Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 11 months ago

MODERATORS

communick@academy.garden

[D] How to update the pytorch file (.pt) outside training?/ (alien.top)

submitted 10 months ago by rakk109@alien.top to c/machinelearning@academy.garden

3 comments fedilink hide all child comments

Hii,

suppose I have two .pt files and they have a common key results and I want to join the results values of the two file how do I do it??

eg:

test1.pt has 4 values : 1 ,2 ,3, 4
test2.pt has 3 values: 5 , 6 ,7
I want a test3.pt with values : 1, 2, 3 ,4, 5 ,6 ,7

Is this possible?? how can I accomplish this ??

top 3 comments

sorted by: hot top controversial new old

[–] im_datta0@alien.top 1 points 10 months ago (1 children)

Probably load the files, iterate over parameters using model.named_parameters() and add them to another tensor while you iterate?

[–] rakk109@alien.top 1 points 10 months ago

Model.named_parameters() are used to get the weights of all the parameters they don't provide any value as results(accuracies). So I obviously can't use that

[–] slashdave@alien.top 1 points 10 months ago

Nothing prevents you from loading two models from separate files in one piece of code and to combine them (in any fashion you choose) into a third model, which you can then save into a third file.