The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

HybridNets: End-to-End Perception Network

LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation

[MICCAI'24] Official implementation of "BGF-YOLO: Enhanced YOLOv8 with Multiscale Attentional Feature Fusion for Brain Tumor Detection".

QuarkDet lightweight object detection in PyTorch .Real-Time Object Detection on Mobile Devices.

This project is a kind of implementation of EfficientDet(CVPR 2020) using mmdetection.

Nuclei segmentation and classification (Cancer cells)

Concise, Modular, Human-friendly PyTorch implementation of MixNet with Pre-trained Weights.

An efficient and multi-scale feature fusion behavior recognition algorithm

Development of a depth estimation model based on a UNET architecture - connection of Bi-directional Feature Pyramid Network (BIFPN) and EfficientNet.

Pytorch implementation of dynamic FPN, PAN, and Bi-FPN

Segmentation models with pretrained backbones. PyTorch.

This is a hybrid variety of detection models which is inspired from bothe centrenet and EfficientDet. This model is as fast as centrenet and much accurate due to the fusion blocks.

Implementation of CVPR 2020 paper "EfficientDet: Scalable and Efficient Object Detection" using PyTorch and OpenCV