lxtGH / lxtGH/OMG-Seg

【小白求助】Novice Seeking Help:Demo 可运行但结果与论文差异大,求复现成功的大佬分享 pip list( Demo Runs but Results Differ Greatly from Paper, Seeking pip list from Successful Reproducers)小白求助:与论文结果相差较大的原因

Open
#76 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.4k
Forks
55
PR merge metrics
No merged PRs in 30d

Description

# OMG-LLaVA seek for help
# OMG-LLaVA 结果求助

大家好~我是刚接触这个项目的小白,目前遇到了一个问题想向各位大佬求助。

我已成功运行项目中的 gradio demo,但实际输出结果与论文中公布的结果相差较大,关键指标(如准确率、误差值等,可根据项目补充具体指标)未能匹配。
经过初步排查,我推测问题可能出在依赖库版本不兼容上可能导致计算逻辑或结果精度差异。
想恳请已经成功复现论文结果的大佬,分享一下你们环境中的pip list输出内容,帮助我排查版本问题。如果有其他可能导致结果差异的建议,也欢迎随时指出~

非常感谢大家的帮助!

English Text
Hi everyone, I'm a novice new to this project and I'm encountering an issue that I hope to get help with from experts here.

I have successfully run the Demo in the project, but the actual output results differ greatly from those published in the paper. Key metrics (e.g., accuracy, error value, please supplement specific metrics based on the project) fail to match.
After preliminary investigation, I speculate that the problem may be caused by incompatible dependency library versions. Different versions of core libraries (such as PyTorch, TensorFlow, numpy, etc.) may lead to differences in calculation logic or result accuracy.
I would greatly appreciate it if any expert who has successfully reproduced the paper's results could share the output of pip list in your environment to help me troubleshoot version issues. If you have other suggestions that may cause result differences, please feel free to point them out as well!
Thank you very much for your help!
```plaintext
accelerate 0.26.0
addict 2.4.0
aiofiles 23.2.1
aiohappyeyeballs 2.6.1
aiohttp 3.13.0
aiosignal 1.4.0
altair 5.5.0
annotated-types 0.7.0
anyio 4.11.0
argon2-cffi 25.1.0
argon2-cffi-bindings 25.1.0
arrow 1.3.0
arxiv 2.2.0
asttokens 3.0.0
async-lru 2.0.5
async-timeout 5.0.1
attrs 25.4.0
babel 2.17.0
beautifulsoup4 4.14.2
bitsandbytes 0.45.5
bleach 6.2.0
blinker 1.9.0
Brotli 1.1.0
cachetools 6.2.0
certifi 2022.12.7
cffi 2.0.0
charset-normalizer 2.1.1
click 8.3.0
colorama 0.4.6
comm 0.2.3
contourpy 1.3.2
cycler 0.12.1
datasets 4.1.1
debugpy 1.8.17
decorator 5.2.1
deepspeed 0.17.6
defusedxml 0.7.1
dill 0.4.0
distro 1.9.0
duckduckgo_search 5.3.1b1
einops 0.8.1
et_xmlfile 2.0.0
exceptiongroup 1.3.0
executing 2.2.1
fastapi 0.118.0
fastjsonschema 2.21.2
feedparser 6.0.12
ffmpy 0.6.1
filelock 3.13.1
fonttools 4.60.1
fqdn 1.5.1
frozenlist 1.8.0
fsspec 2024.6.1
ftfy 6.3.1
func_timeout 4.3.5
gitdb 4.0.12
GitPython 3.1.45
gradio 4.37.2
gradio_client 1.0.2
gradio_image_prompter 0.1.0
griffe 0.49.0
h11 0.16.0
h2 4.3.0
hf-xet 1.1.10
hjson 3.1.0
hpack 4.1.0
httpcore 1.0.9
httpx 0.28.1
huggingface-hub 0.35.3
hyperframe 6.1.0
idna 3.4
imageio 2.37.0
importlib_metadata 8.7.0
importlib_resources 6.5.2
ipykernel 6.30.1
ipython 8.37.0
ipywidgets 8.1.7
isoduration 20.11.0
jedi 0.19.2
Jinja2 3.1.4
json5 0.12.1
jsonpointer 3.0.0
jsonschema 4.25.1
jsonschema-specifications 2025.9.1
jupyter 1.1.1
jupyter_client 8.6.3
jupyter-console 6.6.3
jupyter_core 5.8.1
jupyter-events 0.12.0
jupyter-lsp 2.3.0
jupyter_server 2.17.0
jupyter_server_terminals 0.5.3
jupyterlab 4.4.9
jupyterlab_pygments 0.3.0
jupyterlab_server 2.27.3
