dorniwang Goto Github PK

repvgg

RepVGG: Making VGG-style ConvNets Great Again

res-loglikelihood-regression

Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral

research

comma.ai for the people to experiment with

resnet-1k-layers

Deep Residual Networks with 1K Layers

resnet.torch

an updated version of fb.resnet.torch with many changes.

review_net

Review Network for Caption Generation

ringnet

Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

rl4j

Deep Reinforcement Learning for the JVM

rnn-tutorial-gru-lstm

Language Model GRU with Python and Theano

rnn-tutorial-rnnlm

Recurrent Neural Network Tutorial, Part 2 - Implementing a RNN in Python and Theano

ru-dalle

Generate images from texts. In Russian

sam

sam-1

SAM: Sharpness-Aware Minimization (PyTorch)

samplecode

Sample Code

scalismo

Scalable Image Analysis and Shape Modelling

scalismo-faces

Scalable Image Analysis and Shape Modelling: Module to work with 2d images, with a focus on face images

scipy-lecture-notes

Tutorial material on the scientific Python ecosystem

sdm

Supervised Descent Method Apply to Face Alignment, and Head Pose Estimation with Linear Regression. It is cross-platfrom, easily compile in windows, ubuntu, even in Android & iOS.

semanticsoftsegmentation

Spectral segmentation described in Aksoy et al., "Semantic Soft Segmentation", ACM TOG (Proc. SIGGRAPH), 2018

shufflenet-v2-tensorflow

a lightweight convolutional neural network

shufflenet-v2-tensorflow-1

Tensorflow ShuffleNet v2 implementation

siamese-fc

State-of-the-art performance in arbitrary object tracking at 50-100 FPS with Fully Convolutional Siamese networks.

siggraph18sss

SIGGRAPH2018, Semantic Soft Segmentation, http://people.inf.ethz.ch/aksoyy/sss/

slambook

snake_cuda8

Deep Snake for Real-Time Instance Segmentation,pytorch1.0,cuda8.0

sobolev-reg-of-sgd

The Sobolev Regularization Effect of Stocahstic Gradient Descent

soundnet

SoundNet: Learning Sound Representations from Unlabeled Video. NIPS 2016

spleeter

Deezer source separation library including pretrained models.

squeezenet

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters

srn

Selective Refinement Network for High Performance Face Detection, AAAI, 2019