network is resnet50 and I copied the first layers to Mask RCNN. So, why do I need pre-trained weights, for example, coco pre-trained weights?

I understand that I copy layers and pre-trained weights from resnet.

Thanks in advance.

deep-learning cnn transfer-learning

share|improve this question

edited 3 mins ago

Ethan

612324

asked 5 hours ago

BadumBadum

114

$endgroup$

add a comment | 

0

$begingroup$

I am using a Mask-RCNN. I first chose the resnet50 backbone then downloaded COCO pre-trained weights.

Why do I need pre-trained weights for transfer learning?

The transfer learning approach is to train a base network and then copy its first layers of the target. My base network is resnet50 and I copied the first layers to Mask RCNN. So, why do I need pre-trained weights, for example, coco pre-trained weights?

I understand that I copy layers and pre-trained weights from resnet.

Thanks in advance.

deep-learning cnn transfer-learning

share|improve this question

edited 3 mins ago

Ethan

612324

asked 5 hours ago

BadumBadum

114

$endgroup$

add a comment | 

$begingroup$

I am using a Mask-RCNN. I first chose the resnet50 backbone then downloaded COCO pre-trained weights.

Why do I need pre-trained weights for transfer learning?

The transfer learning approach is to train a base network and then copy its first layers of the target. My base network is resnet50 and I copied the first layers to Mask RCNN. So, why do I need pre-trained weights, for example, coco pre-trained weights?

I understand that I copy layers and pre-trained weights from resnet.

Thanks in advance.

deep-learning cnn transfer-learning

share|improve this question

edited 3 mins ago

Ethan

612324

asked 5 hours ago

BadumBadum

114

$endgroup$

share|improve this question

edited 3 mins ago

Ethan

612324

asked 5 hours ago

BadumBadum

114

share|improve this question

edited 3 mins ago

Ethan

612324

asked 5 hours ago

BadumBadum

114

edited 3 mins ago

Ethan

612324

edited 3 mins ago

Ethan

612324

asked 5 hours ago

BadumBadum

114

asked 5 hours ago

BadumBadum

114

1 Answer
1

active

oldest

votes

0

$begingroup$

You need pre-trainned weights for it to be Transfer Learning.

Copying layer structures is not transfer learning, it is just structuring a network inspired/copied from others.

The transferm learning lies in using pre-trained layers to construct a different network that migth have similarities in the first layers. That is usually useful for Deep Learning.

So the why's to use Transfer Learning are:

• You want to analyse something different in a dataset that was used to train another network




• You want to perform classification in a class that was used to train a certain network but was not annotated before




• You want to train a network for a problem similar to the other one and don't have time or computational power to retrain all layers

share|improve this answer

answered 1 hour ago

Pedro Henrique MonfortePedro Henrique Monforte

905

$endgroup$

add a comment | 

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%2f48317%2fwhy-do-i-need-pre-trained-weights-in-transfer-learning%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

0

$begingroup$

You need pre-trainned weights for it to be Transfer Learning.

Copying layer structures is not transfer learning, it is just structuring a network inspired/copied from others.

The transferm learning lies in using pre-trained layers to construct a different network that migth have similarities in the first layers. That is usually useful for Deep Learning.

So the why's to use Transfer Learning are:

• You want to analyse something different in a dataset that was used to train another network




• You want to perform classification in a class that was used to train a certain network but was not annotated before




• You want to train a network for a problem similar to the other one and don't have time or computational power to retrain all layers

share|improve this answer

answered 1 hour ago

Pedro Henrique MonfortePedro Henrique Monforte

905

$endgroup$

add a comment | 

0

$begingroup$

You need pre-trainned weights for it to be Transfer Learning.

Copying layer structures is not transfer learning, it is just structuring a network inspired/copied from others.

The transferm learning lies in using pre-trained layers to construct a different network that migth have similarities in the first layers. That is usually useful for Deep Learning.

So the why's to use Transfer Learning are:

• You want to analyse something different in a dataset that was used to train another network




• You want to perform classification in a class that was used to train a certain network but was not annotated before




• You want to train a network for a problem similar to the other one and don't have time or computational power to retrain all layers

share|improve this answer

answered 1 hour ago

Pedro Henrique MonfortePedro Henrique Monforte

905

$endgroup$

add a comment | 

$begingroup$

You need pre-trainned weights for it to be Transfer Learning.

Copying layer structures is not transfer learning, it is just structuring a network inspired/copied from others.

The transferm learning lies in using pre-trained layers to construct a different network that migth have similarities in the first layers. That is usually useful for Deep Learning.

So the why's to use Transfer Learning are:

• You want to analyse something different in a dataset that was used to train another network




• You want to perform classification in a class that was used to train a certain network but was not annotated before




• You want to train a network for a problem similar to the other one and don't have time or computational power to retrain all layers

share|improve this answer

answered 1 hour ago

Pedro Henrique MonfortePedro Henrique Monforte

905

$endgroup$

share|improve this answer

answered 1 hour ago

Pedro Henrique MonfortePedro Henrique Monforte

905

answered 1 hour ago

Pedro Henrique MonfortePedro Henrique Monforte

905

answered 1 hour ago

Pedro Henrique MonfortePedro Henrique Monforte

905