fwt1226

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

mmdetection

OpenMMLab Detection Toolbox and Benchmark

d2l-en

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

External-Attention-pytorch

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

pretrained-models.pytorch

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

attention-is-all-you-need-pytorch

A PyTorch implementation of the Transformer model in "Attention is All You Need".

distiller

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller

transformer

A TensorFlow Implementation of the Transformer: Attention Is All You Need

awesome-TS-anomaly-detection

List of tools & datasets for anomaly detection on time-series data.

fast-autoaugment

Official Implementation of 'Fast AutoAugment' in PyTorch.

pytorch_classification

利用pytorch实现图像分类的一个完整的代码，训练，预测，TTA，模型融合，模型部署，cnn提取特征，svm或者随机森林等进行分类，模型蒸馏，一个完整的代码

multilingual-t5

Class-balanced-loss-pytorch

Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"

amc

[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

seq2seq

Attention-based sequence to sequence learning

cnn-svm

An Architecture Combining Convolutional Neural Network (CNN) and Linear Support Vector Machine (SVM) for Image Classification

Anomaly-Detection-PatchSVDD-PyTorch

SPADE-pytorch

PyTorch implementation of "Sub-Image Anomaly Detection with Deep Pyramid Correspondences"

SmallObjectAugmentation

Simple implementation of augmentation for small object detection

RMNet

RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

MLND

Udacity Machine Learning Nano Degree Courses

dataset

Multi30k Dataset

NJUNMT-tf

An open-source neural machine translation system developed by Natural Language Processing Group, Nanjing University.

SSD-Resnet-Attention-FeatureFusion

SSD 改进：backbone增加resnet，并针对resnet加入attention机制，为了充分利用细节特征和语义特征，还加入了特征融合模型

garbage_classification_pro

通过目标检测+图片识别模型对图片中的垃圾进行分类、通过双向LSTM+一维卷积混合模型对物体名称进行垃圾分类

FloW-Dataset

A dataset for floating waste detection in inland waters.

mju-waste

The MJU-Waste dataset from our Sensors paper "A Multi-level Approach to Waste Object Segmentation".

TSD-TSD-for-small-pest-object-detection

channel_prune

channel prune for resnet