nv-nguyen / nope Goto Github PK
View Code? Open in Web Editor NEW[CVPR 2024] PyTorch implementation of NOPE: Novel Object Pose Estimation from a Single Image
[CVPR 2024] PyTorch implementation of NOPE: Novel Object Pose Estimation from a Single Image
Hi can you pls add test_shapeNet.py so that we can test it. Weight provided in other issue is sufficient for running this inference?
Hi,
Thanks for this nice work, can you provide the rendered dataset and the inference code?
Hi,@nv-nguyen:
I notice that the results are not the same in the two versions(23 Mar 2023 and 29 Mar 2024 in arxiv), does changed encoder( VAE network ) in latest version lead to worse result? if yes ,why you change the encoder?
Hi, really interesting work!
Can I give more reference images for every category?
Best regards,
Paolo.
Hi,
Is this file still available to get the code for generation of poses?
Thanks,
Gokul
(base) mona@ada:~/nope$ conda env create -f environment.yml
Retrieving notices: ...working... done
Collecting package metadata (repodata.json): / WARNING conda.models.version:get_matcher(556): Using .* with relational operator is superfluous and deprecated and will be removed in a future version of conda. Your spec was 1.6.0.*, but conda is ignoring the .* and treating it as 1.6.0
WARNING conda.models.version:get_matcher(556): Using .* with relational operator is superfluous and deprecated and will be removed in a future version of conda. Your spec was 1.8.0.*, but conda is ignoring the .* and treating it as 1.8.0
WARNING conda.models.version:get_matcher(556): Using .* with relational operator is superfluous and deprecated and will be removed in a future version of conda. Your spec was 1.7.1.*, but conda is ignoring the .* and treating it as 1.7.1
WARNING conda.models.version:get_matcher(556): Using .* with relational operator is superfluous and deprecated and will be removed in a future version of conda. Your spec was 1.9.0.*, but conda is ignoring the .* and treating it as 1.9.0
done
Solving environment: done
==> WARNING: A newer version of conda exists. <==
current version: 23.7.4
latest version: 23.10.0
Please update conda by running
$ conda update -n base -c defaults conda
Or to minimize the number of packages updated during conda update use
conda install conda=23.10.0
Downloading and Extracting Packages
Preparing transaction: done
Verifying transaction: done
Executing transaction: \ By downloading and using the CUDA Toolkit conda packages, you accept the terms and conditions of the CUDA End User License Agreement (EULA): https://docs.nvidia.com/cuda/eula/index.html
done
Installing pip dependencies: / Ran pip subprocess with arguments:
['/home/mona/anaconda3/envs/nope/bin/python', '-m', 'pip', 'install', '-U', '-r', '/home/mona/nope/condaenv.2tcc2q38.requirements.txt', '--exists-action=b']
Pip subprocess output:
Collecting absl-py==1.3.0
Downloading absl_py-1.3.0-py3-none-any.whl (124 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 124.6/124.6 kB 4.4 MB/s eta 0:00:00
Collecting accelerate==0.14.0
Downloading accelerate-0.14.0-py3-none-any.whl (175 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 176.0/176.0 kB 9.5 MB/s eta 0:00:00
Collecting addict==2.4.0
Using cached addict-2.4.0-py3-none-any.whl (3.8 kB)
Collecting aiohttp==3.8.3
Downloading aiohttp-3.8.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.0 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.0/1.0 MB 11.4 MB/s eta 0:00:00
Collecting aiosignal==1.3.1
Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)
Collecting alembic==1.8.1
Downloading alembic-1.8.1-py3-none-any.whl (209 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 209.8/209.8 kB 16.8 MB/s eta 0:00:00
Collecting antlr4-python3-runtime==4.9.3
