Search Results for "stage"

...It can be used as a portable drop-in replacement for built-in data loaders and data iterators in popular deep learning frameworks. Deep learning applications require complex, multi-stage data processing pipelines that include loading, decoding, cropping, resizing, and many other augmentations. These data processing pipelines, which are currently executed on the CPU, have become a bottleneck, limiting the performance and scalability of training and inference. DALI addresses the problem of the CPU bottleneck by offloading data preprocessing to the GPU. ...

The Player Project: Player is a networked interface to robots and sensors. Stage and Gazebo are Player-friendly multiple-robot simulators. The software aims for POSIX compliance and runs on most UNIX-like OS's. Some parts also work on Windows.

...Extract the corpus to a directory. Change to the code directory.After installing tensorflow, switch to the kcws code directory. Currently, the custom dictionary is supported in the decoding stage. Please refer to kcws/cc/test_seg.cc for specific usage. The dictionary is in text format.

ManFieLd is an easy-to-use framework to develop filtering applications for Distributed System, relieving the burden of the developer to write the support code for the filtering methods.

Weekend-robotics enables the dedicated amateur to build a autonomous robot. It runs on a Linux system for high-level operations and offers an interface to the defacto standard hardware abstraction layer in robotics, Player/Stage.

Obstacle Avoidance in Player/Stage using the ProBT library.

Waygoer is an OCR program. It is based on contour extraction and momentum transformations. This allows for rotation- and scale-invariant recognition. Waygoer is still at an early stage of development.

OpStation_Qt: Operator Station for controlling multiple robots/robotics/devices using Player/Stage/Gazebo written using the open Qt GUI libraries. Written in C and C++. A good platform for storing data from scientific experiments as well as recreation

Emily is a friendly name for the Machine Learning Environment (MLE). This project is at an early stage of development, and no alpha code is yet available.

A 3D physics-simulated world, populated by autonomous creatures who reproduce and evolve over time in order to become best adapted user-defined environmental conditions. Currently in the planning stage; A more detailed description is in the forums.