https://github.com/bayesflow-org/selective-ssm
Experimental exploration of applying Selective State Space Model (S-SSM) architectures within Amortized Bayesian Inference workflows
Science Score: 13.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (5.6%) to scientific vocabulary
Repository
Experimental exploration of applying Selective State Space Model (S-SSM) architectures within Amortized Bayesian Inference workflows
Basic Info
- Host: GitHub
- Owner: bayesflow-org
- License: mit
- Language: Jupyter Notebook
- Default Branch: main
- Size: 615 KB
Statistics
- Stars: 1
- Watchers: 3
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Selective-SSM
Experimental exploration of applying Selective State Space Model (S-SSM) architectures within Amortized Bayesian Inference workflows
Requirements:
- Linux / WSL
- Python 3.11+
- PyTorch 1.12+
- NVIDIA GPU
- CUDA 11.6+
Installation
First create a new conda environment with at least Python 3.11 support
conda create -n bf-ssm python=3.11
Install libraries (should use .yaml env for this)
conda install numpy pandas matplotlib seaborn ipykernel
The conda forge index is currently behind, so we'll have to use pip for the more prominent libraries
pip install torch
pip install keras
pip install triton
pip install mamba-ssm
Install development build of BayesFlow
pip install git+https://github.com/Chase-Grajeda/BayesFlow@ssm-wrapper
Owner
- Name: BayesFlow
- Login: bayesflow-org
- Kind: organization
- Location: Germany
- Repositories: 1
- Profile: https://github.com/bayesflow-org
An organization for applications and extensions of amortized Bayesian inference.
GitHub Events
Total
- Watch event: 1
- Push event: 7
- Create event: 2
Last Year
- Watch event: 1
- Push event: 7
- Create event: 2