在 oxford hand 数据集上对 YOLOv3 做模型剪枝（network slimming）

A collection of state-of-the-art video or single-image super-resolution architectures, reimplemented in tensorflow.

Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks. EDVR has been merged into BasicSR…

该仓库用于记录作者本人参加的各大数据科学竞赛的获奖方案源码以及一些新比赛的原创baseline. 主要涵盖：kaggle, 阿里天池，华为云大赛校园赛，百度aistudio，和鲸社区，datafountain等

Tensorflow Backend for ONNX

The solution of team 'grt123' in DSB2017

Two-stage CenterNet

mixup: Beyond Empirical Risk Minimization

Video classification tools using 3D ResNet

convert dataset to coco/voc format

(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"

mmdetection最小学习版

Code for our CVPR2021 paper coordinate attention

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection, CVPR, Oral, 2020

Train the HRNet model on ImageNet

Keras implementation of Deep Convolutional Generative Adversarial Networks

Zero-Shot Learning with GCN (CVPR 2018)

Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios

D2Go is a toolkit for efficient deep learning

Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels (CVPR, 2019) (PyTorch)

[CVPR 2023] Code for PConv and FasterNet

本文新增添分类，检测，换脸技术等学习教程，各种调参技巧和tricks，卷积结构详细解析可视化，注意力机制代码等详解！本次垃圾分类挑战杯，目的在于构建基于深度学习技术的图像分类模型，实现垃圾图片类别的精准识别，大赛参考深圳垃圾分类标准，按可回收物、厨余垃圾、有害垃圾和其他垃圾四项分类。本项目包含完整的分类网络、数据增强、SVM等各种分类增强策略，后续还会继续更新新的分类技巧。

yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.

MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.

Object detection with multi-level representations generated from deep high-resolution representation learning (HRNetV2h). This is an official implementation for our TPAMI paper "Deep High-Resolutio…

mmdetection源码注释

The implementation of “Gradient Harmonized Single-stage Detector” published on AAAI 2019.

nnDetection is a self-configuring framework for 3D (volumetric) medical object detection which can be applied to new data sets without manual intervention. It includes guides for 12 data sets that …

convert mmdetection model to tensorrt, support fp16, int8, batch input, dynamic shape etc.

The project is an official implement of our CVPR2018 paper "Deep Back-Projection Networks for Super-Resolution" (Winner of NTIRE2018 and PIRM2018)