Stars
中文大模型能力评测榜单:目前已囊括153个大模型,覆盖chatgpt、gpt-4o、谷歌gemini、Claude3.5、百度文心一言、千问、百川、讯飞星火、商汤senseChat、minimax等商用模型, 以及deepseek-v3、qwen2.5、llama3.3、phi-4、glm4、书生internLM2.5等开源大模型。不仅提供能力评分排行榜,也提供所有模型的原始输出结果!
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。
✂️ Automated high-quality background removal framework for an image using neural networks. ✂️
EasyPortrait - Face Parsing and Portrait Segmentation Dataset
👦 Human head semantic segmentation
Code for the model to segment people at the image
The official GitHub page for the review paper "Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models".
A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
Code release for NeRF (Neural Radiance Fields)
🔥Highlighting the top ML papers every week.
Graphic notes on Gilbert Strang's "Linear Algebra for Everyone", 线性代数的艺术中文版, 欢迎PR.
Nightly release of ControlNet 1.1
Paper and implementation of UNet-related model.
Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
links to conference publications in graph-based deep learning
Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (CVPR 2022)
RepVGG: Making VGG-style ConvNets Great Again
real Transformer TeraFLOPS on various GPUs
real Transformer TeraFLOPS on various GPUs
Official Pytorch implementations for "SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation" (NeurIPS 2022)
Image augmentation for machine learning experiments.
Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
OpenMMLab Semantic Segmentation Toolbox and Benchmark.