Why do I need pre-trained weights in transfer learning? The 2019 Stack Overflow Developer Survey Results Are InRight way to Fine Tune - Train a fully connected layer as a separate stepWhy is vanishing gradient a problem?What is the different between Fine-tuning and Transfer-learning?Fine tuning accuracy lower than Raw Transfer Learning AccuracyType of images used to train a neural networkWhere to find pre-trained models for transfer learningDifficulty in choosing Hyperparameters for my CNNHow to properly mean-center my dataWhy is the GoogLeNet retrained model size less compared to others?Does it make sense to train a convolutional neural network on lo-res, use on hi-res pictures?
Variable with quotation marks "$()"
Accepted by European university, rejected by all American ones I applied to? Possible reasons?
Do working physicists consider Newtonian mechanics to be "falsified"?
Word for: a synonym with a positive connotation?
What force causes entropy to increase?
Why can't wing-mounted spoilers be used to steepen approaches?
How did passengers keep warm on sail ships?
Is it ethical to upload a automatically generated paper to a non peer-reviewed site as part of a larger research?
How do spell lists change if the party levels up without taking a long rest?
Humiliated in front of employees
Does Parliament need to approve the new Brexit delay to 31 October 2019?
For what reasons would an animal species NOT cross a *horizontal* land bridge?
Button changing its text & action. Good or terrible?
Why are Marketing Cloud timestamps not stored in the same timezone as Sales Cloud?
Do I have Disadvantage attacking with an off-hand weapon?
Merge multiple DataFrames Pandas
How to read αἱμύλιος or when to aspirate
Why can't devices on different VLANs, but on the same subnet, communicate?
Circular reasoning in L'Hopital's rule
Identify 80s or 90s comics with ripped creatures (not dwarves)
How to politely respond to generic emails requesting a PhD/job in my lab? Without wasting too much time
Using `min_active_rowversion` for global temporary tables
Do ℕ, mathbbN, BbbN, symbbN effectively differ, and is there a "canonical" specification of the naturals?
Is it ok to offer lower paid work as a trial period before negotiating for a full-time job?
Why do I need pre-trained weights in transfer learning?
The 2019 Stack Overflow Developer Survey Results Are InRight way to Fine Tune - Train a fully connected layer as a separate stepWhy is vanishing gradient a problem?What is the different between Fine-tuning and Transfer-learning?Fine tuning accuracy lower than Raw Transfer Learning AccuracyType of images used to train a neural networkWhere to find pre-trained models for transfer learningDifficulty in choosing Hyperparameters for my CNNHow to properly mean-center my dataWhy is the GoogLeNet retrained model size less compared to others?Does it make sense to train a convolutional neural network on lo-res, use on hi-res pictures?
$begingroup$
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
$endgroup$
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
$endgroup$
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
$endgroup$
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
deep-learning cnn transfer-learning
edited Apr 1 at 4:11
Ethan
701625
701625
asked Mar 31 at 22:20
BadumBadum
487
487
add a comment |
add a comment |
2 Answers
2
active
oldest
votes
$begingroup$
When you are calling a pre-trained model (resnet50 in your case) for performing transfer learning, only the model's architecture is actually called.
This architecture is practically useless to perform any sort of computational operation on the data and predicting any output unless trained. For that, you will need the weights (variables understood by the model on some previous dataset).
Weights are more like mathematical coefficients which take the input and performs the computation on the input to generate a required output. They are more like the coefficient in a linear algebra problem. This is the actual reason why it is required to call the weights for the model.
Even if you are not calling any weights in you model, you can make your model trainable and train the same to generate your own weights that fit your data properly rather than fine-tuning your model. Read more about the same here
$endgroup$
add a comment |
$begingroup$
You need pre-trained 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 transfer learning consists of 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 reasons for using 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
$endgroup$
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
);
);
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%2fdatascience.stackexchange.com%2fquestions%2f48317%2fwhy-do-i-need-pre-trained-weights-in-transfer-learning%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
2 Answers
2
active
oldest
votes
2 Answers
2
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
When you are calling a pre-trained model (resnet50 in your case) for performing transfer learning, only the model's architecture is actually called.
This architecture is practically useless to perform any sort of computational operation on the data and predicting any output unless trained. For that, you will need the weights (variables understood by the model on some previous dataset).
Weights are more like mathematical coefficients which take the input and performs the computation on the input to generate a required output. They are more like the coefficient in a linear algebra problem. This is the actual reason why it is required to call the weights for the model.
Even if you are not calling any weights in you model, you can make your model trainable and train the same to generate your own weights that fit your data properly rather than fine-tuning your model. Read more about the same here
$endgroup$
add a comment |
$begingroup$
When you are calling a pre-trained model (resnet50 in your case) for performing transfer learning, only the model's architecture is actually called.
This architecture is practically useless to perform any sort of computational operation on the data and predicting any output unless trained. For that, you will need the weights (variables understood by the model on some previous dataset).
Weights are more like mathematical coefficients which take the input and performs the computation on the input to generate a required output. They are more like the coefficient in a linear algebra problem. This is the actual reason why it is required to call the weights for the model.
Even if you are not calling any weights in you model, you can make your model trainable and train the same to generate your own weights that fit your data properly rather than fine-tuning your model. Read more about the same here
$endgroup$
add a comment |
$begingroup$
When you are calling a pre-trained model (resnet50 in your case) for performing transfer learning, only the model's architecture is actually called.
This architecture is practically useless to perform any sort of computational operation on the data and predicting any output unless trained. For that, you will need the weights (variables understood by the model on some previous dataset).
Weights are more like mathematical coefficients which take the input and performs the computation on the input to generate a required output. They are more like the coefficient in a linear algebra problem. This is the actual reason why it is required to call the weights for the model.
Even if you are not calling any weights in you model, you can make your model trainable and train the same to generate your own weights that fit your data properly rather than fine-tuning your model. Read more about the same here
$endgroup$
When you are calling a pre-trained model (resnet50 in your case) for performing transfer learning, only the model's architecture is actually called.
This architecture is practically useless to perform any sort of computational operation on the data and predicting any output unless trained. For that, you will need the weights (variables understood by the model on some previous dataset).
Weights are more like mathematical coefficients which take the input and performs the computation on the input to generate a required output. They are more like the coefficient in a linear algebra problem. This is the actual reason why it is required to call the weights for the model.
Even if you are not calling any weights in you model, you can make your model trainable and train the same to generate your own weights that fit your data properly rather than fine-tuning your model. Read more about the same here
answered Apr 1 at 10:32
thanatozthanatoz
603421
603421
add a comment |
add a comment |
$begingroup$
You need pre-trained 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 transfer learning consists of 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 reasons for using 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
$endgroup$
add a comment |
$begingroup$
You need pre-trained 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 transfer learning consists of 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 reasons for using 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
$endgroup$
add a comment |
$begingroup$
You need pre-trained 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 transfer learning consists of 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 reasons for using 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
$endgroup$
You need pre-trained 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 transfer learning consists of 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 reasons for using 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
edited Apr 1 at 12:17
Blenzus
16410
16410
answered Apr 1 at 2:37
Pedro Henrique MonfortePedro Henrique Monforte
412112
412112
add a comment |
add a comment |
Thanks for contributing an answer to Data Science Stack Exchange!
- 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.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
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%2fdatascience.stackexchange.com%2fquestions%2f48317%2fwhy-do-i-need-pre-trained-weights-in-transfer-learning%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