Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How to preprocess char-CNN-RNN? #12

Open
leeeeeeo opened this issue Apr 28, 2018 · 4 comments
Open

How to preprocess char-CNN-RNN? #12

leeeeeeo opened this issue Apr 28, 2018 · 4 comments

Comments

@leeeeeeo
Copy link

@hanzhanggit Hello!
Thank you for your contributions on this code.
I'm trying to train this on my own dataset.
I followed reedscot/icml2016, and trained a char-CNN-RNN text encoder.
But it's a .t7 file, not .pickle as your preprocessed char-CNN-RNN text embeddings.
So I'm wondering how to preprocess the char-CNN-RNN text embeddings to a .pickle file?
Thanks again for your contributions.
I'm looking forward to your reply!

@smallflyingpig
Copy link

maybe you can refer this code(https://github.com/taoxugit/AttnGAN). It is trained from scratch, including the text encoder and image encoder

@Liuhongzhi2018
Copy link

@hanzhanggit @leeeeeeo @smallflyingpig
I'm also trying to train this on COCO2017 datasets and need a file "char-CNN-RNN text embeddings.pickle". But from reedscot/icml2016, I only find .t7 files not .pickle. Could you tell me how to get char-CNN-RNN text embeddings.pickle from other datasets?
Thanks.

@saramahersalem
Copy link

saramahersalem commented Jul 12, 2019

@leeeeeeo @smallflyingpig @Liuhongzhi2018
I have my own dataset and i want to know how to get char-CNN-RNN text embeddings.pickle. have you got it?Could you tell me only steps?
I'm looking forward to your replies.
Thanks in advance.

@SreenijaK
Copy link

@saramahersalem did you figure out how to do the charCNNRNN text embeddings?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants