Ying Shen

icon indicating a website link https://yingshen-ys.github.io/

icon company University of Illinois Urbana-Champaign icon location I am a Ph.D. student interested in Multimodal Machine Learning, Natural Language Processing, Computer Vision, Generative Models, and Deep Learning.

Results 5 comments of Ying Shen

Different vocab size between `data.vocab` and `embs_ann`?

> Hi @yingShen-ys, any idea whether such discrepancy exists in the following cases: > > * If you train a new model using our code > * In pretrained models...

Much higher scores when evaluating Episodic Transformer baselines for EDH instances

> Hi @yingShen-ys > > That sounds like a reasonable result. I will leave the issue open however, so that we can see if others are able to reproduce it....

Mapping between the example in `annotations.jsonl` and `physical-interaction-tfrecords`

> Hi Ying, > > If you want the images, I think you might have to do a matching -- but hopefully there's info in there that should help, including...

RunTime Error of metric 'scene', when decoding with BertLMHeadModel

@yinanhe I met the same problem as well. And I am using transformers==4.33.2

RunTime Error of metric 'scene', when decoding with BertLMHeadModel

> [@yingShen-ys](https://github.com/yingShen-ys) Hello, after testing, the transformers in version 4.33.2 can perform normal inference. You can refer to this issue [xinyu1205/recognize-anything#218](https://github.com/xinyu1205/recognize-anything/issues/218). @yinanhe Thank you for the help! I also encountered...