Pinned Repositories
BiSeNet
Add bisenetv2. My implementation of BiSeNet
Deeplab-Large-FOV
My Implementation of the deeplab_v1 (known as deeplab large fov)
DeepLab-v3-plus-cityscapes
mIOU=80.02 on cityscapes. My implementation of deeplabv3+ (also know as 'Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation' based on the dataset of cityscapes).
DenseCL
DenseCL + regionCL-D
fixmatch-pytorch
90%+ with 40 labels. please see the readme for details.
gdGPT
Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
MFM
code for paper "Masked Frequency Modeling for Self-Supervised Visual Pre-Training" (https://arxiv.org/pdf/2206.07706.pdf)
pytorch-loss
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
SphereReID
My implementation of paper: SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification
triplet-reid-pytorch
My implementation of the paper [In Defense of the Triplet Loss for Person Re-Identification]
CoinCheung's Repositories
CoinCheung/pytorch-loss
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
CoinCheung/BiSeNet
Add bisenetv2. My implementation of BiSeNet
CoinCheung/DeepLab-v3-plus-cityscapes
mIOU=80.02 on cityscapes. My implementation of deeplabv3+ (also know as 'Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation' based on the dataset of cityscapes).
CoinCheung/triplet-reid-pytorch
My implementation of the paper [In Defense of the Triplet Loss for Person Re-Identification]
CoinCheung/gdGPT
Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
CoinCheung/SphereReID
My implementation of paper: SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification
CoinCheung/fixmatch-pytorch
90%+ with 40 labels. please see the readme for details.
CoinCheung/Deeplab-Large-FOV
My Implementation of the deeplab_v1 (known as deeplab large fov)
CoinCheung/MFM
code for paper "Masked Frequency Modeling for Self-Supervised Visual Pre-Training" (https://arxiv.org/pdf/2206.07706.pdf)
CoinCheung/SFT-ReID
My implementation of Spectral-Feature-Transformation-ReID, link to the paper: https://arxiv.org/abs/1811.11405
CoinCheung/DenseCL
DenseCL + regionCL-D
CoinCheung/SelfSup
ssl method pretrain experiments and weights: mocov2 + fast-moco + regioncl + mixup + densecl
CoinCheung/AutoAugment_opencv
autoaugment and randomaugment implemented with python opencv(cv2)
CoinCheung/ImageNet-Loader
An imagenet dataloader implemented with opencv and pybind11 based on multi-threading
CoinCheung/porn_identification
implement image processing with a combination of C and python3 based on socket communication
CoinCheung/mixMatch
Pytorch reproduction of the experiment in the paper of MixMatch.
CoinCheung/Segmentatron
My implementation of some segmentation algorithms
CoinCheung/CAPTCHA_IND
Identify CAPTCHA basing on CNN implemented by mxnet
CoinCheung/GAN-mxnet
GAN implemented with mxnet
CoinCheung/image-dedup
Codebase I use for deduplication of image datasets
CoinCheung/maskrcnn-benchmark
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
CoinCheung/BPNeuralNetwork
A BP network implemented with C++
CoinCheung/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
CoinCheung/eewee
CoinCheung/incubator-mxnet
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
CoinCheung/JnOS
try to write an easy OS of my own
CoinCheung/Mossaic-Handling
A program that can find the sensitive areas in a picture and add Mossaic to these areas automatically
CoinCheung/QT2048
a 2048 small game writen by python and c