[IJCAI'21] Deep Automatic Natural Image Matting
Repositories
DefTruth repositories
The platform independent header allowing to compile any C/C++ code containing ARM NEON intrinsic functions for x86 target systems using SIMD up to SSE4 intrinsic functions
中文翻译 + 部分个人理解: ARMv9 SVE/SVE2 内联函数
http://www.facegood.cc
Public repository for the CVPR 2020 paper AvatarMe and the TPAMI 2021 AvatarMe++
整理开源的中文大语言模型,以规模较小、可私有化部署、训练成本较低的模型为主,包括底座模型,垂直领域微调及应用,数据集与教程等。
A curated list of research papers, resources, and advancements on Diffusion Cache and related efficient diffusion model acceleration techniques.
Awesome-LLM: a curated list of Large Language Model
📖A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, FlashAttention, PagedAttention, MLA, Parallelism, etc. 🎉🎉
An awesome & curated list of best LLMOps tools for developers
A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and caching, etc.
BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).
Background Matting: The World is Your Green Screen
Build Production-Grade AI Applications
自己的学习历程,重点包括各种好玩的图像处理算法、运动捕捉、机器学习
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
C++ inplementation of CNN(Cnnvolutional Neural Network) for image classification
PyTorch implementation of "Towards Accurate Facial Motion Retargeting with Identity-Consistent and Expression-Exclusive Constraints" (AAAI2022)
📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).