WisconsinAIVision/ViP-LLaVA issues and pull requests

#33 - [Usage] How to submit the results to the evaluation server

Issue - State: open - Opened by ssbhxlj about 1 month ago

#32 - [Usage] How to run GPT4RoI on the ViP benchmark

Issue - State: closed - Opened by geshang777 about 1 month ago

#31 - [Usage] Tokenization Mismatch

Issue - State: open - Opened by mzamini92 3 months ago - 1 comment

#30 - [Feature request] When the training dataset release

Issue - State: open - Opened by JustinKai0527 3 months ago - 1 comment

#29 - [Usage] Pretrain stage did not save all required files

Issue - State: open - Opened by james20141606 3 months ago - 1 comment

#28 - [Question] The demo collapse

Issue - State: open - Opened by JustinKai0527 4 months ago - 3 comments

#27 - [Discussion] information leakage while intaking the conversition?

Issue - State: open - Opened by james20141606 4 months ago - 1 comment

#26 - [Usage] pip install issue

Issue - State: open - Opened by JustinKai0527 4 months ago - 1 comment

#25 - @mu-cai thanks for replying, here is my pip list I run your install guideline

Issue - State: closed - Opened by JustinKai0527 4 months ago

#24 - [Usage] can't do the gradio demo install error

Issue - State: open - Opened by JustinKai0527 4 months ago - 4 comments

#23 - Is it better to breakdown one image's different boxes into multiple questions?[Question]

Issue - State: open - Opened by james20141606 5 months ago - 3 comments

#22 - [Usage] Unfixed Random Seed and Get the Different Result in each Experiments

Issue - State: open - Opened by ia-gu 5 months ago - 1 comment

#21 - Update README.md

Pull Request - State: closed - Opened by nguyenvulong 5 months ago

#20 - Validation loss on pretraining?[Feature request]

Issue - State: open - Opened by james20141606 5 months ago - 6 comments

#19 - [Question] The checkpoint finetuned on RefCOCOg

Issue - State: open - Opened by zd11024 6 months ago - 2 comments

#18 - [Issue] Mismatch in tensor dimensions between 'input_ids' and 'output_ids' at the specified dimension.

Issue - State: open - Opened by tarekdawey 6 months ago - 2 comments

#17 - [Question] About Data Augmentation

Issue - State: closed - Opened by ia-gu 7 months ago - 4 comments

#16 - Release of Projector Weights

Issue - State: closed - Opened by YFCodeDream 7 months ago - 2 comments

#15 - [Question] Finetune Stage 2 Model

Issue - State: open - Opened by Xuefei98 8 months ago - 3 comments

#14 - [Question] Warning occurred when """model = LlavaLlamaForCausalLM.from_pretrained(model_path, low_cpu_mem_usage=True, **kwargs)""" in builder.py

Issue - State: closed - Opened by ia-gu 8 months ago - 2 comments

#13 - [Question] Can you provide register-specific instruction data with the help of GPT-4V?

Issue - State: closed - Opened by mary-0830 8 months ago - 2 comments

#12 - [Question] 请问这个文件怎么找不到了呢？convert_vipbench_for_eval.py

Issue - State: closed - Opened by mary-0830 8 months ago - 1 comment

#11 - [Usage] pre-requisites for multi-image and multi-prompt generation

Issue - State: open - Opened by sykverse 8 months ago - 3 comments

#10 - [Issue] Tensor mismatch at Runtime

Issue - State: open - Opened by RatraSahil 8 months ago - 5 comments

#9 - [Discussion] Unable to use the demo

Issue - State: open - Opened by ymmhcm 8 months ago - 6 comments

#8 - [Question] On the test set used for inference evaluation

Issue - State: open - Opened by mary-0830 9 months ago - 1 comment

#7 - Can u provide the subset only for ViP except llava mix original?

Issue - State: open - Opened by lucasjinreal 9 months ago - 5 comments

#6 - How to use visual prompts with huggingface?

Issue - State: closed - Opened by joshmyersdean 9 months ago - 3 comments

#5 - Training Stage

Issue - State: closed - Opened by 980044579 11 months ago

Ecosyste.ms: Issues

GitHub / WisconsinAIVision/ViP-LLaVA issues and pull requests