wslucy Goto Github PK

ad-kd

Source code of ACL 2023 accepted paper "AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression"

co-teaching

NeurIPS'18: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels

data2vec-pytorch

PyTorch implementation of "data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language" from Meta AI

datasets

deep-learning

dist_kd

Official implementation of paper "Knowledge Distillation from A Stronger Teacher", NeurIPS 2022

distilbert

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

distilling-step-by-step

dog-breed-classifier

Udacity (Project 2) Dog Breed Classifier with PyTorch.

fastcodellama

accelerate the inference of codellama

fcfd

Official implementation of the paper "Function-Consistent Feature Distillation" (ICLR 2023)

fine-tune-bert

Pytorch implementation of finetuning bert on a custom dataset.

gan-tutorial

Simple Implementation of many GAN models with PyTorch 1.0

informer2020

The GitHub repository for the paper "Informer" accepted by AAAI 2021.

learning-to-reweight-examples

PyTorch Implementation of the paper Learning to Reweight Examples for Robust Deep Learning

learning-without-forgetting

Implementation of Learning without Forgetting paper

license_plate_detection_pytorch

A two stage lightweight and high performance license plate recognition in MTCNN and LPRNet

license_plate_recognition_pytorch

该工作由电子科技大学陈昂、刘俊凯、夏子寒同学完成。我们提出可以使用深度学习的方案对**车牌进行检测和识别。我们提出使用YOLOv3网络进行车牌检测，然后创新性地对检测后的车牌使用空间变换网络STN加以校正，最后使用LPRNet网络进行车牌的字符与数字识别。目前实测结果，在老师提供的45张数据集上，我们的YOLOv3网络检测准确率（IOU）达到98.2%，深度学习级联网络识别准确率为95.6%。我们采用大量测试集，最终我们的YOLOv3_STN_LPRNet级联网络识别准确率稳定在93.3%，不加空间变换网络STN的话，识别准确率在66%左右。 总体来说，使用深度学习的方案比传统方案效果提升的非常好，而且我们加入空间变换网络STN的做法对于提升识别准确率很有效。

madkd

MadKD

meta-weight-net

NeurIPS'19: Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting (Pytorch implementation for noisy labels).

mnist_gan

In this project I explore four diffrent approaches to generate MNIST image with general adversial network.

moco

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

multi-level-logit-distillation

Code for 'Multi-level Logit Distillation' (CVPR2023)

overhaul-distillation

Official PyTorch implementation of "A Comprehensive Overhaul of Feature Distillation" (ICCV 2019)

packd

The official implementation of [ACMMM2022] Pay Attention to Your Positive Pairs: Positive Pair Aware Contrastive Knowledge Distillation

papers-in-100-lines-of-code

maxout networks

person-reid-tiny-baseline

Open source person re-identification in Pytorch

pytorch-generative-model-collections

Collection of generative models in Pytorch version. pytorch0.4

reasoning-teacher

Official code for "Large Language Models Are Reasoning Teachers", ACL 2023

reviewkd

Distilling Knowledge via Knowledge Review, CVPR 2021