how to test the pretrained model on the dataset?

[yayeoCddy]

you have released codes about how to train and how to make a demo..
but how we evaluate the pretrained model?I have found ./demo/birds-eval.yml and downloaded the pre-trained model birds_model_164000.ckpt in ./model
meanwhile, the test CUB dataset have produced by the prepocess_birds.py, such as char-CNN-RNN-embedding.pickle, filenames.pickle, but the file *.txt and *.t7 are needed in birds_demo.sh..

so how to test the pretrained stackedGAN?

[tejas-gokhale]

I am facing the same issue even after training on my own. The *.t7 files are missing and so I cannot test it.

[thak123]

Did anyone find the *,t7 files

[ningning32]

@thak123 add torch is necessary

[namrathadeepthi]

Facing the same issue, example_captions.t7 is missing. Where is it?

[ningning32]

Have you installed the Torch ? i fixed this question by checking the bird_demo.sh line .13. ----- th get_embedding.lua , so i install Torch and get the example_captions.t7 At 2018-04-14 18:59:14, "namrathadeepthi" <[email protected]> wrote: Facing the same issue, example_captions.t7 is missing. Where is it? — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or mute the thread.

[ast1997]

i can't find the example_captions.t7 file. Can anyone help me out

[vigneshdurairaj]

@ast1997 you have to download torch and compile the get_embeddings.lua file to get the example_captions.t7 file.

use this resource to install torch: http://torch.ch/docs/getting-started.html#_
and if you have ubuntu 18.04 and cuda 10 go this source directly because the version given in the official torch repo is not compatible with cuda 10: nagadomi/waifu2x#253 (comment)