A course on aligning smol models.

Efficient vision foundation models for high-resolution generation and perception.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Sources for the book "Machine Learning in Production"

This is a collection of our NAS and Vision Transformer work.

An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"

FasterAI: Prune and Distill your models with FastAI and PyTorch

Pytorch implementation of RetinaNet object detection.

OpenMMLab Model Compression Toolbox and Benchmark.

Contrastive Language-Image Pretraining

OpenMMLab Detection Toolbox and Benchmark

Explainability for Vision Transformers

An easy to use PyTorch to TensorRT converter

A PyTorch Implementation of Single Shot MultiBox Detector

Mobile vision models and code

A faster pytorch implementation of faster r-cnn

code for "AttentiveNAS Improving Neural Architecture Search via Attentive Sampling"

learning and feeling SLAM together with hands-on-experiments

AlphaNet Improved Training of Supernet with Alpha-Divergence

This is the official pytorch implementation for paper: BiDet: An Efficient Binarized Object Detector, which is accepted by CVPR2020.

Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm. In ECCV 2018 and IJCV

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

(CVPR 2021 Oral) Open World Object Detection

MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks