Learn More
Resend Email
1
AvatarOfKaine
3y

You know it is not acceptable to not finally answer this goddamn question for myself or with some help !

PyTorch is driving me insane !
I follow the goddamn docs, practically just created a copy of the sample for the training portion, even if my design were to suck, the training steps SHOULD change the model parameters right ?

so if I do a...

model.parameters().clone() before training
and mode.parameters().clone() after training

torch.equal(p1.data,p2.data) should be false right ????

question
Favorite
Ranter
Comments
  • 1
    3y
    If you just want to use a model, wouldn’t tensorflow be better? I haven’t been using ML since 2019 but I used pytorch instead of tf because I have to create a complex modification of an existing model
  • 1
    3y
    @devTea no idea but torch seemed better and tf doesn’t run on my machine lol

    Their instructions are so simple !!!
  • 1
    3y
    @devTea and hey in essence we had this conversation before so of course you know what this preceded heh

    Care to point out what is wrong ?
  • 1
    3y
    @AvatarOfKaine I’ve checked out the gist, but I’ve forgotten how to use it

    Sorry I couldn’t help much
  • 1
    3y
    @devTea :(
  • 1
    3y
    @devTea I want my model train set to work but the tracks aren’t connected right and it keeps derailing :(
devRant © 2021 Hexical Labs LLC
Privacy Policy  |  Terms of Service
Add Comment