Nmtpynmtpy is a Python framework based on dl4mt-tutorial to experiment with Neural Machine Translation pipelines.
Stars: ✭ 127 (-35.86%)
ScanPyTorch source code for "Stacked Cross Attention for Image-Text Matching" (ECCV 2018)
Stars: ✭ 306 (+54.55%)
MerlinThis is now the official location of the Merlin project.
Stars: ✭ 1,168 (+489.9%)
DeepxiDeep Xi: A deep learning approach to a priori SNR estimation implemented in TensorFlow 2/Keras. For speech enhancement and robust ASR.
Stars: ✭ 304 (+53.54%)
Gluon2pytorchGluon to PyTorch deep neural network model converter
Stars: ✭ 70 (-64.65%)
Human Motion PredictionSimple baselines and RNNs for predicting human motion in tensorflow. Presented at CVPR 17.
Stars: ✭ 294 (+48.48%)
Coco Annotator✏️ Web-based image segmentation tool for object detection, localization, and keypoints
Stars: ✭ 1,138 (+474.75%)
Segmentation modelsSegmentation models with pretrained backbones. Keras and TensorFlow Keras.
Stars: ✭ 3,575 (+1705.56%)
ReturnnThe RWTH extensible training framework for universal recurrent neural networks
Stars: ✭ 290 (+46.46%)
Deep RankingLearning Fine-grained Image Similarity with Deep Ranking is a novel application of neural networks, where the authors use a new multi scale architecture combined with a triplet loss to create a neural network that is able to perform image search. This repository is a simplified implementation of the same
Stars: ✭ 64 (-67.68%)
Vit PytorchImplementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Stars: ✭ 7,199 (+3535.86%)
Absa kerasKeras Implementation of Aspect based Sentiment Analysis
Stars: ✭ 126 (-36.36%)
Timesformer PytorchImplementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification
Stars: ✭ 225 (+13.64%)
Global Self Attention NetworkA Pytorch implementation of Global Self-Attention Network, a fully-attention backbone for vision tasks
Stars: ✭ 64 (-67.68%)
Toolboxvarious cv tools, such as label tools, data augmentation, label conversion, etc.
Stars: ✭ 279 (+40.91%)
Pan[Params: Only 272K!!!] Efficient Image Super-Resolution Using Pixel Attention, in ECCV Workshop, 2020.
Stars: ✭ 151 (-23.74%)
Pytorch Image ClassificationTutorials on how to implement a few key architectures for image classification using PyTorch and TorchVision.
Stars: ✭ 272 (+37.37%)
TarsA deep generative model library in Theano and Lasagne
Stars: ✭ 61 (-69.19%)
Resnetcam KerasKeras implementation of a ResNet-CAM model
Stars: ✭ 269 (+35.86%)
HyperdensenetThis repository contains the code of HyperDenseNet, a hyper-densely connected CNN to segment medical images in multi-modal image scenarios.
Stars: ✭ 124 (-37.37%)
Keras VisNeural network visualization toolkit for keras
Stars: ✭ 2,900 (+1364.65%)
Feel The KernGenerating proportional fonts with deep learning
Stars: ✭ 59 (-70.2%)
Keras ResnetKeras package for deep residual networks
Stars: ✭ 257 (+29.8%)
Image CaptioningImplementation of 'X-Linear Attention Networks for Image Captioning' [CVPR 2020]
Stars: ✭ 171 (-13.64%)
MirnetOfficial repository for "Learning Enriched Features for Real Image Restoration and Enhancement" (ECCV 2020). SOTA results for image denoising, super-resolution, and image enhancement.
Stars: ✭ 247 (+24.75%)
im2pTensorflow implement of paper: A Hierarchical Approach for Generating Descriptive Image Paragraphs
Stars: ✭ 43 (-78.28%)
FixupA Re-implementation of Fixed-update Initialization
Stars: ✭ 122 (-38.38%)
icedataIceData: Datasets Hub for the *IceVision* Framework
Stars: ✭ 41 (-79.29%)
Basic nns in frameworksseveral basic neural networks[mlp, autoencoder, CNNs, recurrentNN, recursiveNN] implements under several NN frameworks[ tensorflow, pytorch, theano, keras]
Stars: ✭ 58 (-70.71%)
captioning chainerA fast implementation of Neural Image Caption by Chainer
Stars: ✭ 17 (-91.41%)
Pytorch Pose EstimationPyTorch Implementation of Realtime Multi-Person Pose Estimation project.
Stars: ✭ 152 (-23.23%)
conxThe On-Ramp to Deep Learning
Stars: ✭ 93 (-53.03%)
Ca NetCode for Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation.
Stars: ✭ 56 (-71.72%)
alpha-zeroAlphaZero implementation for Othello, Connect-Four and Tic-Tac-Toe based on "Mastering the game of Go without human knowledge" and "Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm" by DeepMind.
Stars: ✭ 68 (-65.66%)
Math object detectionAn image recognition/object detection model that detects handwritten digits and simple math operators. The output of the predicted objects (numbers & math operators) is then evaluated and solved.
Stars: ✭ 52 (-73.74%)
linformerImplementation of Linformer for Pytorch
Stars: ✭ 119 (-39.9%)
Graph attention poolAttention over nodes in Graph Neural Networks using PyTorch (NeurIPS 2019)
Stars: ✭ 186 (-6.06%)
transganformerImplementation of TransGanFormer, an all-attention GAN that combines the finding from the recent GanFormer and TransGan paper
Stars: ✭ 137 (-30.81%)
SemanticsegmentationA framework for training segmentation models in pytorch on labelme annotations with pretrained examples of skin, cat, and pizza topping segmentation
Stars: ✭ 52 (-73.74%)
ADL2019Applied Deep Learning (2019 Spring) @ NTU
Stars: ✭ 20 (-89.9%)
Yolov3 Point从零开始学习YOLOv3教程解读代码+注意力模块(SE,SPP,RFB etc)
Stars: ✭ 119 (-39.9%)
Pretrained Models.pytorchPretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
Stars: ✭ 8,318 (+4101.01%)
reweighted-wsImplementation of the reweighted wake-sleep machine learning algorithm
Stars: ✭ 39 (-80.3%)
HartHierarchical Attentive Recurrent Tracking
Stars: ✭ 149 (-24.75%)
ArnetCVPR 2018 - Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present
Stars: ✭ 94 (-52.53%)
SegmentronSupport PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)
Stars: ✭ 490 (+147.47%)
Keras Self AttentionAttention mechanism for processing sequential data that considers the context for each timestamp.
Stars: ✭ 489 (+146.97%)
RpnplusRPN+(Tensorflow) for people detection
Stars: ✭ 191 (-3.54%)
TorchdistillPyTorch-based modular, configuration-driven framework for knowledge distillation. 🏆18 methods including SOTA are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy.
Stars: ✭ 177 (-10.61%)
Facenet PytorchPretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
Stars: ✭ 2,564 (+1194.95%)