🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

This is a pytorch repository of YOLOv4, attentive YOLOv4 and mobilenet YOLOv4 with PASCAL VOC and COCO

YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet, SwinTransformer YOLO), Module(CBAM, DCN), Pruning (EagleEye, Network Slimming), Quantization (MQBench) and Deployment (TensorRT, ncnn) Compression Tool Box.

More readable and flexible yolov5 with more backbone(gcn, resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer, etc) and (cbam，dcn and so on), and tensorrt

Model Compression—YOLOv3 with multi lightweight backbones(ShuffleNetV2 HuaWei GhostNet), attention, prune and quantization

CBAM implementation on TensowFlow

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

CBAM implementation on TensorFlow Slim

CBAM: Convolutional Block Attention Module for CIFAR100 on VGG19

CBAM(Convolutional Block Attention Module) implementation on TensowFlow2.0

Open-source, zero-dependency demos of production carbon calculators from GreenCalculus — Scope 1 stationary combustion, SBTi near-term targets, FLAG land emissions, PCAF financed emissions, and CBAM quarterly reporting. GHG Protocol & IPCC AR6 aligned, fully traceable, vanilla JS.

可以训练yolov5(v6.0)、yolox、小型网络，添加注意力机制

This repo contains the 3D implementation of the commonly used attention mechanism for imaging.

PHP package to read metadata and extract covers from eBooks, comics and audiobooks.

Hyperspectral Unmixing via Dual Attention Convolutional Neural Networks | 基于双注意力卷积神经网络的高光谱图像解混

Spatial and Channel Attention in CNN Architectures for Image Classification task

ZAM: Zero parameter Attention Module

This is a torchvision style CNN models collection based on pytorch.

Code for paper "Channel Pruning Guided by Spatial and Channel Attention for DNNs in Intelligent Edge Computing"

This project presents a fingerprint matching system utilizing deep learning. It features multiple models, including VGG-based, SENet, CBAM, Self-Attention, and Dual-Attention architectures. Pre-trained MobileNet models with Self-Attention and SENet are also included. A web application allows for easy demonstration of the model's capabilities.