-
try all .yaml files in INPUT_CONFIG.
PATH_DATA = 'data'
PATH_MODELS = 'output/vlqa_POLYP_2024_05_04_17_16_50/model_final.pth'
TRAIN = 'false'
INPUT_CONFIG = 'output/vlqa_POLYP_2024_05_04_17…
-
Hi team, thanks for you great work!
I am trying to replace vision tower with DINOv2 which is provided in tinyllava-factory scripts. But have anyone evaluted its performance?
-
Generate the dataloaders for the following datasets.
saint.___.: coyo-dataset on mini-gpt.
@snat-s: OKVQA, VQA-V2
We need some help with the following:
Multimodal C4.
Classic C4.
Conceptual…
-
Hi Team,
We are trying to evaulate image captioning for peir gross, we are getting the below error. Similar issue has been reported earlier, zer-shot has been suggested, for image captioning it is …
-
I faced following error when evaluating on SAL TextVQA
```
assert self.PAD_IDX != self.answer_vocab.UNK_INDEX
AssertionError
```
It ran without error when I change the vocab file from fixed_answe…
-
Hello,
Thank you for your work. I am interested in creating custom instruction data and I wonder if you will release the code to obtain the data for "open-llava-next_instruct_mix1M.json"?
I have…
-
### DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
- [X] I understand that I will be **blocked** if I *intentionally* remove or skip any mandatory\* field
### Checklist
- [X] I'm requesting a site-specif…
-
Updating taggui to the latest state of the main branch and also making sure that `requirements.txt` are installed I'm now trying to use `THUDM/cogagent-vqa-hf` but I get this message:
```
Loading TH…
-
I'm honored to learn about such an excellent work. Could you please provide me with the training set or a link to the training set for VQA-Med-2021?
-
(tested with http://localhost:8000/ui/color)
With the Blip-vqa-base method, the Warning messages for black&white or grayscale images seem wrong:
* color image: warning "image is in b/w or grayscale"…