xdcesc,github

libfacedetection

An open source library for face detection in images. The face detection speed can reach 1000FPS.

linear-attention-recurrent-neural-network

A recurrent attention module consisting of an LSTM cell which can query its own past cell states by the means of windowed multi-head attention. The formulas are derived from the BN-LSTM and the Transformer Network. The LARNN cell with attention can be easily used inside a loop on the cell state, just like any other RNN.

liquid-dsp

digital signal processing library for software-defined radios

liquid-fpm

fixed-point math library for embedded signal processing

listen-attend-and-spell

A listen attend and spell reimplementation in tensorflow, using a custom attention mechanism.

listen-attend-and-spell-pytorch

Listen Attend and Spell (LAS) implement in pytorch

loss-landscape

Code for visualizing the loss landscape of neural nets

lpdec

lstm-gru-pytorch

LSTM and GRU in PyTorch

lstm-neural-network-for-time-series-prediction

LSTM built using Keras Python package to predict time series steps and sequences. Includes sin wave and stock market data

lstm-rnn

Portal of Johannes and Felix's RNN implementation and further modifications for ASR

lstm_ctc

LSTM CTC End2End Speech Recognition.

lstms.pth

PyTorch implementations of LSTM Variants (Dropout + Layer Norm)

lte-ofdma-downlink-simulation

LTE OFDMA Downlink Simulation

marbles

IBM Blockchain - Marbles Demo

mask_rcnn

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

masp

Microphone Array Speech Processing

masr

中文语音识别，提供预训练模型，高识别率 Chinese Speech Recognition; Mandarin Automatic Speech Recognition;

massive-mimo-myths

Simulation code for “Massive MIMO: Ten Myths and One Critical Question” by Emil Björnson, Erik G. Larsson, Thomas L. Marzetta, IEEE Communications Magazine, vol. 54, no. 2, pp. 114-123, February 2016

massivemimobook

Book PDF and simulation code for the monograph "Massive MIMO Networks: Spectral, Energy, and Hardware Efficiency" by Emil Björnson, Jakob Hoydis and Luca Sanguinetti, published in Foundations and Trends in Signal Processing, 2017.