address-netA package to structure Australian addresses
Stars: ✭ 171 (+194.83%)
tiny-rnnLightweight C++11 library for building deep recurrent neural networks
Stars: ✭ 41 (-29.31%)
catacombThe simplest machine learning library for launching UIs, running evaluations, and comparing model performance.
Stars: ✭ 13 (-77.59%)
mtad-gat-pytorchPyTorch implementation of MTAD-GAT (Multivariate Time-Series Anomaly Detection via Graph Attention Networks) by Zhao et. al (2020, https://arxiv.org/abs/2009.02040).
Stars: ✭ 85 (+46.55%)
Mozi此项目致力于构建一套最基础,最精简,可维护的react-native项目,支持ios,android 🌹
Stars: ✭ 501 (+763.79%)
reasoning attentionUnofficial implementation algorithms of attention models on SNLI dataset
Stars: ✭ 34 (-41.38%)
pkgcheckpkgcore-based QA utility for ebuild repos
Stars: ✭ 19 (-67.24%)
bert attn vizVisualize BERT's self-attention layers on text classification tasks
Stars: ✭ 41 (-29.31%)
Clockwork-RNNThis repository is a reproduction of the clockwork RNN paper.
Stars: ✭ 20 (-65.52%)
aquality-selenium-javaAquality Selenium is a library built over Selenium WebDriver tool that allows to automate work with web browsers. Selenium WebDriver requires some skill and experience. So, Aquality Selenium suggests simplified and most importantly safer and more stable way to work with Selenium WebDriver.
Stars: ✭ 41 (-29.31%)
RganRecurrent (conditional) generative adversarial networks for generating real-valued time series data.
Stars: ✭ 480 (+727.59%)
AiROfficial Repository for ECCV 2020 paper "AiR: Attention with Reasoning Capability"
Stars: ✭ 41 (-29.31%)
MobileQA离线端阅读理解应用 QA for mobile, Android & iPhone
Stars: ✭ 49 (-15.52%)
MetaTraderForecastRNN based Forecasting App for Meta Trader and similar trading platforms
Stars: ✭ 103 (+77.59%)
Pytorch GatMy implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!
Stars: ✭ 908 (+1465.52%)
Attention一些不同的Attention机制代码
Stars: ✭ 17 (-70.69%)
tensorflow-chatbot-chinese網頁聊天機器人 | tensorflow implementation of seq2seq model with bahdanau attention and Word2Vec pretrained embedding
Stars: ✭ 50 (-13.79%)
Rnn NluA TensorFlow implementation of Recurrent Neural Networks for Sequence Classification and Sequence Labeling
Stars: ✭ 463 (+698.28%)
ACTAlternative approach for Adaptive Computation Time in TensorFlow
Stars: ✭ 16 (-72.41%)
Boilerplate Dynet Rnn LmBoilerplate code for quickly getting set up to run language modeling experiments
Stars: ✭ 37 (-36.21%)
nemesystGeneralised and highly customisable, hybrid-parallelism, database based, deep learning framework.
Stars: ✭ 17 (-70.69%)
TCN-TFTensorFlow Implementation of TCN (Temporal Convolutional Networks)
Stars: ✭ 107 (+84.48%)
dreyeve[TPAMI 2018] Predicting the Driver’s Focus of Attention: the DR(eye)VE Project. A deep neural network learnt to reproduce the human driver focus of attention (FoA) in a variety of real-world driving scenarios.
Stars: ✭ 88 (+51.72%)
StagyStagy is a tool for quick deployment of staging environments.
Stars: ✭ 19 (-67.24%)
STAR Network[PAMI 2021] Gating Revisited: Deep Multi-layer RNNs That Can Be Trained
Stars: ✭ 16 (-72.41%)
Dense BiLSTMTensorflow Implementation of Densely Connected Bidirectional LSTM with Applications to Sentence Classification
Stars: ✭ 48 (-17.24%)
Market-Trend-PredictionThis is a project of build knowledge graph course. The project leverages historical stock price, and integrates social media listening from customers to predict market Trend On Dow Jones Industrial Average (DJIA).
Stars: ✭ 57 (-1.72%)
Mac NetworkImplementation for the paper "Compositional Attention Networks for Machine Reasoning" (Hudson and Manning, ICLR 2018)
Stars: ✭ 444 (+665.52%)
presidential-rnnProject 4 for Metis bootcamp. Objective was generation of character-level RNN trained on Donald Trump's statements using Keras. Also generated Markov chains, and quick pyTorch RNN as baseline. Attempted semi-supervised GAN, but was unable to test in time.
Stars: ✭ 26 (-55.17%)
Sequence-Models-courseraSequence Models by Andrew Ng on Coursera. Programming Assignments and Quiz Solutions.
Stars: ✭ 53 (-8.62%)
lstm-attentionAttention-based bidirectional LSTM for Classification Task (ICASSP)
Stars: ✭ 87 (+50%)
Selected StoriesAn experimental web text editor that runs a LSTM model while you write to suggest new lines
Stars: ✭ 39 (-32.76%)
srcinvsource code audit tool
Stars: ✭ 45 (-22.41%)
PFL-Non-IIDThe origin of the Non-IID phenomenon is the personalization of users, who generate the Non-IID data. With Non-IID (Not Independent and Identically Distributed) issues existing in the federated learning setting, a myriad of approaches has been proposed to crack this hard nut. In contrast, the personalized federated learning may take the advantage…
Stars: ✭ 58 (+0%)
deep-learning-notes🧠👨💻Deep Learning Specialization • Lecture Notes • Lab Assignments
Stars: ✭ 20 (-65.52%)
FlauiUI automation library for .Net
Stars: ✭ 892 (+1437.93%)
RnnsharpRNNSharp is a toolkit of deep recurrent neural network which is widely used for many different kinds of tasks, such as sequence labeling, sequence-to-sequence and so on. It's written by C# language and based on .NET framework 4.6 or above versions. RNNSharp supports many different types of networks, such as forward and bi-directional network, sequence-to-sequence network, and different types of layers, such as LSTM, Softmax, sampled Softmax and others.
Stars: ✭ 277 (+377.59%)
Customer-Feedback-AnalysisMulti Class Text (Feedback) Classification using CNN, GRU Network and pre trained Word2Vec embedding, word embeddings on TensorFlow.
Stars: ✭ 18 (-68.97%)
FARED for Anomaly DetectionOfficial source code of "Fast Adaptive RNN Encoder-Decoder for Anomaly Detection in SMD Assembly Machine"
Stars: ✭ 14 (-75.86%)
VadVoice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD. We also provide our directly recorded dataset.
Stars: ✭ 622 (+972.41%)
Mcan VqaDeep Modular Co-Attention Networks for Visual Question Answering
Stars: ✭ 273 (+370.69%)