Rajaswa Patil
Rajaswa Patil
Hi, @gowtham1997 👋 Thanks for highlighting our work! The complete dataset and code is now available here: https://github.com/rajaswa/indic-syntax-evaluation Request to add this to the catalog @anoopkunchukuttan
you can change the kernel size = 2 for final layer of the discriminator and kernel size = 1 for generator. This will work for imagesize = 32
The ultimate usage can be something like this: ```python from decepticonlp import attacker from deceptionlp.transforms import transforms import torch from torch.uitls.data import Dataset #define adversarial transforms tfms = transforms.Compose( [...
This shall be a multi-step process, avoid limiting yourself to the above mentioned example functionalities and please feel free to discuss more functionalities.
Which one seems the better option: 1. Implement everything in crude way as shown in example above and then added logger, huggingface/nlp and other enhancements slowly over time 2. Start...
@Sharad24 can you provide some reference examples for these 'integration' type tests? Maybe from GenRL?
Sure. I can try and help. Meanwhile, we can add example scripts, if not tests? ``` examples/attacks/run_attack_imdb.py ```
Go ahead @parantak
This can be done. As of now, we are avoiding dependencies on pre-trained embeddings and any other thing that might require major dependencies and an active internet connection for the...
It'd be great if we have a source for this. It won't make sense putting efforts into something which won't be used eventually.