CoinCheung

Add bisenetv2. My implementation of BiSeNet

CoinCheung

My Implementation of the deeplab_v1 (known as deeplab large fov)

CoinCheung

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

90%+ with 40 labels. please see the readme for details.

CoinCheung

label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful

CoinCheung

My implementation of paper: SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification

CoinCheung

My implementation of the paper [In Defense of the Triplet Loss for Person Re-Identification]

CoinCheung

My implementation of Spectral-Feature-Transformation-ReID, link to the paper: https://arxiv.org/abs/1811.11405

CoinCheung

code for paper "Masked Frequency Modeling for Self-Supervised Visual Pre-Training" (https://arxiv.org/pdf/2206.07706.pdf)

CoinCheung

Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.

CoinCheung