Common class for Linear, Conv1d, Conv2d,…, LSTM,When should you use a class vs a struct in C++?*.h or *.hpp for your class definitionsUse 'class' or 'typename' for template parameters?How to call a parent class function from derived class function?Meaning of 'const' last in a function declaration of a class?error: request for member '..' in '..' which is of non-class typeConstexpr class: Inheritance?Checking template parameter inheritance with SFINAEHow to correctly give inputs to Embedding, LSTM and Linear layers in PyTorch?pytorch - Where is “conv1d” implemented?
Why should there be two solutions for each parameter of likelihood ratio equation for Weibull-distribution?
Can I get a PhD for developing an educational software?
Higman's lemma and a manuscript of Erdős and Rado
Can you board the plane when your passport is valid less than 3 months?
Count the number of paths to n
Was the Boeing 2707 design flawed?
How to prevent a hosting company from accessing a VM's encryption keys?
Semantic difference between regular and irregular 'backen'
How much does Commander Data weigh?
How should i charge 3 lithium ion batteries?
Did Dr. Hannibal Lecter like Clarice or attracted towards her?
Prevent use of CNAME record for untrusted domain
If the Shillelagh cantrip is applied to a club with non-standard damage dice, what is the resulting damage dice?
Why is getting a PhD considered "financially irresponsible"?
What happened to the HDEV ISS Experiment? Is it over?
Can an Arcane Focus be embedded in one's body?
Number of academics in various EU countries
Tex Quotes(UVa 272)
When, exactly, does the Rogue Scout get to use their Skirmisher ability?
Retroactively modifying humans for Earth?
Breaker Mapping Questions
Can Orcus use Multiattack with any melee weapon?
Unlock your Lock
Why is strlen so complex in C?
Common class for Linear, Conv1d, Conv2d,…, LSTM,
When should you use a class vs a struct in C++?*.h or *.hpp for your class definitionsUse 'class' or 'typename' for template parameters?How to call a parent class function from derived class function?Meaning of 'const' last in a function declaration of a class?error: request for member '..' in '..' which is of non-class typeConstexpr class: Inheritance?Checking template parameter inheritance with SFINAEHow to correctly give inputs to Embedding, LSTM and Linear layers in PyTorch?pytorch - Where is “conv1d” implemented?
.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty margin-bottom:0;
Is there any class that all torch::nn::Linear, torch::nn::Conv1d, torch::nn::Conv2d, ... torch::nn::GRU, .... all inherit from that? torch::nn::Module seems be a good option, though there is a middle class, called torch::nn::Cloneable, so that torch::nn::Module does not work. Also, torch::nn::Cloneable itself is a template so that needs type in the declaration.
I want to create a general class model, which has std::vector<the common class> layers, so that later I can fill layers with any type of layer that I want, e.g., Linear, LSTM, etc. Is there such a capability in the current API? This can be done easily in python, though here we need declaration and this hinders the python's easiness.
Thanks,
Afshin
c++ pytorch libtorch
asked Mar 18 at 14:31
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
add a comment |
Is there any class that all torch::nn::Linear, torch::nn::Conv1d, torch::nn::Conv2d, ... torch::nn::GRU, .... all inherit from that? torch::nn::Module seems be a good option, though there is a middle class, called torch::nn::Cloneable, so that torch::nn::Module does not work. Also, torch::nn::Cloneable itself is a template so that needs type in the declaration.
I want to create a general class model, which has std::vector<the common class> layers, so that later I can fill layers with any type of layer that I want, e.g., Linear, LSTM, etc. Is there such a capability in the current API? This can be done easily in python, though here we need declaration and this hinders the python's easiness.
Thanks,
Afshin
c++ pytorch libtorch
asked Mar 18 at 14:31
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
add a comment |
Is there any class that all torch::nn::Linear, torch::nn::Conv1d, torch::nn::Conv2d, ... torch::nn::GRU, .... all inherit from that? torch::nn::Module seems be a good option, though there is a middle class, called torch::nn::Cloneable, so that torch::nn::Module does not work. Also, torch::nn::Cloneable itself is a template so that needs type in the declaration.
I want to create a general class model, which has std::vector<the common class> layers, so that later I can fill layers with any type of layer that I want, e.g., Linear, LSTM, etc. Is there such a capability in the current API? This can be done easily in python, though here we need declaration and this hinders the python's easiness.
