Replies: 2 comments 2 replies
-
For Deep Clustering, we don't have native support yet. It shouldn't be
hard, and we should have done it for a while already.
Why do you fail to load the yaml file? It's in your experiment folder.
Le mar. 8 juin 2021 à 14:04, hananbo26 ***@***.***> a écrit :
… I have trained the Deep Clustering model but I don't know how can I load
it.
I use this function to load:
model = torch_utils.load_state_dict_in(checkpoint["state_dict"], model)
and this function to get the model:
model, _ = make_model_and_optimizer(conf),
But the later requires parsing the conf.yaml file, which I fail to do.
Is there an easiest way to load a trained model?
Thanks,
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#513>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/AEND2HERWBHYV6BXOU3BPHDTRYBNXANCNFSM46JZRXVA>
.
|
Beta Was this translation helpful? Give feedback.
1 reply
-
You should not build the parser etc.. Just load the file and instantiate
the model with it.
Le mar. 8 juin 2021 à 16:23, hananbo26 ***@***.***> a écrit :
… Thanks for the answer,
I succeeded in loading the yaml file but fail to parse it.
Attaching a screenshot of my code with the error message.
[image: screenshot]
<https://user-images.githubusercontent.com/18651755/121202382-eac24700-c87d-11eb-9a78-80dcfe5f3fe8.png>
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#513 (reply in thread)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AEND2HBAIMH367P3T6PBBRLTRYRVHANCNFSM46JZRXVA>
.
|
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I have trained the Deep Clustering model but I don't know how can I load it.
I use this function to load:
model = torch_utils.load_state_dict_in(checkpoint["state_dict"], model)
and this function to get the model:
model, _ = make_model_and_optimizer(conf),
But the later requires parsing the conf.yaml file, which I fail to do.
Is there an easiest way to load a trained model?
Thanks,
Beta Was this translation helpful? Give feedback.
All reactions