Displaying 1 to 9 from 9 results

bi-att-flow - Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization

  •    Python

The model has ~2.5M parameters. The model was trained with NVidia Titan X (Pascal Architecture, 2016). The model requires at least 12GB of GPU RAM. If your GPU RAM is smaller than 12GB, you can either decrease batch size (performance might degrade), or you can use multi GPU (see below). The training converges at ~18k steps, and it took ~4s per step (i.e. ~20 hours). You can still omit them, but training will be much slower.

R-Net - Tensorflow Implementation of R-Net

  •    Python

There have been a lot of known problems caused by using different software versions. Please check your versions before opening issues or emailing me. See release for trained model.

DrQA - A pytorch implementation of Reading Wikipedia to Answer Open-Domain Questions.

  •    Python

A pytorch implementation of the ACL 2017 paper Reading Wikipedia to Answer Open-Domain Questions (DrQA). Reading comprehension is a task to produce an answer when given a question and one or more pieces of evidence (usually natural language paragraphs). Compared to question answering over knowledge bases, reading comprehension models are more flexible and have revealed a great potential for zero-shot learning.

LambdaHack - Haskell game engine library for roguelike dungeon crawlers; try out the browser version at

  •    Haskell

As an example of the engine's capabilities, here is a showcase of shooting down explosive projectiles. A couple were shot down close enough to enemies to harm them. Others exploded closer to our party members and took out of the air the projectiles that would otherwise harm them. This was a semi-automatic stealthy speedrun of the escape scenario of the sample game that comes with the engine. Small fixed font. The enemy gang has a huge numerical and equipment superiority. Our team loots the area on auto-pilot until the first foe is spotted. Then they scout out enemy positions. Then hero 1 draws enemies and unfortunately enemy fire as well, which is when he valiantly shoots down explosives to avoid the worst damage. Then heroine 2 sneaks behind enemy lines to reach the remaining treasure. That accomplished, the captain signals retreat and leaves for the next area (the zoo).




node-squad - Run N functions in parallel, and wait for all of them to be finished before starting another batch

  •    Javascript

Run N functions in parallel. When all the functions are finished, N new functions are triggered, until the input data set is drained. This package is based on the excellent https://github.com/kriskowal/q It can be used for different purpose (API throttling, rate limiting, etc.).

MnemonicReader - A PyTorch implementation of Mnemonic Reader for the Machine Comprehension task

  •    Python

The Mnemonic Reader is a deep learning model for Machine Comprehension task. You can get details from this paper. It combines advantages of match-LSTM, R-Net and Document Reader and utilizes a new unit, the Semantic Fusion Unit (SFU), to achieve state-of-the-art results (at that time). This model is a PyTorch implementation of Mnemonic Reader. At the same time, a PyTorch implementation of R-Net and a PyTorch implementation of Document Reader are also included to compare with the Mnemonic Reader. Pretrained models are also available in release.

dawn-bench-entries - DAWNBench: An End-to-End Deep Learning Benchmark and Competition

  •    Python

To add your model to our leaderboard, open a Pull Request with title <Model name> || <Task name> || <Author name> (example PR), with JSON (and TSV where applicable) result files in the format outlined below. We evaluate image classification performance on the CIFAR10 dataset.

Allure - Allure of the Stars is a near-future Sci-Fi roguelike and tactical squad game written in Haskell

  •    Haskell

Not a single picture in this game. You have to imagine everything yourself, like with a book (a grown-up book, without pictures). Once you learn to imagine things, though, you can keep exploring and mastering the world and making up stories for a long time. The game is written in Haskell1 using the LambdaHack10 roguelike game engine. Please see the changelog file for recent improvements and the issue tracker for short-term plans. Long term goals are high replayability and auto-balancing through procedural content generation and persistent content modification based on player behaviour. Contributions are welcome.







We have large collection of open source products. Follow the tags from Tag Cloud >>


Open source products are scattered around the web. Please provide information about the open source projects you own / you use. Add Projects.