Neural spEnd-to-end ASR/LM implementation with PyTorch
Stars: ✭ 408 (+221.26%)
SightseqComputer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection
Stars: ✭ 116 (-8.66%)
Speech TransformerA PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.
Stars: ✭ 565 (+344.88%)
Text ClassificationImplementation of papers for text classification task on DBpedia
Stars: ✭ 682 (+437.01%)
HyperdensenetThis repository contains the code of HyperDenseNet, a hyper-densely connected CNN to segment medical images in multi-modal image scenarios.
Stars: ✭ 124 (-2.36%)
NmtpytorchSequence-to-Sequence Framework in PyTorch
Stars: ✭ 392 (+208.66%)
3d Densenet3D Dense Connected Convolutional Network (3D-DenseNet for action recognition)
Stars: ✭ 118 (-7.09%)
EesenThe official repository of the Eesen project
Stars: ✭ 738 (+481.1%)
torch-asgAuto Segmentation Criterion (ASG) implemented in pytorch
Stars: ✭ 42 (-66.93%)
Asrt speechrecognitionA Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
Stars: ✭ 4,943 (+3792.13%)
Caffe ocr主流ocr算法研究实验性的项目,目前实现了CNN+BLSTM+CTC架构
Stars: ✭ 1,156 (+810.24%)
Eeg DlA Deep Learning library for EEG Tasks (Signals) Classification, based on TensorFlow.
Stars: ✭ 165 (+29.92%)
KerasdeepspeechA Keras CTC implementation of Baidu's DeepSpeech for model experimentation
Stars: ✭ 245 (+92.91%)
Keras SincnetKeras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)
Stars: ✭ 47 (-62.99%)
ctc-asrEnd-to-end trained speech recognition system, based on RNNs and the connectionist temporal classification (CTC) cost function.
Stars: ✭ 112 (-11.81%)
AESRC2020a deep accent recognition network
Stars: ✭ 35 (-72.44%)
Pytorch classification利用pytorch实现图像分类的一个完整的代码,训练,预测,TTA,模型融合,模型部署,cnn提取特征,svm或者随机森林等进行分类,模型蒸馏,一个完整的代码
Stars: ✭ 395 (+211.02%)
Deeplearning Nlp ModelsA small, interpretable codebase containing the re-implementation of a few "deep" NLP models in PyTorch. Colab notebooks to run with GPUs. Models: word2vec, CNNs, transformer, gpt.
Stars: ✭ 64 (-49.61%)
SincnetSincNet is a neural architecture for efficiently processing raw audio samples.
Stars: ✭ 764 (+501.57%)
Athenaan open-source implementation of sequence-to-sequence based speech processing engine
Stars: ✭ 542 (+326.77%)
CaptcharecognitionEnd-to-end variable length Captcha recognition using CNN+RNN+Attention/CTC (pytorch implementation). 端到端的不定长验证码识别
Stars: ✭ 97 (-23.62%)
Id Card Detector💳 Detecting the National Identification Cards with Deep Learning (Faster R-CNN)
Stars: ✭ 114 (-10.24%)
DeepfaceKeras implementation of the renowned publication "DeepFace: Closing the Gap to Human-Level Performance in Face Verification" by Taigman et al. Pre-trained weights on VGGFace2 dataset.
Stars: ✭ 113 (-11.02%)
Text recognition toolboxtext_recognition_toolbox: The reimplementation of a series of classical scene text recognition papers with Pytorch in a uniform way.
Stars: ✭ 114 (-10.24%)
Ccnet Pure PytorchCriss-Cross Attention for Semantic Segmentation in pure Pytorch with a faster and more precise implementation.
Stars: ✭ 124 (-2.36%)
FastpunctPunctuation restoration and spell correction experiments.
Stars: ✭ 121 (-4.72%)
Leader LineDraw a leader line in your web page.
Stars: ✭ 1,872 (+1374.02%)
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 (+1122.05%)
Tf2An Open Source Deep Learning Inference Engine Based on FPGA
Stars: ✭ 113 (-11.02%)
LibfacedetectionAn open source library for face detection in images. The face detection speed can reach 1000FPS.
Stars: ✭ 10,852 (+8444.88%)
Mobilenet YoloMobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB🔥🔥🔥
Stars: ✭ 1,566 (+1133.07%)
Pwc Net pytorchpytorch implementation of "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume"
Stars: ✭ 111 (-12.6%)
Mnist ClassificationPytorch、Scikit-learn实现多种分类方法,包括逻辑回归(Logistic Regression)、多层感知机(MLP)、支持向量机(SVM)、K近邻(KNN)、CNN、RNN,极简代码适合新手小白入门,附英文实验报告(ACM模板)
Stars: ✭ 109 (-14.17%)
DeepwayThis project is an aid to the blind. Till date there has been no technological advancement in the way the blind navigate. So I have used deep learning particularly convolutional neural networks so that they can navigate through the streets.
Stars: ✭ 118 (-7.09%)
Numpy MlMachine learning, in numpy
Stars: ✭ 11,100 (+8640.16%)
Lambda NetworksImplementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute
Stars: ✭ 1,497 (+1078.74%)
Captcha基于CNN的验证码整体识别
Stars: ✭ 125 (-1.57%)
Cnn Inference Engine Quick ViewA quick view of high-performance convolution neural networks (CNNs) inference engines on mobile devices.
Stars: ✭ 124 (-2.36%)
Places365The Places365-CNNs for Scene Classification
Stars: ✭ 1,549 (+1119.69%)
DeepspeechrecognitionA Chinese Deep Speech Recognition System 包括基于深度学习的声学模型和基于深度学习的语言模型
Stars: ✭ 1,421 (+1018.9%)
Min nlp practiceChinese & English Cws Pos Ner Entity Recognition implement using CNN bi-directional lstm and crf model with char embedding.基于字向量的CNN池化双向BiLSTM与CRF模型的网络,可能一体化的完成中文和英文分词,词性标注,实体识别。主要包括原始文本数据,数据转换,训练脚本,预训练模型,可用于序列标注研究.注意:唯一需要实现的逻辑是将用户数据转化为序列模型。分词准确率约为93%,词性标注准确率约为90%,实体标注(在本样本上)约为85%。
Stars: ✭ 107 (-15.75%)