Linear Attention Recurrent Neural NetworkA 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. (LARNN)
Stars: ✭ 119 (-38.02%)
RegnetNonrigid image registration using multi-scale 3D convolutional neural networks
Stars: ✭ 151 (-21.35%)
NaszillaNaszilla is a Python library for neural architecture search (NAS)
Stars: ✭ 181 (-5.73%)
Deep image priorImage reconstruction done with untrained neural networks.
Stars: ✭ 168 (-12.5%)
ImagenetTensorFlow implementation of AlexNet and its training and testing on ImageNet ILSVRC 2012 dataset
Stars: ✭ 155 (-19.27%)
All Conv KerasAll Convolutional Network: (https://arxiv.org/abs/1412.6806#) implementation in Keras
Stars: ✭ 115 (-40.1%)
Stock Price PredictorThis project seeks to utilize Deep Learning models, Long-Short Term Memory (LSTM) Neural Network algorithm, to predict stock prices.
Stars: ✭ 146 (-23.96%)
Deep K Means Pytorch[ICML 2018] "Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions"
Stars: ✭ 115 (-40.1%)
OsmdeepodOSMDeepOD - OpenStreetMap (OSM) and Machine Learning (Deep Learning) based Object Detection from Aerial Imagery (Formerly also known as "OSM-Crosswalk-Detection").
Stars: ✭ 174 (-9.37%)
Models Comparison.pytorch Code for the paper Benchmark Analysis of Representative Deep Neural Network Architectures
Stars: ✭ 148 (-22.92%)
Rnn Text Classification TfTensorflow Implementation of Recurrent Neural Network (Vanilla, LSTM, GRU) for Text Classification
Stars: ✭ 114 (-40.62%)
IresnetImproved Residual Networks (https://arxiv.org/pdf/2004.04989.pdf)
Stars: ✭ 163 (-15.1%)
DeepgazeComputer Vision library for human-computer interaction. It implements Head Pose and Gaze Direction Estimation Using Convolutional Neural Networks, Skin Detection through Backprojection, Motion Detection and Tracking, Saliency Map.
Stars: ✭ 1,552 (+708.33%)
Arc PytorchThe first public PyTorch implementation of Attentive Recurrent Comparators
Stars: ✭ 147 (-23.44%)
GninaA deep learning framework for molecular docking
Stars: ✭ 183 (-4.69%)
Shiftresnet CifarResNet with Shift, Depthwise, or Convolutional Operations for CIFAR-100, CIFAR-10 on PyTorch
Stars: ✭ 112 (-41.67%)
Cs231n Convolutional Neural Networks SolutionsAssignment solutions for the CS231n course taught by Stanford on visual recognition. Spring 2017 solutions are for both deep learning frameworks: TensorFlow and PyTorch.
Stars: ✭ 110 (-42.71%)
SruSRU is a recurrent unit that can run over 10 times faster than cuDNN LSTM, without loss of accuracy tested on many tasks.
Stars: ✭ 2,009 (+946.35%)
DensepointDensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing (ICCV 2019)
Stars: ✭ 110 (-42.71%)
Facedet实现常用基于深度学习的人脸检测算法
Stars: ✭ 109 (-43.23%)
Deep SpyingSpying using Smartwatch and Deep Learning
Stars: ✭ 172 (-10.42%)
ExermoteUsing Machine Learning to predict the type of exercise from movement data
Stars: ✭ 108 (-43.75%)
LivianetThis repository contains the code of LiviaNET, a 3D fully convolutional neural network that was employed in our work: "3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study"
Stars: ✭ 143 (-25.52%)
NltkNLTK Source
Stars: ✭ 10,309 (+5269.27%)
Cs231nMy assignment solutions for CS231n - Convolutional Neural Networks for Visual Recognition
Stars: ✭ 162 (-15.62%)
Mp Cnn TorchMulti-Perspective Convolutional Neural Networks for modeling textual similarity (He et al., EMNLP 2015)
Stars: ✭ 106 (-44.79%)
Attribute Aware Attention[ACM MM 2018] Attribute-Aware Attention Model for Fine-grained Representation Learning
Stars: ✭ 143 (-25.52%)
Idn CaffeCaffe implementation of "Fast and Accurate Single Image Super-Resolution via Information Distillation Network" (CVPR 2018)
Stars: ✭ 104 (-45.83%)
SimpsonrecognitionDetect and recognize The Simpsons characters using Keras and Faster R-CNN
Stars: ✭ 131 (-31.77%)
Sparse Winograd CnnEfficient Sparse-Winograd Convolutional Neural Networks (ICLR 2018)
Stars: ✭ 156 (-18.75%)
Antialiased Cnnspip install antialiased-cnns to improve stability and accuracy
Stars: ✭ 1,363 (+609.9%)
AutoclintA specially designed light version of Fast AutoAugment
Stars: ✭ 171 (-10.94%)
Mad TwinnetThe code for the MaD TwinNet. Demo page:
Stars: ✭ 99 (-48.44%)
Crypto RnnLearning the Enigma with Recurrent Neural Networks
Stars: ✭ 139 (-27.6%)
AwslambdafacePerform deep neural network based face detection and recognition in the cloud (via AWS lambda) with zero model configuration or tuning.