jupyterlab_widgets 3.0.15
kiwisolver 1.4.9
kornia 0.8.1
kornia_rs 0.1.9
lagent 0.2.4
lark 1.3.0
lazy_loader 0.4
Markdown 3.9
markdown-it-py 4.0.0
MarkupSafe 2.1.5
mat4py 0.6.0
matplotlib 3.10.6
matplotlib-inline 0.1.7
mdurl 0.1.2
mistune 3.1.4
mmcv 2.0.1
mmdet 3.1.0
mmengine 0.10.7
mmpretrain 1.0.1
mmsegmentation 1.1.1
model-index 0.1.11
modelindex 0.0.2
modelscope 1.30.0
mpi4py_mpich 3.1.5
mpmath 1.3.0
msgpack 1.1.1
multidict 6.7.0
multiprocess 0.70.16
narwhals 2.7.0
nbclient 0.10.2
nbconvert 7.16.6
nbformat 5.10.4
nest-asyncio 1.6.0
networkx 3.3
ninja 1.13.0
notebook 7.4.7
notebook_shim 0.2.4
numpy 1.26.4
nvidia-ml-py 13.580.82
opencv-python 4.8.1.78
openpyxl 3.1.5
ordered-set 4.1.0
orjson 3.11.3
overrides 7.7.0
packaging 25.0
pandas 2.3.3
pandocfilters 1.5.1
parso 0.8.5
peft 0.7.1
pexpect 4.9.0
phx-class-registry 4.1.0
pillow 10.4.0
pip 25.2
platformdirs 4.4.0
prettytable 3.16.0
prometheus_client 0.23.1
prompt_toolkit 3.0.52
propcache 0.4.0
protobuf 6.32.1
psutil 7.1.0
ptyprocess 0.7.0
pure_eval 0.2.3
py-cpuinfo 9.0.0
pyarrow 21.0.0
pycocotools 2.0.10
pycparser 2.23
pydantic 2.10.6
pydantic_core 2.27.2
pydeck 0.9.1
pydub 0.25.1
Pygments 2.19.2
pyparsing 3.2.5
python-dateutil 2.9.0.post0
python-json-logger 4.0.0
python-multipart 0.0.20
pytz 2025.2
PyYAML 6.0.3
pyzmq 27.1.0
referencing 0.36.2
regex 2025.9.18
requests 2.32.5
rfc3339-validator 0.1.4
rfc3986-validator 0.1.1
rfc3987-syntax 1.1.0
rich 14.1.0
rpds-py 0.27.1
ruff 0.13.3
safetensors 0.6.2
scikit-image 0.25.2
scipy 1.15.3
semantic-version 2.10.0
Send2Trash 1.8.3
sentencepiece 0.2.1
setuptools 78.1.1
sgmllib3k 1.0.0
shapely 2.1.2
shellingham 1.5.4
six 1.17.0
smmap 5.0.2
sniffio 1.3.1
socksio 1.0.0
soupsieve 2.8
stack-data 0.6.3
starlette 0.48.0
streamlit 1.50.0
sympy 1.13.3
tenacity 9.1.2
termcolor 3.1.0
terminado 0.18.1
terminaltables 3.1.10
tifffile 2025.5.10
tiktoken 0.12.0
timeout-decorator 0.5.0
timm 1.0.20
tinycss2 1.4.0
tokenizers 0.15.2
toml 0.10.2
tomli 2.2.1
tomlkit 0.12.0
torch 2.1.2+cu118
torchaudio 2.1.2+cu118
torchvision 0.16.2+cu118
tornado 6.5.2
tqdm 4.67.1
traitlets 5.14.3
transformers 4.36.0
transformers-stream-generator 0.0.5
triton 2.1.0
typer 0.19.2
types-python-dateutil 2.9.0.20250822
typing_extensions 4.12.2
typing-inspection 0.4.2
tzdata 2025.2
uri-template 1.3.0
urllib3 2.5.0
uvicorn 0.37.0
watchdog 6.0.0
wcwidth 0.2.14
webcolors 24.11.1
webencodings 0.5.1
websocket-client 1.8.0
websockets 11.0.3
wheel 0.45.1
widgetsnbextension 4.0.14
xtuner 0.1.21 /root/autodl-tmp/OMG-Seg-main/OMG-Seg-main/omg_llava
xxhash 3.6.0
yapf 0.43.0
yarl 1.22.0
zipp 3.23.0
```
![](https://images.cnblogs.com/cnblogs_com/blogs/828475/galleries/2447233/o_251015055209_%E5%B1%8F%E5%B9%95%E6%88%AA%E5%9B%BE%202025-10-15%20135158.png)

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names the Gradio demo and includes a pip list, but no repository file, test, evaluation command, or target metric is specified. Start by reproducing the demo and comparing the reported environment with the project's documented dependencies; a useful resolution would identify the cause of the paper-result discrepancy and define a reproducible evaluation path.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.