Sandbox for training deep learning networks

Proper implementation of ResNet-s for CIFAR10/100 in pytorch that matches description of the original paper.

The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf

PyTorch implementation of CNNs for CIFAR benchmark

Unofficial PyTorch Reimplementation of RandAugment.

Reproduces ResNet-V3 with pytorch

Implementation of the mixup training method

Multi-Scale Dense Networks for Resource Efficient Image Classification （ICLR 2018 Oral）

Quickly comparing your image classification models with the state-of-the-art models (such as DenseNet, ResNet, ...)

TensorFlow implementation of GoogLeNet and Inception for image classification.

Deep fusion project of deeply-fused nets, and the study on the connection to ensembling

Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch.

ResNet-20/32/44/56/110 on CIFAR-10 with Caffe

Open Set Recognition

Implementation of our Pattern Recognition paper "DMT: Dynamic Mutual Training for Semi-Supervised Learning"

The official implementation of paper: "Inter-Instance Similarity Modeling for Contrastive Learning"

[TIP 2022] Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training. Plus, an image classification toolbox includes ResNet, Wide-ResNet, ResNeXt, ResNeSt, ResNeXSt, SENet, Shake-Shake, DenseNet, PyramidNet, and EfficientNet.

Training ImageNet / CIFAR models with sota strategies and fancy techniques such as ViT, KD, Rep, etc.

Training Low-bits DNNs with Stochastic Quantization

Python toolkit for speech processing