LISA

LISA copied to clipboard

Segmentation Performance Evaluation Result is significantly different than paper gIoU:60.0 cIoU:67.8 vs gIoU:0.0759 cIoU:0.0648

5

Hi @X-Lai, @tianzhuotao, @yukang2017, @yanwei-li , @xbkaishui I am evaluating your method with your provided model (xinlai/LISA-13B-llama2-v1) as a part of my research studies. I see the significant difference between...

ssablak

Token indices sequence length is longer than the specified maximum sequence length for this model (565 > 512). Running this sequence through the model will result in indexing errors

1

I am trying to retrain the LISA with 7B model, I encounter such warning: Token indices sequence length is longer than the specified maximum sequence length for this model (565...

Roberyan

Is LISA model on Hugginface?

2

Hi there! I'm exploring whether LISA is available on Hugging Face. I came across one link [here](https://huggingface.co/xinlai/LISA-13B-llama2-v0-explanatory), but unfortunately, there's no description provided. My interest lies in Hugging Face because...

gauravsh0812

Which file is the lora weight?

3

Hi, Great work! I was wondering what is the difference between different model files, like `bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt`, `mp_rank_00_model_states.pt`, `pytorch_model.bin` which is obtained after the `zero_to_fp32.py`, and the file obtained after `merge_lora_weights_and_save_hf_model.py`....

hxx-who

Hi, Thanks for such a great and interesting work. I would like to ask how long it takes to infer a picture in the refcocog dataset using Lisa-7b on a...

Yting68

Availability of ReasonSeg Testing Set

5

Hi Thank you for your impressive work. In order to reproduce the results of your paper and do further research. Could you let me know if the testing set of...

wangjunchi

Comparison with GroundedDINO

1

Dear author, Thank you for your significant contribution to the community; the performance of your model is truly impressive. I am curious to know if you have considered replacing the...

Yebulabula

AttributeError: 'NoneType' object has no attribute 'shape'

9

Hi, thank you for your excellent work. I trained my own lisa model and merged the weights. But when i try to run the chat.py for inference, the error occured...

Ringhu

Token indices sequence length is longer than the specified maximum sequence length for this model (XXX > 512). Running this sequence through the model will result in indexing errors

3

During training the model, I frequently receive the following warning: `Token indices sequence length is longer than the specified maximum sequence length for this model (590 > 512). Running this...

meincv

No output segmentation image when running chat.py

2

Hi, when running chat.py, I can get the text response, but the shape of the mask is [0, 1, x, x], how can I fix it? Thanks in advance!

Derek0907