variational_sampling_methods

(★ 51)

[ICML 2024] Official implementation for "Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling".

파일 탐색기

최종 버전 다운로드 (.zip)

- - __init__.cpython-310.pyc
  - __init__.cpython-39.pyc
- - aft.py
  - aft_trainer.py
- - cmcd_rnd.py
  - cmcd_trainer.py
- - flow_transport.py
  - flows.py
  - markov_kernel.py
  - mcmc.py
  - resampling.py
  - samplers.py
  - types.py
  - utils.py
- - craft.py
  - craft_trainer.py
- - dds_rnd.py
  - dds_trainer.py
- - dis_is_weights.py
  - dis_rnd.py
  - dis_trainer.py
- - gbs_isw.py
  - gbs_trainer.py
- - gfn_rnd.py
  - gfn_trainer.py
- - gmmvi_trainer.py
- - base_dist.py
  - cmcd.py
  - cmcd_trainer.py
  - ld_eval.py
  - ld_init.py
  - ld_utils.py
  - ldvi_trainer.py
  - mcd_trainer.py
  - od_langevin.py
  - optimizer.py
  - score_network.py
  - ud_langevin.py
  - uha_trainer.py
  - ula_trainer.py
- - ldvi_isw.py
  - ldvi_trainer.py
- - mcd_rnd.py
  - mcd_trainer.py
- - mfvi_trainer.py
- - nfvi.py
  - nfvi_trainer.py
- - pis_rnd.py
  - pis_trainer.py
- - smc.py
  - smc_trainer.py
- - uha_isw.py
  - uha_trainer.py
- - ula_isw.py
  - ula_trainer.py
- - aldp_conf.cpython-39.pyc
- - aft.yaml
  - cmcd.yaml
  - craft.yaml
  - dds.yaml
  - dis.yaml
  - fab.yaml
  - gbs.yaml
  - gfn.yaml
  - gmmvi.yaml
  - ldvi.yaml
  - mcd.yaml
  - mfvi.yaml
  - nfvi.yaml
  - pis.yaml
  - smc.yaml
  - uha.yaml
  - ula.yaml
- - slurm.yaml
- - brownian.yaml
  - cancer.yaml
  - credit.yaml
  - funnel.yaml
  - gaussian.yaml
  - gaussian_mixture.yaml
  - gaussian_mixture1d.yaml
  - gaussian_mixture40.yaml
  - ionosphere.yaml
  - lennard_jones.yaml
  - lgcp.yaml
  - lorenz.yaml
  - many_well.yaml
  - nice_digits.yaml
  - nice_fashion.yaml
  - planar_robot.yaml
  - rings.yaml
  - seeds.yaml
  - sonar.yaml
  - student_t_mixture.yaml
- base_conf.yaml
- setup.yaml
- - __init__.cpython-310.pyc
  - aldp.cpython-39.pyc
  - aldp_test.cpython-39-pytest-7.4.2.pyc
  - base_problem.cpython-310.pyc
  - base_target.cpython-310.pyc
  - base_target.cpython-38.pyc
  - base_target.cpython-39.pyc
  - breast_cancer.cpython-310.pyc
  - breast_cancer.cpython-39.pyc
  - brownian.cpython-310.pyc
  - brownian.cpython-38.pyc
  - brownian.cpython-39.pyc
  - funnel.cpython-310.pyc
  - funnel.cpython-38.pyc
  - funnel.cpython-39.pyc
  - gaussian.cpython-310.pyc
  - gaussian.cpython-39.pyc
  - gaussian_mixture.cpython-310.pyc
  - gaussian_mixture.cpython-39.pyc
  - german_credit.cpython-310.pyc
  - german_credit.cpython-39.pyc
  - gmm40.cpython-310.pyc
  - gmm40.cpython-38.pyc
  - gmm40.cpython-39.pyc
  - gmm_fab_sanity_check.cpython-39.pyc
  - ionosphere.cpython-310.pyc
  - ionosphere.cpython-39.pyc
  - lgcp.cpython-310.pyc
  - lgcp.cpython-39.pyc
  - lorenz.cpython-310.pyc
  - lorenz.cpython-39.pyc
  - many_well.cpython-310.pyc
  - many_well.cpython-39.pyc
  - mixture_models.cpython-310.pyc
  - nice.cpython-310.pyc
  - nice.cpython-39.pyc
  - planar_robot.cpython-310.pyc
  - planar_robot.cpython-39.pyc
  - rings.cpython-310.pyc
  - rings.cpython-39.pyc
  - seeds.cpython-310.pyc
  - seeds.cpython-39.pyc
  - sonar.cpython-310.pyc
  - sonar.cpython-39.pyc
  - student_t_mixture.cpython-310.pyc
  - student_t_mixture.cpython-39.pyc
- - aldp_10k.h5
  - breast_cancer.data
  - breastcancer_gt_with_lns_10k.npz
  - download_aldp_training_data.sh
  - german.data-numeric
  - german_credit10k.npy
  - ionosphere_full.pkl
  - params_nice_fashion_mnist_28x28_flax.pkl
  - params_nice_mnist_14x14_flax.pkl
  - params_nice_mnist_28x28_flax.pkl
  - pines.csv
  - planar_robot_gt_10k.npz
  - position_min_energy.npy
  - sonar_full.pkl
  - vae.pickle
- base_target.py
- breast_cancer.py
- brownian.py
- funnel.py
- gaussian.py
- gaussian_mixture.py
- german_credit.py
- gmm1d.py
- gmm40.py
- ionosphere.py
- lennard_jones.py
- lgcp.py
- lorenz.py
- many_well.py
- nice.py
- planar_robot.py
- rings.py
- seeds.py
- sonar.py
- student_t_mixture.py
- - __init__.cpython-310.pyc
  - __init__.cpython-38.pyc
  - __init__.cpython-39.pyc
  - helper.cpython-310.pyc
  - helper.cpython-39.pyc
  - path_utils.cpython-310.pyc
  - path_utils.cpython-38.pyc
  - path_utils.cpython-39.pyc
  - plot.cpython-38.pyc
  - plot.cpython-39.pyc
  - plotting.cpython-39.pyc
  - print_util.cpython-310.pyc
  - print_util.cpython-38.pyc
  - print_util.cpython-39.pyc
  - sub_traj_plotting.cpython-39.pyc
  - target_conf_selector.cpython-39.pyc
  - train_selector.cpython-310.pyc
  - train_selector.cpython-39.pyc
- - __init__.py
  - classifier_model.py
  - classifier_trainer.py
  - data_utils.py
  - train_classifier.py
- - __init__.py
  - base.py
  - nice.py
  - nice_config.py
  - nice_run.py
  - nice_utils.py
- __init__.py
- helper.py
- path_utils.py
- plot.py
- print_util.py
- train_selector.py
.gitignore
LICENSE
README.md
requirements.txt
run.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/DenisBless/variational_sampling_methods

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd variational_sampling_methods

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

conda create -n sampling_bench python==3.10.14 pip --yes

이 명령어를 터미널에 그대로 입력해 실행하세요.

pip install -r requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.