Thanks,
Afshin
c++ pytorch libtorch
asked Mar 18 at 14:31
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
Is there any class that all torch::nn::Linear, torch::nn::Conv1d, torch::nn::Conv2d, ... torch::nn::GRU, .... all inherit from that? torch::nn::Module seems be a good option, though there is a middle class, called torch::nn::Cloneable, so that torch::nn::Module does not work. Also, torch::nn::Cloneable itself is a template so that needs type in the declaration.
I want to create a general class model, which has std::vector<the common class> layers, so that later I can fill layers with any type of layer that I want, e.g., Linear, LSTM, etc. Is there such a capability in the current API? This can be done easily in python, though here we need declaration and this hinders the python's easiness.
Thanks,
Afshin
c++ pytorch libtorch
c++ pytorch libtorch
asked Mar 18 at 14:31
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
asked Mar 18 at 14:31
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
asked Mar 18 at 14:31
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
asked Mar 18 at 14:31
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
asked Mar 18 at 14:31
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
5479 silver badges21 bronze badges
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
I found that nn::sequential can be used for a this purpose, and it does not need a forward implementation, which can be a positive point and at a same time a negative point. nn::sequential already requires each module to have a forward implementation, and calls the forward functions in a sequence that they have added in. So, one cannot create an ad-hock non-usual forward pass like Dense-Net with that, though it is good enough for general usages.
In addition, it seems that nn::sequential just uses a std::vector<nn::AnyModule> as its underlying module list. So, std::vector<nn::AnyModule> also might be used.
answered Mar 27 at 20:01
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
add a comment |
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
);
);
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%2f55223728%2fcommon-class-for-linear-conv1d-conv2d-lstm%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
I found that nn::sequential can be used for a this purpose, and it does not need a forward implementation, which can be a positive point and at a same time a negative point. nn::sequential already requires each module to have a forward implementation, and calls the forward functions in a sequence that they have added in. So, one cannot create an ad-hock non-usual forward pass like Dense-Net with that, though it is good enough for general usages.
In addition, it seems that nn::sequential just uses a std::vector<nn::AnyModule> as its underlying module list. So, std::vector<nn::AnyModule> also might be used.
answered Mar 27 at 20:01
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
add a comment |
I found that nn::sequential can be used for a this purpose, and it does not need a forward implementation, which can be a positive point and at a same time a negative point. nn::sequential already requires each module to have a forward implementation, and calls the forward functions in a sequence that they have added in. So, one cannot create an ad-hock non-usual forward pass like Dense-Net with that, though it is good enough for general usages.
In addition, it seems that nn::sequential just uses a std::vector<nn::AnyModule> as its underlying module list. So, std::vector<nn::AnyModule> also might be used.
answered Mar 27 at 20:01
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
add a comment |
I found that nn::sequential can be used for a this purpose, and it does not need a forward implementation, which can be a positive point and at a same time a negative point. nn::sequential already requires each module to have a forward implementation, and calls the forward functions in a sequence that they have added in. So, one cannot create an ad-hock non-usual forward pass like Dense-Net with that, though it is good enough for general usages.
In addition, it seems that nn::sequential just uses a std::vector<nn::AnyModule> as its underlying module list. So, std::vector<nn::AnyModule> also might be used.
answered Mar 27 at 20:01
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
I found that nn::sequential can be used for a this purpose, and it does not need a forward implementation, which can be a positive point and at a same time a negative point. nn::sequential already requires each module to have a forward implementation, and calls the forward functions in a sequence that they have added in. So, one cannot create an ad-hock non-usual forward pass like Dense-Net with that, though it is good enough for general usages.
In addition, it seems that nn::sequential just uses a std::vector<nn::AnyModule> as its underlying module list. So, std::vector<nn::AnyModule> also might be used.
answered Mar 27 at 20:01
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
answered Mar 27 at 20:01
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
answered Mar 27 at 20:01
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
answered Mar 27 at 20:01
Afshin OroojlooyAfshin Oroojlooy
5479 silver badges21 bronze badges
5479 silver badges21 bronze badges
add a comment |
add a comment |
Got a question that you can’t ask on public Stack Overflow? Learn more about sharing private information with Stack Overflow for Teams.
Got a question that you can’t ask on public Stack Overflow? Learn more about sharing private information with Stack Overflow for Teams.
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.
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%2f55223728%2fcommon-class-for-linear-conv1d-conv2d-lstm%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
