DayZ-Epoch - Experimental DayZ Mod for Arma 2

  •        89

Experimental DayZ Mod for Arma 2



Related Projects

DayZ-Private - Custom DB connection between server and DayZ

  •    C++

Custom DB connection between server and DayZ

FDC - Flocirc;r De Cunho

  •    Java

The FDC application allows coin collectors to keep and manage a collection of coins. The Collector may categorize the coins with its value, year, mintmark, country, epoch, unit and it's condition. Each coin may have also a description and an image.

epoch - A general purpose, real-time visualization library.

  •    HTML

A general purpose real-time charting library for building beautiful, smooth, and high performance visualizations.

Satellite NavigatiOn Orbit Program JAVA

  •    Java

The Satellite NavigatiOn Orbit Program JAVA (SNOOPJ) is a tool, which calculates the satellite coordinates for every observation epoch and the receiver position. It required the NAVIGATION-File and the OBSERVATION-File (RINEX).

faster-rnnlm - Faster Recurrent Neural Network Language Modeling Toolkit with Noise Contrastive Estimation and Hierarchical Softmax

  •    C++

In a nutshell, the goal of this project is to create an rnnlm implementation that can be trained on huge datasets (several billions of words) and very large vocabularies (several hundred thousands) and used in real-world ASR and MT problems. Besides, to achieve better results this implementation supports such praised setups as ReLU+DiagonalInitialization [1], GRU [2], NCE [3], and RMSProp [4]. How fast is it? Well, on One Billion Word Benchmark [8] and 3.3GHz CPU the program with standard parameters (sigmoid hidden layer of size 256 and hierarchical softmax) processes more then 250k words per second in 8 threads, i.e. 15 millions of words per minute. As a result an epoch takes less than one hour. Check Experiments section for more numbers and figures.

Deep-Learning-Tricks - Enumerate diverse machine learning training tricks.


This is an attempt to enumerate different machine learning training tricks I gather around as well as some network architectures. The goal is to briefly give a description of the trick as well as an intuition about why it is working. My knowledge is quite limited so this is prone to errors/imprecisions. This should be a collaborative work so feel free to complete or correct. Most of the tricks may seem trivial for those who have some experience in machine learning but I feel like while there is a lot of very good theoretical material available for machine learning, there is still a lack of practical advice. Those would really have helped me when I started. The excellent CS231n Stanford course already has a good list of training tricks. What: The learning rate is probably the most important hyperparameter to tune. A strategy used to select the hyperparameters is to randomly sample them (uniformly or logscale) and see the testing error after a few epoch.

libcds - A C++ library of Concurrent Data Structures

  •    C++

The Concurrent Data Structures (CDS) library is a collection of concurrent containers that don't require external (manual) synchronization for shared access, and safe memory reclamation (SMR) algorithms like Hazard Pointer and user-space RCU that is used as an epoch-based SMR. CDS is mostly header-only template library. Only SMR core implementation is segregated to .so/.dll file.

SiaNet - An easy to use C# deep learning library with CUDA/OpenCL support

  •    CSharp

Developing a C# wrapper to help developer easily create and train deep neural network models. The below is a classification example with Titanic dataset. Able to reach 75% accuracy within 10 epoch.