Starred repositories
Open-Sora: Democratizing Efficient Video Production for All
MICA - Towards Metrical Reconstruction of Human Faces [ECCV2022]
Metrical Monocular Photometric Tracker [ECCV2022]
MediaPipe BlazePose pose estimation for Unity projects.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
A memory-efficient implementation of DenseNets
Implementation of paper "Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning" in PyTorch
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…
Comparison of Generative Models in Tensorflow
🌍 针对小白的算法训练 | 包括四部分：①.大厂面经 ②.力扣图解 ③.千本开源电子书 ④.百张技术思维导图（项目花了上百小时，希望可以点 star 支持，🌹感谢~）推荐免费ChatGPT使用网站
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
TensorRT MODNet, YOLOv4, YOLOv3, SSD, MTCNN, and GoogLeNet
Automatic Colorization of Anime Sketch Image
k-means clustering with the Intersection over Union (IoU) metric as described in the YOLO9000 paper
Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"
Tensorflow2.0 🍎🍊 is delicious, just eat it! 😋😋
A guideline for building practical production-level deep learning systems to be deployed in real world applications.
Code for our paper "Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition"
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
mobilenetv3 with pytorch，provide pre-train model
This is a PyTorch implementation of the ECCV2018 paper "Learning to Navigate for Fine-grained Classification" (Ze Yang, Tiange Luo, Dong Wang, Zhiqiang Hu, Jun Gao, Liwei Wang).
@CVPR2018: Efficient unrolling iterative matrix square-root normalized ConvNets, implemented by PyTorch (and code of B-CNN,Compact bilinear pooling etc.) for training from scratch & finetuning.
This is a pytorch re-implementation of Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition
Destruction and Construction Learning for Fine-grained Image Recognition
Image augmentation for machine learning experiments.
A PyTorch Implementation of Single Shot MultiBox Detector
Datasets, Transforms and Models specific to Computer Vision