Aditya Bhattacharya

icon indicating a website link https://www.aditya-bhattacharya.net/

icon location India icon location I am primarily a technology explorer with deep interest in Data Science, Machine Learning and Artificial Intelligence. https://www.aditya-bhattacharya.net/

Results 7 comments of Aditya Bhattacharya

pretrained model can't be read

@sgrvinod @kpis-msa - Getting a similar issue. Is there a solution to this? Migrating to an old pytorch version will work here? ``` 772 unpickler = pickle_module.Unpickler(f, **pickle_load_args) 773 unpickler.persistent_load...

pretrained model can't be read

It seems that models.py is required to be in the same folder as the trained model while loading the pytorch model in the old way. This link was helpful for...

The questions about training

I solved the BLEU score 0, by pointing to the correct Test dataset. I had used the COCO Wordmap but using the Flickr8K Test Data. Pointing that to the correct...

caption.py strange output

Hey, how are you loading the pretrained models provided? @efacco I am getting this issue? Is it due to any PyTorch version problem? ``` 772 unpickler = pickle_module.Unpickler(f, **pickle_load_args) 773...

Weird result with your upload model and word map

@sgrvinod - Same issue I am seeing

transformers-based version of this repository

I will be interested for this as well!

Support for specifying a range during conditional sampling

Thanks @npatki for sharing the workaround code. Can such conditions be defined even before generating the samples? I think it would be better to have something like generate with conditions...