maco
An unofficial pytorch implementation of "Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization" [Fel+, NeurIPS 2023].
Science Score: 54.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (6.0%) to scientific vocabulary
Repository
An unofficial pytorch implementation of "Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization" [Fel+, NeurIPS 2023].
Basic Info
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
MACO (MAgnitude Constrained Optimization)
This is an unofficial pytorch implementation of the experiments executed in the paper, "Unlocking Feature Visualization for Deeper Networks with Magnitude Constrained Optimization" [Fel+, NeurIPS 2023].
[!Important] Now, an official PyTorch implementation by authors is available as a library (Horama). I highly recommend to use it instead of this repo. An official TensorFlow implementation by authors is also available from here.
What is this repo about?
TBD
Owner
- Name: Yoshihiro Fukuhara
- Login: gatheluck
- Kind: user
- Location: Tokyo
- Website: http://gatheluck.net
- Twitter: gatheluck
- Repositories: 77
- Profile: https://github.com/gatheluck
Citation (CITATION.cff)
cff-version: 1.2.0
message: "If you want to cite the framework, feel free to use this (but only if you loved it 😊)"
title: "Ascender"
abstract: "Ascender is a GitHub repository template for research projects using Python as a developing language."
date-released: 2022-10-26
authors:
- family-names: "Fukuhara"
given-names: "Yoshihiro"
- family-names: "Kubotani"
given-names: "Yoshiki"
- name: "cvpaper.challenge XCCV group"
version: 0.2.0
doi: 10.5281/zenodo.7672842
license: "MIT"
url: "https://github.com/cvpaperchallenge/Ascender"
GitHub Events
Total
- Watch event: 1
- Push event: 8
- Create event: 2
Last Year
- Watch event: 1
- Push event: 8
- Create event: 2
Dependencies
- actions/cache v4 composite
- actions/checkout v4 composite
- docker/bake-action v4 composite
- docker/setup-buildx-action v3 composite
- actions/cache v4 composite
- actions/checkout v4 composite
- docker/bake-action v4 composite
- docker/setup-buildx-action v3 composite
- ${BASE_IMAGE} latest build
- timm >=1.0.15
- torch >=2.5.1
- torchvision >=0.20.1
- tqdm >=4.67.1
- ascender 0.3.0
- certifi 2025.1.31
- charset-normalizer 3.4.1
- colorama 0.4.6
- filelock 3.16.1
- filelock 3.17.0
- fsspec 2025.3.0
- huggingface-hub 0.29.2
- idna 3.10
- jinja2 3.1.6
- markupsafe 2.1.5
- markupsafe 3.0.2
- mpmath 1.3.0
- networkx 3.1
- networkx 3.2.1
- networkx 3.4.2
- numpy 1.24.4
- numpy 2.0.2
- numpy 2.2.3
- nvidia-cublas-cu12 12.4.5.8
- nvidia-cuda-cupti-cu12 12.4.127
- nvidia-cuda-nvrtc-cu12 12.4.127
- nvidia-cuda-runtime-cu12 12.4.127
- nvidia-cudnn-cu12 9.1.0.70
- nvidia-cufft-cu12 11.2.1.3
- nvidia-curand-cu12 10.3.5.147
- nvidia-cusolver-cu12 11.6.1.9
- nvidia-cusparse-cu12 12.3.1.170
- nvidia-cusparselt-cu12 0.6.2
- nvidia-nccl-cu12 2.21.5
- nvidia-nvjitlink-cu12 12.4.127
- nvidia-nvtx-cu12 12.4.127
- packaging 24.2
- pillow 10.4.0
- pillow 11.1.0
- pyyaml 6.0.2
- requests 2.32.3
- safetensors 0.5.3
- setuptools 75.9.1
- sympy 1.12.1
- sympy 1.13.1
- timm 1.0.15
- torch 2.5.1
- torch 2.6.0
- torchvision 0.20.1
- torchvision 0.21.0
- tqdm 4.67.1
- triton 3.1.0
- triton 3.2.0
- typing-extensions 4.12.2
- urllib3 2.2.3
- urllib3 2.3.0