Pinned Repositories
DiffRate
[ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging techniques, while incorporating a differentiable compression rate.
CrossArch_KD
Deep-Learning
:computer:深度学习实战：手写数字识别、Discuz验证码识别、垃圾分类、语义分割
expert_readed_books
2021年最新总结，推荐工程师合适读本，计算机科学，软件技术，创业，**类，数学类，人物传记书籍
kmeans-anchor-boxes
k-means clustering with the Intersection over Union (IoU) metric as described in the YOLO9000 paper
MAE_cifar
PyTorch implementation of Masked Autoencoder
PREFALLKD-PRE-IMPACT-FALL-DETECTION-VIA-CNN-VIT-KNOWLEDGE-DISTILLATION
fall detection via cnn-vit distillation
pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
pytorch-openpose
pytorch implementation of openpose including Hand and Body Pose Estimation.
RCD
the offical implement of “DISTILL VISION TRANSFORMERS TO CNNS VIA TEACHER COLLABORATION”
SunkiLin's Repositories
SunkiLin/RCD
the offical implement of “DISTILL VISION TRANSFORMERS TO CNNS VIA TEACHER COLLABORATION”
SunkiLin/CrossArch_KD
SunkiLin/Deep-Learning
:computer:深度学习实战：手写数字识别、Discuz验证码识别、垃圾分类、语义分割
SunkiLin/expert_readed_books
2021年最新总结，推荐工程师合适读本，计算机科学，软件技术，创业，**类，数学类，人物传记书籍
SunkiLin/kmeans-anchor-boxes
k-means clustering with the Intersection over Union (IoU) metric as described in the YOLO9000 paper
SunkiLin/MAE_cifar
PyTorch implementation of Masked Autoencoder
SunkiLin/PREFALLKD-PRE-IMPACT-FALL-DETECTION-VIA-CNN-VIT-KNOWLEDGE-DISTILLATION
fall detection via cnn-vit distillation
SunkiLin/pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
SunkiLin/pytorch-openpose
pytorch implementation of openpose including Hand and Body Pose Estimation.