How do we compare different models performance
Clash Royale CLAN TAG#URR8PPP
.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty margin-bottom:0;
up vote
1
down vote
favorite
I am doing some research work regarding deep learning, I have a model and now I want to know and compare how my model performs as compared to others existing model.(like capsule networks, CNN ets..)
I have no idea of about how to evaluate model performance:-
Que 1. For how many epochs and for what batch size(lets say for mnist digits dataset) do I need to train my model?
Que 2. Is there any time condition to train my model, or I can train my model for same no of epochs as other models? Like lets say comparisons have been made after training models for 1 hour. Or is there any condition that I have to train my model for particular amount of time(like 1 hour)?
Que 3. What is the state of the art accuracy and error for mnist dataset today?
Que 4. How do we calculate error?
Thanks for helping :)
deep-learning model-comparison
New contributor
add a comment |Â
up vote
1
down vote
favorite
I am doing some research work regarding deep learning, I have a model and now I want to know and compare how my model performs as compared to others existing model.(like capsule networks, CNN ets..)
I have no idea of about how to evaluate model performance:-
Que 1. For how many epochs and for what batch size(lets say for mnist digits dataset) do I need to train my model?
Que 2. Is there any time condition to train my model, or I can train my model for same no of epochs as other models? Like lets say comparisons have been made after training models for 1 hour. Or is there any condition that I have to train my model for particular amount of time(like 1 hour)?
Que 3. What is the state of the art accuracy and error for mnist dataset today?
Que 4. How do we calculate error?
Thanks for helping :)
deep-learning model-comparison
New contributor
3
Possible duplicate of What are the current state-of-the-art convolutional neural networks?
â Sycorax
Oct 1 at 14:57
add a comment |Â
up vote
1
down vote
favorite
up vote
1
down vote
favorite
I am doing some research work regarding deep learning, I have a model and now I want to know and compare how my model performs as compared to others existing model.(like capsule networks, CNN ets..)
I have no idea of about how to evaluate model performance:-
Que 1. For how many epochs and for what batch size(lets say for mnist digits dataset) do I need to train my model?
Que 2. Is there any time condition to train my model, or I can train my model for same no of epochs as other models? Like lets say comparisons have been made after training models for 1 hour. Or is there any condition that I have to train my model for particular amount of time(like 1 hour)?
Que 3. What is the state of the art accuracy and error for mnist dataset today?
Que 4. How do we calculate error?
Thanks for helping :)
deep-learning model-comparison
New contributor
I am doing some research work regarding deep learning, I have a model and now I want to know and compare how my model performs as compared to others existing model.(like capsule networks, CNN ets..)
I have no idea of about how to evaluate model performance:-
Que 1. For how many epochs and for what batch size(lets say for mnist digits dataset) do I need to train my model?
Que 2. Is there any time condition to train my model, or I can train my model for same no of epochs as other models? Like lets say comparisons have been made after training models for 1 hour. Or is there any condition that I have to train my model for particular amount of time(like 1 hour)?
Que 3. What is the state of the art accuracy and error for mnist dataset today?
Que 4. How do we calculate error?
Thanks for helping :)
deep-learning model-comparison
deep-learning model-comparison
New contributor
New contributor
edited Oct 2 at 8:53
New contributor
asked Oct 1 at 8:31
Rishik
84
84
New contributor
New contributor
3
Possible duplicate of What are the current state-of-the-art convolutional neural networks?
â Sycorax
Oct 1 at 14:57
add a comment |Â
3
Possible duplicate of What are the current state-of-the-art convolutional neural networks?
â Sycorax
Oct 1 at 14:57
3
3
Possible duplicate of What are the current state-of-the-art convolutional neural networks?
â Sycorax
Oct 1 at 14:57
Possible duplicate of What are the current state-of-the-art convolutional neural networks?
â Sycorax
Oct 1 at 14:57
add a comment |Â
1 Answer
1
active
oldest
votes
up vote
2
down vote
accepted
Que 1. For how many epochs and for what batch size(lets say for mnist
digits dataset) do I need to train my model?
This depends on your model. Different models may perform differently when trained on different number of epochs, with different batch sizes. Basically, batch size, learning rate, dropout and other regularization methods all have some regularizing effect and interact with each other. They also interact with number of epochs needed to train the model (more regularization needs more training epochs).
Que 2. Is there any time condition to train my model, or I can train
my model for same no of epochs as other models? Like lets say
comparisons have been made after training models for 1 hour. Or is
there any condition that I have to train my model for particular
amount of time(like 1 hour)?
No, unless you want to make comparison under time restriction. Notice that this would need you to re-run all the other models in the same conditions as your model, since the results will vary a lot depending on the computational resources that were used by different authors. If you won't re-train the models, you wouldn't know if the results are due to having better (or worse) computational resources or using better model.
Que 3. What is the state of the art accuracy and error for mnist
dataset today?
You can find such results (with references) on LeCun's page on MINST or here.
Que 4. How do we calculate error?
Error rate is 1-accuracy, but accuracy is not the best measure of performance, so you should consider other measures as well.
As a comment, MINST is not a great benchmark since everyone trains on it, we probably have NN architectures that overfit to MINST.
add a comment |Â
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
up vote
2
down vote
accepted
Que 1. For how many epochs and for what batch size(lets say for mnist
digits dataset) do I need to train my model?
This depends on your model. Different models may perform differently when trained on different number of epochs, with different batch sizes. Basically, batch size, learning rate, dropout and other regularization methods all have some regularizing effect and interact with each other. They also interact with number of epochs needed to train the model (more regularization needs more training epochs).
