文件名称:feature_selection
文件大小:39.06MB
文件格式:ZIP
更新时间:2024-04-08 05:35:12
Python
这是JaromírJanisch , TomášPevný和ViliamLisý撰写的AAAI 2019论文《使用深度强化学习的具有昂贵功能的分类》的源代码://// 可用的更新版本:该文章的增强版本名为分类,具有作为顺序决策问题的代价高昂的功能 ,它分析了更多设置(硬预算,lambda的拉格朗日优化和缺少的功能)。该代码在该存储库的分支中可用。 引用为: @inproceedings{janisch2019classification, title={Classification with Costly Features using Deep Reinforcement Learning}, author={Janisch, Jaromír and Pevný, Tomáš and Lisý, Viliam}, booktitle={AAAI Conference on
【文件预览】:
feature_selection-main
----Untitled.ipynb(1KB)
----eval.py(2KB)
----config_datasets()
--------cifar2.py(248B)
--------forest.py(83B)
--------yeast.py(81B)
--------forest2.py(86B)
--------forest2_fakehpc.py(210B)
--------cifar.py(248B)
--------__pycache__()
--------mnist.py(247B)
--------wine.py(80B)
--------mb.py(78B)
--------mb_fakehpc.py(204B)
----agent.py(5KB)
----main.py(6KB)
----pool.py(852B)
----run_val_0.dat(274B)
----run_trn_0.dat(0B)
----utils.py(529B)
----tools()
--------conv_forest_2.py(2KB)
--------conv_forest.py(2KB)
--------conv_mnist.py(2KB)
--------test.py(208B)
--------hpc_fake.py(1KB)
--------conv_miniboone.py(1KB)
--------conv_wine.py(1KB)
--------hpc_svm.py(6KB)
--------conv_cifar.py(2KB)
--------test_code.ipynb(15B)
--------requirements.txt(9KB)
--------conv_cifar_2.py(2KB)
--------conv_yeast.py(2KB)
--------debug.m(797B)
----data()
--------wine-hpc(3KB)
--------raw()
--------wine-meta(1KB)
--------wine-val(3KB)
--------wine-test(6KB)
--------wine-train(5KB)
----model_best_(155KB)
----model(155KB)
----run.state(219B)
----__pycache__()
--------brain.cpython-36.pyc(5KB)
--------env.cpython-36.pyc(5KB)
--------config.cpython-36.pyc(3KB)
--------log.cpython-36.pyc(3KB)
--------log.cpython-38.pyc(3KB)
--------agent.cpython-38.pyc(4KB)
--------utils.cpython-38.pyc(1005B)
--------agent.cpython-36.pyc(4KB)
--------pool.cpython-38.pyc(1KB)
--------utils.cpython-36.pyc(987B)
--------pool.cpython-36.pyc(1KB)
--------env.cpython-38.pyc(5KB)
--------net.cpython-36.pyc(3KB)
--------config.cpython-38.pyc(3KB)
--------brain.cpython-38.pyc(5KB)
--------net.cpython-38.pyc(3KB)
----model_pretrained_(155KB)
----trained_hpc()
--------cifar-hpc(938KB)
--------wine-hpc(3KB)
--------cifar-2-hpc(938KB)
--------mnist-hpc(1.15MB)
--------forest-hpc(6.87MB)
--------forest-2-hpc(6.87MB)
--------mb-hpc-fake(1.48MB)
--------yeast-hpc(17KB)
--------forest-2-hpc-fake(6.87MB)
--------mb-hpc(1.48MB)
----model_best(155KB)
----LICENSE(1KB)
----model_(155KB)
----model_pretrained(155KB)
----run_trn_perf.dat(63B)
----env.py(5KB)
----log.py(4KB)
----requirement.txt(822B)
----net.py(3KB)
----config.py(4KB)
----.ipynb_checkpoints()
--------Untitled-checkpoint.ipynb(72B)
----README.md(2KB)
----run_val_perf.dat(63B)
----brain.py(5KB)