[ buster ]
[ ソース: lua-torch-optim ]
パッケージ: lua-torch-optim (0~20171127-ga5ceed7-1)
lua-torch-optim に関するリンク
Debian の資源:
lua-torch-optim ソースパッケージをダウンロード:
- [lua-torch-optim_0~20171127-ga5ceed7-1.dsc]
- [lua-torch-optim_0~20171127-ga5ceed7.orig.tar.gz]
- [lua-torch-optim_0~20171127-ga5ceed7-1.debian.tar.xz]
メンテナ:
外部の資源:
- ホームページ [github.com]
類似のパッケージ:
Numeric Optimization Package for Torch Framework
This package contains several optimization routines and a logger for Torch.
The following algorithms are provided:
* Stochastic Gradient Descent * Averaged Stochastic Gradient Descent * L-BFGS * Congugate Gradients * AdaDelta * AdaGrad * Adam * AdaMax * FISTA with backtracking line search * Nesterov's Accelerated Gradient method * RMSprop * Rprop * CMAESAll these algorithms are designed to support batch optimization as well as stochastic optimization. It's up to the user to construct an objective function that represents the batch, mini-batch, or single sample on which to evaluate the objective.
This package provides also logging and live plotting capabilities via the `optim.Logger()` function. Live logging is essential to monitor the network accuracy and cost function during training and testing, for spotting under- and over-fitting, for early stopping or just for monitoring the health of the current optimisation task.
その他の lua-torch-optim 関連パッケージ
|
|
|
|
-
- dep: lua-torch-torch7
- Torch Package for Torch Framework
-
- dep: lua-torch-xlua
- Lua Extension Package for Torch Framework