Stars: ✭ 98 (-48.96%)
Keras LmuKeras implementation of Legendre Memory Units
Stars: ✭ 160 (-16.67%)
Pytorch EsnAn Echo State Network module for PyTorch.
Stars: ✭ 98 (-48.96%)
Har Keras CnnHuman Activity Recognition (HAR) with 1D Convolutional Neural Network in Python and Keras
Stars: ✭ 97 (-49.48%)
Ml Systemspapers on scalable and efficient machine learning systems
Stars: ✭ 182 (-5.21%)
WsddnWeakly Supervised Deep Detection Networks (CVPR 2016)
Stars: ✭ 138 (-28.12%)
CnniqaCVPR2014-Convolutional neural networks for no-reference image quality assessment
Stars: ✭ 96 (-50%)
Motion SenseMotionSense Dataset for Human Activity and Attribute Recognition ( time-series data generated by smartphone's sensors: accelerometer and gyroscope)
Stars: ✭ 159 (-17.19%)
Pytorch Kaldipytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
Stars: ✭ 2,097 (+992.19%)
Speech signal processing and classificationFront-end speech processing aims at extracting proper features from short- term segments of a speech utterance, known as frames. It is a pre-requisite step toward any pattern recognition problem employing speech or audio (e.g., music). Here, we are interesting in voice disorder classification. That is, to develop two-class classifiers, which can discriminate between utterances of a subject suffering from say vocal fold paralysis and utterances of a healthy subject.The mathematical modeling of the speech production system in humans suggests that an all-pole system function is justified [1-3]. As a consequence, linear prediction coefficients (LPCs) constitute a first choice for modeling the magnitute of the short-term spectrum of speech. LPC-derived cepstral coefficients are guaranteed to discriminate between the system (e.g., vocal tract) contribution and that of the excitation. Taking into account the characteristics of the human ear, the mel-frequency cepstral coefficients (MFCCs) emerged as descriptive features of the speech spectral envelope. Similarly to MFCCs, the perceptual linear prediction coefficients (PLPs) could also be derived. The aforementioned sort of speaking tradi- tional features will be tested against agnostic-features extracted by convolu- tive neural networks (CNNs) (e.g., auto-encoders) [4]. The pattern recognition step will be based on Gaussian Mixture Model based classifiers,K-nearest neighbor classifiers, Bayes classifiers, as well as Deep Neural Networks. The Massachussets Eye and Ear Infirmary Dataset (MEEI-Dataset) [5] will be exploited. At the application level, a library for feature extraction and classification in Python will be developed. Credible publicly available resources will be 1used toward achieving our goal, such as KALDI. Comparisons will be made against [6-8].
Stars: ✭ 155 (-19.27%)
Pytorch Vfi CftGenerate slow-motion videos by interpolating more frames
Stars: ✭ 130 (-32.29%)
Deep LyricsLyrics Generator aka Character-level Language Modeling with Multi-layer LSTM Recurrent Neural Network
Stars: ✭ 127 (-33.85%)
Bilinear Cnn TensorflowThis is an implementation of Bilinear CNN for fine grained visual recognition using TensorFlow.
Stars: ✭ 187 (-2.6%)
VidaugEffective Video Augmentation Techniques for Training Convolutional Neural Networks
Stars: ✭ 178 (-7.29%)