Comments (12)
Mac, M1
I have met and solved this problem like this:
1、brew install cmake ffmpeg@4, (ffmpeg5 not work,cause decord need ffmpeg4)
2、install decord from source code
3、install lavis from source code
from lavis.
@dxli94 That didn't work for me. I even tried downgrading to python 3.8 and python 3.7, but kept getting the same issue. I'm on an M1 Mac. How can I fix this?
from lavis.
So I'm unable to use it for calling BLIP2
Obviously not a viable long-term solution, but if all you (or anyone else coming here) want to do is just calling BLIP to do e.g. image captioning, you can clone the repo, comment out the decord imports in lavis/datasets/data_utils.py
as well as commenting out / removing decord in requirements.txt
, and then running pip install -e .
, that worked for me.
from lavis.
ERROR: Could not find a version that satisfies the requirement decord (from versions: none)
ERROR: No matching distribution found for decord
from lavis.
Hi, from the other closed issue #122 , I tried removing decord from requirements. txt but it's still required by load_model_and_preprocess function. Check screenshot attached. So I'm unable to use it for calling BLIP2 @dxli94
from lavis.
Hi @jhwang7628 ,
Thanks for your interest.
Can you install decord if removing the requirement on its versions? E.g. decord>=0.6.0 into decord in requirement-dev.txt.
Thanks.
from lavis.
@dxli94 That didn't work for me. I even tried downgrading to python 3.8 and python 3.7, but kept getting the same issue. I'm on an M1 Mac. How can I fix this?
Hi @Nutlope , what is the error message you get?
from lavis.
is it solved ?
from lavis.
So I'm unable to use it for calling BLIP2
Obviously not a viable long-term solution, but if all you (or anyone else coming here) want to do is just calling BLIP to do e.g. image captioning, you can clone the repo, comment out the decord imports in
lavis/datasets/data_utils.py
as well as commenting out / removing decord inrequirements.txt
, and then runningpip install -e .
, that worked for me.
This worked for getting past the decord error. Especially for running the colab notebook example in LAVIS's Homepage on github
from lavis.
Mac, M1
I have met and solved this problem like this: 1、brew install cmake ffmpeg@4, (ffmpeg5 not work,cause decord need ffmpeg4) 2、install decord from source code 3、install lavis from source code
This worked wonders, Thanks @hiwgy
from lavis.
Mac, M1
I have met and solved this problem like this: 1、brew install cmake ffmpeg@4, (ffmpeg5 not work,cause decord need ffmpeg4) 2、install decord from source code 3、install lavis from source code
I tried this and it worked successfully until I hit a dependency issue with LAVIS. LAVIS requires open3d==0.13.0 which is only supported by python 3.6, 3.7, and 3.8 (see docs).
I tried to downgrade to python 3.8, but decode requires >= python 3.9. Thus, stuck in a dependency loop. Will keep exploring and update if I find anything.
For reference, I am running python 3.11.2 on an M1 Pro Mac.
PS - if you have ffmpeg@5 installed, you need to overwrite the homebrew symlink.
brew link --overwrite ffmpeg@4
from lavis.
Mac, M1
I have met and solved this problem like this: 1、brew install cmake ffmpeg@4, (ffmpeg5 not work,cause decord need ffmpeg4) 2、install decord from source code 3、install lavis from source codeI tried this and it worked successfully until I hit a dependency issue with LAVIS. LAVIS requires open3d==0.13.0 which is only supported by python 3.6, 3.7, and 3.8 (see docs).
I tried to downgrade to python 3.8, but decode requires >= python 3.9. Thus, stuck in a dependency loop. Will keep exploring and update if I find anything.
For reference, I am running python 3.11.2 on an M1 Pro Mac.
PS - if you have ffmpeg@5 installed, you need to overwrite the homebrew symlink.
brew link --overwrite ffmpeg@4
Just to update on this, I finally got lavis to install. What worked for me was this:
- install ffmpeg@4 using
brew install ffmpeg@4
- update the link since I had ffmpeg5 using
brew link --overwrite ffmpeg@4
- install decode from source using instructions here
- install lavis from PyPi using
pip install salesforce-lavis
from lavis.
Related Issues (20)
- Why do I always encounter CUDA out of memory problem when I load the load_model_process function? Can the RTX 3090 be used for the BLIP-2 model?" HOT 2
- The results of DocVQA, infoVQA, and OCRVQA evaluating the instructblip model are very low
- Score difference in ITM and ITC ?
- Can existing large datasets be used to fine tune the blip2 caption task?
- OPT2.7B underperforming & weird behavior compared to flant5xl on image captioning? HOT 5
- The role of modeling_opt.py in the BLIP2 model
- Image use to present LAVIS
- How to run InstructBLIP with other LLM model
- How can I calculate the similarity between multimodal features and Unimodal features
- Potentially wrong inherence in lavis.datasets.datasets.base_dataset
- Input of multiple images
- how use it output target class。
- how to deal with “Missing keys ” HOT 1
- huggingface_hub.utils._validators.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: ''.
- How should I use blip2 for vqa task training? HOT 3
- XInstructBLIP demo text generation
- salesforce-lavis 1.0.2 requires transformers<4.27,>=4.25.0, but you have transformers 4.40.0 which is incompatible.
- Use BLIP-2 for Image Captioning HOT 1
- safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge HOT 2
- Loss calculation across GPUs using all_gather_with_grad function
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from lavis.