Que 2. Is there any time condition to train my model, or I can train
my model for same no of epochs as other models? Like lets say
comparisons have been made after training models for 1 hour. Or is
there any condition that I have to train my model for particular
amount of time(like 1 hour)?
No, unless you want to make comparison under time restriction. Notice that this would need you to re-run all the other models in the same conditions as your model, since the results will vary a lot depending on the computational resources that were used by different authors. If you won't re-train the models, you wouldn't know if the results are due to having better (or worse) computational resources or using better model.
Que 3. What is the state of the art accuracy and error for mnist
dataset today?
You can find such results (with references) on LeCun's page on MINST or here.
Que 4. How do we calculate error?
Error rate is 1-accuracy, but accuracy is not the best measure of performance, so you should consider other measures as well.
As a comment, MINST is not a great benchmark since everyone trains on it, we probably have NN architectures that overfit to MINST.
add a comment |Â
up vote
2
down vote
accepted
Que 1. For how many epochs and for what batch size(lets say for mnist
digits dataset) do I need to train my model?
This depends on your model. Different models may perform differently when trained on different number of epochs, with different batch sizes. Basically, batch size, learning rate, dropout and other regularization methods all have some regularizing effect and interact with each other. They also interact with number of epochs needed to train the model (more regularization needs more training epochs).
Que 2. Is there any time condition to train my model, or I can train
my model for same no of epochs as other models? Like lets say
comparisons have been made after training models for 1 hour. Or is
there any condition that I have to train my model for particular
amount of time(like 1 hour)?
No, unless you want to make comparison under time restriction. Notice that this would need you to re-run all the other models in the same conditions as your model, since the results will vary a lot depending on the computational resources that were used by different authors. If you won't re-train the models, you wouldn't know if the results are due to having better (or worse) computational resources or using better model.
Que 3. What is the state of the art accuracy and error for mnist
dataset today?
You can find such results (with references) on LeCun's page on MINST or here.
Que 4. How do we calculate error?
Error rate is 1-accuracy, but accuracy is not the best measure of performance, so you should consider other measures as well.
As a comment, MINST is not a great benchmark since everyone trains on it, we probably have NN architectures that overfit to MINST.
add a comment |Â
up vote
2
down vote
accepted
up vote
2
down vote
accepted
Que 1. For how many epochs and for what batch size(lets say for mnist
digits dataset) do I need to train my model?
This depends on your model. Different models may perform differently when trained on different number of epochs, with different batch sizes. Basically, batch size, learning rate, dropout and other regularization methods all have some regularizing effect and interact with each other. They also interact with number of epochs needed to train the model (more regularization needs more training epochs).
Que 2. Is there any time condition to train my model, or I can train
my model for same no of epochs as other models? Like lets say
comparisons have been made after training models for 1 hour. Or is
there any condition that I have to train my model for particular
amount of time(like 1 hour)?
No, unless you want to make comparison under time restriction. Notice that this would need you to re-run all the other models in the same conditions as your model, since the results will vary a lot depending on the computational resources that were used by different authors. If you won't re-train the models, you wouldn't know if the results are due to having better (or worse) computational resources or using better model.
Que 3. What is the state of the art accuracy and error for mnist
dataset today?
You can find such results (with references) on LeCun's page on MINST or here.
Que 4. How do we calculate error?
Error rate is 1-accuracy, but accuracy is not the best measure of performance, so you should consider other measures as well.
As a comment, MINST is not a great benchmark since everyone trains on it, we probably have NN architectures that overfit to MINST.
Que 1. For how many epochs and for what batch size(lets say for mnist
digits dataset) do I need to train my model?
This depends on your model. Different models may perform differently when trained on different number of epochs, with different batch sizes. Basically, batch size, learning rate, dropout and other regularization methods all have some regularizing effect and interact with each other. They also interact with number of epochs needed to train the model (more regularization needs more training epochs).
Que 2. Is there any time condition to train my model, or I can train
my model for same no of epochs as other models? Like lets say
comparisons have been made after training models for 1 hour. Or is
there any condition that I have to train my model for particular
amount of time(like 1 hour)?
No, unless you want to make comparison under time restriction. Notice that this would need you to re-run all the other models in the same conditions as your model, since the results will vary a lot depending on the computational resources that were used by different authors. If you won't re-train the models, you wouldn't know if the results are due to having better (or worse) computational resources or using better model.
Que 3. What is the state of the art accuracy and error for mnist
dataset today?
You can find such results (with references) on LeCun's page on MINST or here.
Que 4. How do we calculate error?
Error rate is 1-accuracy, but accuracy is not the best measure of performance, so you should consider other measures as well.
As a comment, MINST is not a great benchmark since everyone trains on it, we probably have NN architectures that overfit to MINST.
edited Oct 1 at 13:53
answered Oct 1 at 8:59
Timâ¦
53.2k9120205
53.2k9120205
add a comment |Â
add a comment |Â
Rishik is a new contributor. Be nice, and check out our Code of Conduct.
Rishik is a new contributor. Be nice, and check out our Code of Conduct.
Rishik is a new contributor. Be nice, and check out our Code of Conduct.
Rishik is a new contributor. Be nice, and check out our Code of Conduct.
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
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstats.stackexchange.com%2fquestions%2f369560%2fhow-do-we-compare-different-models-performance%23new-answer', 'question_page');
);
Post as a guest
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
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
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
3
Possible duplicate of What are the current state-of-the-art convolutional neural networks?
â Sycorax
Oct 1 at 14:57