Pinned Repositories
3d-ken-burns
an implementation of 3D Ken Burns Effect from a Single Image using PyTorch
A-Light-and-Fast-Face-Detector-for-Edge-Devices
a light and fast face detector for edge devices
ACNet
ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
AdaBound
An optimizer that trains as fast as Adam and as good as SGD.
AdamW-and-SGDW
Fixing Weight Decay Regularization in Adam
adaptive-threshold
deepFashion3D
3D Real Garment Dataset
Detectron2-deepfashion2
Learning-Similarity-Conditions
nerf
Code release for NeRF (Neural Radiance Fields)
chaoso's Repositories
chaoso/C-Steganography-Framework
C code to decode a JPEG and provide access to the DCT coefficients
chaoso/caffe-tensorflow
Caffe models in TensorFlow
chaoso/dct_simd
SIMD implementation of 4x4 and 8x8 Fast DCT with OpenCV demo
chaoso/epeg
Insanely fast JPEG/ JPG thumbnail scaling with the minimum fuss and CPU overhead. It makes use of libjpeg features of being able to load an image by only decoding the DCT coefficients needed to reconstruct an image of the size desired.
chaoso/fashion-landmarks
Fashion Landmark Detection in the Wild
chaoso/High-Dimensional-LBP
My implementation of high dimensional LBP feature for face recognition
chaoso/jpeg_toolbox_python
extract the dct coefficient of jpeg images. Provide c and python interface.
chaoso/L-GM-loss
Implementation of our accepted CVPR 2018 paper "Rethinking Feature Distribution for Loss Functions in Image Classification"
chaoso/pre-resnet-gen-caffe
Generate Caffe prototxt of pre-activation ResNet on ImageNet
chaoso/pyjpeg-dct
WIP Python interface to libjpeg to access DCT coefficients
chaoso/pyspark-hbase
自用
chaoso/pythonConvertCifar-10
convert cifar-10 dataset from bin to png or jpg
chaoso/spiralNet
Looking at the manifold hypothesis in deep learning. Creating a simple spiral dataset allows me to reveal how neural networks follow an optimal packing strategy during their training.
chaoso/webvision
An exploratory project which wants to find ways to learn from noisy data
chaoso/wsn_DC_arm_dct_dctQuanLossless
dctQuanLossless方法，VS平台采用ARM DCT变换代码，WSN
chaoso/youtube8m
:arrow_forward: Repository for our CVPR 2017 workshop paper: Encoding Video and Label Priors for Multi-label Video Classification on YouTube-8M dataset