396 skills found · Page 1 of 14
xmu-xiaoma666 / External Attention Pytorch🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐
ImageOptim / GifskiGIF encoder based on libimagequant (pngquant). Squeezes maximum possible quality from the awful GIF format.
hujie-frank / SENetSqueeze-and-Excitation Networks
SqueezerIO / SqueezerSqueezer Framework - Build serverless dApps
forresti / SqueezeNetSqueezeNet: AlexNet-level accuracy with 50x fewer parameters
xvjiarui / GCNetGCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
balderdashy / Sails Docs**Latest docs now live in the Sails core repo!** The source markdown files for the official Sails.js documentation, which gets compiled, squeezed, and stretched into HTML when we deploy the Sails website.
taki0112 / SENet TensorflowSimple Tensorflow implementation of "Squeeze and Excitation Networks" using Cifar10 (ResNeXt, Inception-v4, Inception-resnet-v2)
BichenWuUCB / SqueezeDetA tensorflow implementation for SqueezeDet, a convolutional neural network for object detection.
SqueezeAILab / SqueezeLLM[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
emacsattic / Helm SwoopEfficiently hopping squeezed lines powered by Emacs helm interface
cybertec-postgresql / Pg SqueezeA PostgreSQL extension for automatic bloat cleanup
BichenWuUCB / SqueezeSegImplementation of SqueezeSeg, convolutional neural networks for LiDAR point clout segmentation
ralph-irving / SqueezeliteLightweight headless squeezebox player for Lyrion Media Server
jtamames / SqueezeMetaA complete pipeline for metagenomic analysis
rcmalli / Keras SqueezenetSqueezeNet implementation with Keras Framework
songhan / SqueezeNet Deep CompressionNo description available
titu1994 / Keras Squeeze Excite NetworkImplementation of Squeeze and Excitation Networks in Keras
fudan-zvg / SeaFormer[ICLR 2023 & IJCV 2025] SeaFormer: Squeeze-enhanced Axial Transformer
ai-med / Squeeze And ExcitationPyTorch Implementation of 2D and 3D 'squeeze and excitation' blocks for Fully Convolutional Neural Networks
