Abhishek Das

Results 21 comments of Abhishek Das

Thanks @sourabhtk37, good catch! Unfortunately, I no longer have the bandwidth to maintain this project :/ (I should probably mention that in the readme.) If you could send in a...

Thanks for trying it out @Mr-Lopes! This is great, if you could send a quick PR with these fixes, I'm happy to merge them.

Yup, sounds good!

Do you have `data.t7`, `answers_vocab.t7`, and `questions_vocab.t7` in the `data/` folder and the model checkpoint in the `checkpoints/` folder? (Download links given [here](https://github.com/abhshkdz/neural-vqa#pretrained-model-and-data-files)).

That's odd. It seems like a path issue. Line 47 is `local data = torch.load(tensor_file)`. If you `th` and `torch.load('data/data.t7')`, do you get the same error?

Thanks. Same error. How about `torch.load('data/data.t7', 'binary')`?

Thanks. [Seems like](https://github.com/cmusatyalab/openface/issues/42) an architecture issue. Could you try downloading `data.ascii.t7` from [here](https://computing.ece.vt.edu/~abhshkdz/data.ascii.t7). And then try `torch.load('data/data.ascii.t7', 'ascii')`.

Strange! The [documentation](https://github.com/torch/torch7/blob/master/doc/serialization.md) suggests `ascii` should be readable. Not sure what the issue is. You might want to try asking on the Torch group: https://groups.google.com/forum/#!forum/torch7.

Hey @yadavankit, `data.t7` looks fine. The error looks like you're using `luajit`, the checkpoint was created using lua5.1 ([ref](https://github.com/torch/distro#lua-and-torch)).