Deep Learning

Frameworks for Neural Networks and Deep Learning.

Newest releases

brade31919 Source code of the IROS 2020 paper "Depth Estimation from Monocular Images and Sparse Radar Data"
 

ivanpanshin Implementation of Supervised Contrastive Learning with AMP, EMA, SWA, and many other tricks
 

twistedcubic Neural LSH [ICLR 2020] - Using supervised learning to produce better space partitions for fast nearest neighbor search.
 

YueWuHKUST Official implementation of Paper "Future Video Synthesis With Object Motion Prediction"(CVPR 2020)
 

google-research World Models is a platform-agnostic library to facilitate visual based agents for planning. This notebook (run it in colab) shows how to use World Models library and its different components.
 

jackwish This tflite package parses TensorFlow Lite (TFLite) models (*.tflite), which are built by TFLite converter. For background, please refer to Introducing TFLite Parser Python Package.
 

fastai timm is a deep-learning library created by Ross Wightman and is a collection of SOTA computer vision models, layers, utilities, optimizers, schedulers, data-loaders, augmentations and also training/validating scripts with ability
 

itayhubara Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming
 

berenslab Companion repository to Lause, Berens & Kobak (2020): "Analytic Pearson residuals for normalization of single-cell RNA-seq UMI data", bioRxiv
 

alessiabertugli PyTorch code for NeurIPSW 2020 paper (4th Workshop on Meta-Learning) "Few-Shot Unsupervised Continual Learning through Meta-Examples"
 

EvgenyKashin Implementation of Spectral Leakage and Rethinking the Kernel Size in CNNs in Pytorch
 

lucidrains Simple implementation of Feedback Transformer in Pytorch.
 

filipsPL tl;dr / abstract. System which can be used for localization the position of a cat in a building using bluetooth low energy (BLE) beacons attached to the object, a set of cheap ESP32 detectors, and Machine Learning models.
 

galatolofederico Repository for the paper Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search
 

XanaduAI Contains material for the PennyLane tutorial at CERN on 3/4 February 2021.
 

terryyz PyArmadillo is a linear algebra library for the Python language, with an emphasis on ease of use.
 

NVlabs StyleGAN2-ADA — Official PyTorch implementation
 

cfzd PyTorch implementation of the paper "FcaNet: Frequency Channel Attention Networks".
 

willi-menapace This paper introduces the unsupervised learning problem of playable video generation (PVG). In PVG, we aim at allowing a user to control the generated video by selecting a discrete action at every time step as when playing a video
 

tfzhou Exploring Cross-Image Pixel Contrast for Semantic Segmentation
 

zhaoyuzhi This page is for paper SCGAN: Saliency Map-guided Colorization with Generative Adversarial Network pubished on IEEE Transactions on Circuits and Systems for Video Technology (TCSVT).
 

haqishen SIIM-ISIC-Melanoma-Classification-1st-Place-Solution
 

deeplearningbrasil MARS-Gym (MArketplace Recommender Systems Gym), a benchmark framework for modeling, training, and evaluating RL-based recommender systems for marketplaces.
 

MCG-NJU Learning Spatiotemporal Features via Video and Text Pair Discrimination
 

SysCV This is the offical implementation of paper Quasi-Dense Similarity Learning for Multiple Object Tracking.
 

joaoantoniocn The Additive Margin MobileNet1D is a new light weight deep learning model for Speaker Recognition which is based on the MobileNetV2 architecture and the Additive Margin Softmax (AM-Softmax) loss function.)
 

achen353 Training and fine-tuning YOLOv4 Tiny on custom object detection dataset for Taiwanese traffic
 

colorjam PAMS: Quantized Super-Resolution via Parameterized Max Scale
 

EscVM Official TensorFlow code for the forthcoming paper "Efficient-CapsNet: Capsule Network with Self-Attention Routing".
 

Jacobsolawetz LSOIE: A Large-Scale Dataset for Supervised Open Information Extraction (EACL 2021), along with the training procedures necessary to train your open information extractor from these data, and finally, you will find evaluation tec
 

feiaxyt 1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking
 

baxtree Automatically synchronize subtitles to audiovisual content with a pretrained deep neural network and forced alignments
 

HughWen Serving Agent is designed as a middleware for model serving between web server and model server to help the server improve the GPU utilization then speedup online inference.