HanielF

Latest commit is 3 years ago, and the code relys on some packages such as urllib, cPickle, tensorflow, pytorch, cocoapi, whose version is incompatible with my environment. I also find...

I notice that butd output a 'npz' file corresponding to a single image. When i want to extract video caption based on xmodaler, it requires a global video feature. How...

MSVD dataset contains 1970 video clips, which is split into 1200(train set), 100(val set), 670(test set). While in what you provided in google drive, the number of video features and...

`> no suitable ctc data to write` when basecalling with `save-ctc` flag

2

Hi~ I am trying to train a bonito model from scratch. To obtain my training data, i basecalled the reads with the command as below: ```bash data_path="~/codes/bonito/data" key="Acinetobacter_baumannii_AYP-A2" bonito basecaller...

Why the attn mask is not used in forward function?

1

Compared with `left_product` function, attention mask is not used in `forward()` function. How to use the attention mask in the forward method?

Could you please upload the config file based on ViT Base for UFO/OneForAll

1

Thanks for your contribution to the development of the unified model. I notice that the config file for ViT base model is not uploaded. The model configuration described in the...

It's unnecessary to copy `~/optimus-switch/*` to `/etc/`. What's more, some executable files copied to `/usr/local/bin/` should only be kept with their basenames.