Loading legacy lua models fails in pytorch showing Spatial Convolution Layers has no bias
up vote
0
down vote
favorite
So I wanted to port this repositories DGAN code written in torch-lua to pytorch but for that I have to convert the model weights too since I don't have the computing power to train the model and want the exact same image generators. I tried using the load_lua
function in pytorch but it doesn't work.
Exact error on pytorch's Github issue
I also tried using several model converters from GitHub but they too throw the same error.
Note: I'm using the CPU weights from the repo for model conversion
Can anyone suggest a way for me to convert these pretrained models so that I can load them in pytorch or suggest something else?
python lua deep-learning pytorch
add a comment |
up vote
0
down vote
favorite
So I wanted to port this repositories DGAN code written in torch-lua to pytorch but for that I have to convert the model weights too since I don't have the computing power to train the model and want the exact same image generators. I tried using the load_lua
function in pytorch but it doesn't work.
Exact error on pytorch's Github issue
I also tried using several model converters from GitHub but they too throw the same error.
Note: I'm using the CPU weights from the repo for model conversion
Can anyone suggest a way for me to convert these pretrained models so that I can load them in pytorch or suggest something else?
python lua deep-learning pytorch
add a comment |
up vote
0
down vote
favorite
up vote
0
down vote
favorite
So I wanted to port this repositories DGAN code written in torch-lua to pytorch but for that I have to convert the model weights too since I don't have the computing power to train the model and want the exact same image generators. I tried using the load_lua
function in pytorch but it doesn't work.
Exact error on pytorch's Github issue
I also tried using several model converters from GitHub but they too throw the same error.
Note: I'm using the CPU weights from the repo for model conversion
Can anyone suggest a way for me to convert these pretrained models so that I can load them in pytorch or suggest something else?
python lua deep-learning pytorch
So I wanted to port this repositories DGAN code written in torch-lua to pytorch but for that I have to convert the model weights too since I don't have the computing power to train the model and want the exact same image generators. I tried using the load_lua
function in pytorch but it doesn't work.
Exact error on pytorch's Github issue
I also tried using several model converters from GitHub but they too throw the same error.
Note: I'm using the CPU weights from the repo for model conversion
Can anyone suggest a way for me to convert these pretrained models so that I can load them in pytorch or suggest something else?
python lua deep-learning pytorch
python lua deep-learning pytorch
asked 1 min ago
Aszen
11
11
add a comment |
add a comment |
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
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%2fstackoverflow.com%2fquestions%2f53139673%2floading-legacy-lua-models-fails-in-pytorch-showing-spatial-convolution-layers-ha%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