Giters

akshitac8 / tfvaegan

[ECCV 2020] Official Pytorch implementation for "Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification". SOTA results for ZSL and GZSL

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

performance about CUB dataset

YanYan0716 opened this issue · comments

commented

thanks for your work, i am very interest in this work,
when i download the code and try to train on CUB as you offered the features, but i think maybe i did not train it successful. i did not change any parameter， could you give me some idea about this situation

1624348069(1)

commented

thanks for your again

commented

is your environment setup correct? Did you change anything in the code?

commented

my pytorch.version=1.2.0
some API maybe different as your environment, so i have to change some code,
the important change such as :
Variable(XXX, requires_grad=False)
but i did not change others, such as models, loss function even any one of the hyperparameters
dose it matter?

or i need to using pytorch=0.3.1 to make it work?

commented

I know GAN but i am not familiar with VAE, so some knowledge in your paper is hard to understand for me. and i am learning it from your code....
thanks again for your reply

commented

yes, please maintain the same environment as mentioned in the readme to replicate the same results.

commented

@YanYan0716 is the issue solved?

commented

yes, i am sorry for my belated reply. and thanks for your enthusiasm.