laikaExperiments with satellite image data
Stars: ✭ 97 (+24.36%)
Pytorch Seq2seqTutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
Stars: ✭ 3,418 (+4282.05%)
Rnn pytorchUsing the Pytorch to build an image temporal prediction model of the encoder-forecaster structure, ConvGRU kernel & ConvLSTM kernel
Stars: ✭ 83 (+6.41%)
DeepharmonizationDemo code of the paper: "Deep Image Harmonization", Y.-H. Tsai, X. Shen, Z. Lin, K. Sunkavalli, X. Lu and M.-H. Yang, CVPR 2017
Stars: ✭ 120 (+53.85%)
badcharsBad char generator to instruct encoders such as shikata-ga-nai to transform those to other chars.
Stars: ✭ 178 (+128.21%)
Gec PseudodataRepository of "An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction" (EMNLP-IJCNLP 2019)
Stars: ✭ 49 (-37.18%)
S-DCNetUnofficial Pytorch implementation of S-DCNet and SS-DCNet
Stars: ✭ 17 (-78.21%)
Semantic Segmentation SuiteSemantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!
Stars: ✭ 2,395 (+2970.51%)
FfmpegcommandFFmpegCommand适用于Android的FFmpeg命令库,实现了对音视频相关的处理,能够快速的处理音视频,大概功能包括:音视频剪切,音视频转码,音视频解码原始数据,音视频编码,视频转图片或gif,视频添加水印,多画面拼接,音频混音,视频亮度和对比度,音频淡入和淡出效果等
Stars: ✭ 394 (+405.13%)
DeepchatmodelsConversation models in TensorFlow. (website removed)
Stars: ✭ 312 (+300%)
AvroA fast Go Avro codec
Stars: ✭ 132 (+69.23%)
MARUNetMulti-level Attention Refined UNet for crowd counting
Stars: ✭ 30 (-61.54%)
CSRNet-kerasImplementation of the CSRNet paper (CVPR 18) in keras-tensorflow
Stars: ✭ 107 (+37.18%)
Image captioninggenerate captions for images using a CNN-RNN model that is trained on the Microsoft Common Objects in COntext (MS COCO) dataset
Stars: ✭ 51 (-34.62%)
ailia-modelsThe collection of pre-trained, state-of-the-art AI models for ailia SDK
Stars: ✭ 1,102 (+1312.82%)
Simple Binary EncodingSimple Binary Encoding (SBE) - High Performance Message Codec
Stars: ✭ 2,544 (+3161.54%)
Transformer Temporal TaggerCode and data form the paper BERT Got a Date: Introducing Transformers to Temporal Tagging
Stars: ✭ 55 (-29.49%)
Rnn For Joint NluPytorch implementation of "Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling" (https://arxiv.org/abs/1609.01454)
Stars: ✭ 176 (+125.64%)
Multi Scale AttentionCode for our paper "Multi-scale Guided Attention for Medical Image Segmentation"
Stars: ✭ 281 (+260.26%)
Encoder decoderFour styles of encoder decoder model by Python, Theano, Keras and Seq2Seq
Stars: ✭ 269 (+244.87%)
DekuDeclarative binary reading and writing: bit-level, symmetric, serialization/deserialization
Stars: ✭ 136 (+74.36%)
CrowdFlowOptical Flow Dataset and Benchmark for Visual Crowd Analysis
Stars: ✭ 87 (+11.54%)
Abstractive SummarizationImplementation of abstractive summarization using LSTM in the encoder-decoder architecture with local attention.
Stars: ✭ 128 (+64.1%)
Crowd-Counting-with-MCNNsCrowd counting on the ShanghaiTech dataset, using multi-column convolutional neural networks.
Stars: ✭ 23 (-70.51%)
KarkinosPenetration Testing and Hacking CTF's Swiss Army Knife with: Reverse Shell Handling - Encoding/Decoding - Encryption/Decryption - Cracking Hashes / Hashing
Stars: ✭ 115 (+47.44%)
Smart-City-SampleThe smart city reference pipeline shows how to integrate various media building blocks, with analytics powered by the OpenVINO™ Toolkit, for traffic or stadium sensing, analytics and management tasks.
Stars: ✭ 141 (+80.77%)
Screen Recorder Ffmpeg Cpp*Multimedia project* A screen recording application to capture your desktop and store in a video format. Click here to watch the demo
Stars: ✭ 98 (+25.64%)
PyramidScaleNetworkTo the best of our knowledge, this is the first work to explicitly address feature similarity issue in multi-column design. Extensive experiments on four challenging benchmarks (ShanghaiTech, UCF_CC_50, UCF-QNRF, and Mall) demonstrate the effectiveness of the proposed innovations as well as the superior performance over the state-of-the-art. Mor…
Stars: ✭ 17 (-78.21%)
Deeplab v3 plusThis is an ongoing re-implementation of DeepLab_v3_plus on pytorch which is trained on VOC2012 and use ResNet101 for backbone.