Downloading antlr4-python3-runtime-4.9.3.tar.gz (117 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 117.0/117.0 kB 36.1 MB/s eta 0:00:00
Preparing metadata (setup.py): started
Preparing metadata (setup.py): finished with status 'done'
Collecting asttokens==2.1.0
Downloading asttokens-2.1.0-py2.py3-none-any.whl (26 kB)
Collecting astunparse==1.6.3
Downloading astunparse-1.6.3-py2.py3-none-any.whl (12 kB)
Collecting async-timeout==4.0.2
Downloading async_timeout-4.0.2-py3-none-any.whl (5.8 kB)
Collecting attrs==22.1.0
Downloading attrs-22.1.0-py2.py3-none-any.whl (58 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 58.8/58.8 kB 18.9 MB/s eta 0:00:00
Collecting autopage==0.5.1
Downloading autopage-0.5.1-py3-none-any.whl (29 kB)
Collecting backcall==0.2.0
Using cached backcall-0.2.0-py2.py3-none-any.whl (11 kB)
Collecting blenderproc==2.5.0
Downloading blenderproc-2.5.0-py3-none-any.whl (501 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 501.4/501.4 kB 17.7 MB/s eta 0:00:00
Collecting blobfile==2.0.0
Downloading blobfile-2.0.0-py3-none-any.whl (73 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 73.3/73.3 kB 21.6 MB/s eta 0:00:00
Collecting boto3==1.26.70
Downloading boto3-1.26.70-py3-none-any.whl (132 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 132.7/132.7 kB 9.2 MB/s eta 0:00:00
Collecting botocore==1.29.70
Downloading botocore-1.29.70-py3-none-any.whl (10.4 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 10.4/10.4 MB 34.9 MB/s eta 0:00:00
Collecting cachetools==5.2.0
Downloading cachetools-5.2.0-py3-none-any.whl (9.3 kB)
Collecting cfgv==3.3.1
Downloading cfgv-3.3.1-py2.py3-none-any.whl (7.3 kB)
Collecting click==8.1.3
Downloading click-8.1.3-py3-none-any.whl (96 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 96.6/96.6 kB 29.4 MB/s eta 0:00:00
Collecting cliff==4.1.0
Downloading cliff-4.1.0-py3-none-any.whl (81 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 81.0/81.0 kB 31.5 MB/s eta 0:00:00
Pip subprocess error:
ERROR: Could not find a version that satisfies the requirement clip==1.0 (from versions: 0.0.1, 0.1.0, 0.2.0)
ERROR: No matching distribution found for clip==1.0
failed
CondaEnvException: Pip failed
(base) mona@ada:~$ uname -a
Linux ada 6.2.0-36-generic #37~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Oct 9 15:34:04 UTC 2 x86_64 x86_64 x86_64 GNU/Linux
(base) mona@ada:~$ lsb_release -a
LSB Version: core-11.1.0ubuntu4-noarch:security-11.1.0ubuntu4-noarch
Distributor ID: Ubuntu
Description: Ubuntu 22.04.3 LTS
Release: 22.04
Codename: jammy
(base) mona@ada:~$ conda --version
conda 23.7.4
Hello,
Will the inference on unseen images work correctly if the image is of a person/hands holding the object?
Thank You.
Great job!
Are you planning to provide model weights?
Hi,
Thanks for your interesting work!
I noticed that the evaluation is primarily conducted on synthetic objects. Thus I'd like to ask whether you have tried the proposed method on real-world objects or datasets, for example, on some BOP benchmark datasets.
Hi,
Would you be able to share the test_script if its implemented?
I was following the README for inference, but the actual test script itself is not present in the repository.
Hi,
I am trying to run the script for training.
I looks as if you are using a huggingface model for VAE, using diffusers.AutoencoderKL
But I am not able to access the stable-diffusion-v1-5 model using AutoencoderKL.from_config
("error no config json is present")
I tried changing from autoencoder to StableDiffusionPipeline in diffusers, and using trained weights from runwayml/stable-diffusion-v1-5 , but this class StableDiffusionPipeline do not have an encode method.
Would be glad if you can help fix this issue.
Thanks,
Gokul
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.