The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
- pytorch
- resnet
- pretrained-models
- pretrained-weights
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
vits2 backbone with multilingual-bert
Fit interpretable models. Explain blackbox machine learning.
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
- unet
- fpn
- segmentation
- keras
Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
- convolutional-neural-networks
- efficient-inference
- imagenet
- model-compression
DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.
DeepLab v3+ model in PyTorch. Support different backbones.
- deeplab-v3-plus
- pytorch
- xception
- resnet
🔥🔥🔥 专注于YOLO11,YOLOv8、TYOLOv12、YOLOv10、RT-DETR、YOLOv7、YOLOv5改进模型,Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀
[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
Integrate deep learning models for image classification | Backbone learning/comparison/magic modification project
Official implementation of PVT series
Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.
- vizier
- hyperparameter-optimization
- tuning
- tuning-parameters
MonkeyOCRv2 Vision Encoder — A Document-Native Visual Backbone
Open-source implementation of Google Vizier for hyper parameters tuning
Official PyTorch implementation of VisionHOPE: Visual Backbones as Self-Modifying Learning Systems.
TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
Lightweight optimization with local, global, population-based and sequential techniques across mixed search spaces
- optimization
- gradient-free-optimization
- bayesian-optimization
- particle-swarm-optimization
船长关于机器学习、计算机视觉和工程技术的总结和分享
Pytorch Implementations of large number classical backbone CNNs, data enhancement, torch loss, attention, visualization and some common algorithms.
集成了openai-api、coze、deepseek、cursor、windsurf、qodo、blackbox、you、grok、bing 绘画 多款AI的聊天逆向接口适配到 OpenAI API 标准接口服务端。
A hyperparameter optimization framework, inspired by Optuna.
- bayesian-optimization
- bandit-algorithms
- evolution-strategies
- blackbox-optimization
Towards Reverse-Engineering Black-Box Neural Networks, ICLR'18