Stars: ✭ 83 (+6.41%)
Image SegmentationImplementation of FCN (8/16/32) in Tensorflow. 🌀 在TensorFlow框架下实现 FCN (全卷积神经网络) 。
Stars: ✭ 19 (-75.64%)
udacity-cvnd-projectsMy solutions to the projects assigned for the Udacity Computer Vision Nanodegree
Stars: ✭ 36 (-53.85%)
TextboxTextBox is an open-source library for building text generation system.
Stars: ✭ 257 (+229.49%)
SockeyeSequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet
Stars: ✭ 990 (+1169.23%)
Speech recognition with tensorflowImplementation of a seq2seq model for Speech Recognition using the latest version of TensorFlow. Architecture similar to Listen, Attend and Spell.
Stars: ✭ 253 (+224.36%)
Deep Visual Attention PredictionKeras implementation of paper 'Deep Visual Attention Prediction' which predicts human eye fixation on view-free scenes.
Stars: ✭ 19 (-75.64%)
pixel-decoderA tool for running deep learning algorithms for semantic segmentation with satellite imagery
Stars: ✭ 68 (-12.82%)
Ffmpegandroid最新版ffmpeg3.3-android,并通过CMake方式移植到Android中,并实现编解码,转码,推拉流,滤镜等各种功能
Stars: ✭ 526 (+574.36%)
Text summarization with tensorflowImplementation of a seq2seq model for summarization of textual data. Demonstrated on amazon reviews, github issues and news articles.
Stars: ✭ 226 (+189.74%)
NeuralmonkeyAn open-source tool for sequence learning in NLP built on TensorFlow.
Stars: ✭ 400 (+412.82%)
NeuralCodeTranslatorNeural Code Translator provides instructions, datasets, and a deep learning infrastructure (based on seq2seq) that aims at learning code transformations
Stars: ✭ 32 (-58.97%)
Tf Seq2seqSequence to sequence learning using TensorFlow.
Stars: ✭ 387 (+396.15%)
Screenshot To CodeA neural network that transforms a design mock-up into a static website.
Stars: ✭ 13,561 (+17285.9%)
crowd-countingImage Crowd Counting Using Convolutional Neural Network and Markov Random Field
Stars: ✭ 32 (-58.97%)
Slot filling and intent detection of sluslot filling, intent detection, joint training, ATIS & SNIPS datasets, the Facebook’s multilingual dataset, MIT corpus, E-commerce Shopping Assistant (ECSA) dataset, CoNLL2003 NER, ELMo, BERT, XLNet
Stars: ✭ 298 (+282.05%)
BasecrackDecode All Bases - Base Scheme Decoder
Stars: ✭ 196 (+151.28%)
Rxffmpeg🔥💥RxFFmpeg 是基于 ( FFmpeg 4.0 + X264 + mp3lame + fdk-aac + opencore-amr + openssl ) 编译的适用于 Android 平台的音视频编辑、视频剪辑的快速处理框架,包含以下功能:视频拼接,转码,压缩,裁剪,片头片尾,分离音视频,变速,添加静态贴纸和gif动态贴纸,添加字幕,添加滤镜,添加背景音乐,加速减速视频,倒放音视频,音频裁剪,变声,混音,图片合成视频,视频解码图片,抖音首页,视频播放器及支持 OpenSSL https 等主流特色功能
Stars: ✭ 3,358 (+4205.13%)
NWPU-Crowd-Sample-CodeThe sample code for a large-scale crowd counting dataset, NWPU-Crowd.
Stars: ✭ 140 (+79.49%)
Deep News SummarizationNews summarization using sequence to sequence model with attention in TensorFlow.
Stars: ✭ 167 (+114.1%)
util封装了一些Java常用的功能
Stars: ✭ 19 (-75.64%)
W-Net-KerasAn unofficial implementation of W-Net for crowd counting.
Stars: ✭ 20 (-74.36%)
IIMPyTorch implementations of the paper: "Learning Independent Instance Maps for Crowd Localization"
Stars: ✭ 94 (+20.51%)
Androidcamera🔥🔥🔥自定义Android相机(仿抖音 TikTok),其中功能包括视频人脸识别贴纸,美颜,分段录制,视频裁剪,视频帧处理,获取视频关键帧,视频旋转,添加滤镜,添加水印,合成Gif到视频,文字转视频,图片转视频,音视频合成,音频变声处理,SoundTouch,Fmod音频处理。 Android camera(imitation Tik Tok), which includes video editor,audio editor,video face recognition stickers, segment recording,video cropping, video frame processing, get the first video frame, key frame, v…
Stars: ✭ 2,112 (+2607.69%)