Variational Auto-Encoder - nbviewer
batch_size = 100 n_epochs = 100 n_hiddens_recog = [500] n_hiddens_gen = [500] n_latents = 20 n_layers_recog = len(n_hiddens_recog) n_layers_gen = len(n_hiddens_gen) layers = {} # Recognition model. rec_layer_sizes = [(x_train.shape[1], n_hiddens_recog[0])] rec_layer_sizes += zip(n_hiddens_recog[:-1], n_hiddens_recog[1:]) rec_layer_sizes += [(n_hiddens_recog[-1], n_latents * 2)] for i, (n_incoming,
REINFORCEjs: Gridworld with Dynamic Programming
# About **REINFORCEjs** is a Reinforcement Learning library that implements several common RL algorithms supported with fun web demos, and is currently maintained by [@karpathy](https://twitter.com/karpathy). In particular, the library currently includes: ### Dynamic Programming For solving finite (and not too large), deterministic MDPs. The solver uses standard tabular methods will no bells and w
lwlm, The Latent Words Language Model.
Daichi Mochihashi NTT Communication Science Laboratories $Id: lwlm.html,v 1.1 2010/03/19 10:15:06 daichi Exp $ lwlm is an exact, full Bayesian implementation of the Latent Words Language Model (Deschacht and Moens, 2009). It automatically learns synonymous words to infer context-dependent "latent word" for each word appearance, in a completely unsupervised fashion. Technically, LWLM is a higher-or
public:hog_descriptor_computation_and_visualization [juergen's work wiki]
Mat img_raw = imread("C:\\testimg.png", 1); // load as color image resize(img_raw, img_raw, Size(64,128) ); Mat img; cvtColor(img_raw, img, CV_RGB2GRAY); HOGDescriptor d; // Size(128,64), //winSize // Size(16,16), //blocksize // Size(8,8), //blockStride, // Size(8,8), //cellSize, // 9, //nbins, // 0, //derivAper, // -1, //winSigma, // 0, //histogramNormType, // 0.2, //L2HysThresh, // 0 //gammal co
Koen van de Sande: Color Descriptors (including color SIFT)
See: Koen E. A. van de Sande, Theo Gevers and Cees G. M. Snoek, Evaluating Color Descriptors for Object and Scene Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 32 (9), pages 1582-1596, 2010. [PDF] [BibTeX] for an evaluation of color descriptors carried out using this software. The paper provides a structured overview of color invariant descriptors in the conte
Documentation for GPML Matlab Code
Documentation for GPML Matlab Code version 4.2 1) What? The code provided here originally demonstrated the main algorithms from Rasmussen and Williams: Gaussian Processes for Machine Learning. It has since grown to allow more likelihood functions, further inference methods and a flexible framework for specifying GPs. Other GP packages can be found here. The code is written by Carl Edward Rasmussen
Affine-SIFT (ASIFT)
SIFT and ASIFT --- online demo : try if your images match! Jean-Michel Morel Guoshen Yu morel[AT]cmla.ens-cachan.fr yu[AT]cmap.polytechnique.fr News: The ASIFT source code and online demo are now published in the journal IPOL! 2011.02.24 News: frequently asked questions on ASIFT. --- 2009.11.22 Summary: A fully affine invariant image comparison method, Affine-SIFT (ASIFT) is introduce
Supervised latent Dirichlet allocation for classification
This is a C++ implementation of supervised latent Dirichlet allocation (sLDA) for classification. Note that the code here is slightly different from what was described in [2] in order to speed up. Note that this is only the sLDA. The annotation part is not yet posted. Downloads Download the readme.txt . Download the code (version 1.0): slda.tgz . Sample data A preprocesed 8-class image dataset [
研究の掃溜ノオト Gaussian Processes on Python
[PR]上記の広告は3ヶ月以上新規記事投稿のないブログに表示されています。新しい記事を書く事で広告が消えます。
Sources
Simple Sparse Bundle Adjustment (SSBA) A version of a sparse bundle adjustment implementation with adjustable intrinsics and distortion parameters (either shared by all views or varying for each view) is available here. The README gives some information about file formats etc. There are two medium sized datasets included in the distribution. Some remarks: This software is provided under the terms
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
DQN (Code for Human-Level Control through Deep Reinforcement Learning)
This is a minimal implementation of training for a language model using long short-term memory (LSTM) neural networks
Google Code Archive - Long-term storage for Google Code Project Hosting.
publications_posters_presentations_code[Finale's Research Website]