Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet, WideResNet)

Wide Residual Networks (WideResNets) in PyTorch

PyTorch implementation for 3D CNN models for medical image data (1 channel gray scale images).

SE-Net Incorporates with ResNet and WideResnet on CIFAR-10/100 Dataset.

CIFAR10, CIFAR100 results with VGG16,Resnet50,WideResnet using pytorch-lightning

97.39% on CIFAR10 with PyTorch

vanilla training and adversarial training in PyTorch

wide resnet in tensorflow

WideResNet implementation on MNIST dataset. FGSM and PGD adversarial attacks on standard training, PGD adversarial training, and Feature Scattering adversarial training.

the CIFAR10 dataset

Image recognition on CIFAR 10, CIFAR 100, Caltech 101 and Caltech 256 datasets. With the implementation of WideResNet, InceptionV3 and DenseNet neural networks.

PyTorch implementation of deep CNNs

Code for paper: "Improved Residual Network Based on Norm-Preservation for Visual Recognition" https://doi.org/10.1016/j.neunet.2022.10.023

Image Texture Segmentation

CIFAR10 PyTorch implementation of "MixMatch - A Holistic Approach to Semi-Supervised Learning"

An implementation of WideResNets with Fixup initialization in Jax/Flax. This can be useful for use cases where Batch Normalization should be avoided (for example when using the Laplace approximation to the Bayesian posterior).

Training a Wide Residual Network on the CIFAR - 10 dataset with a limit of 5 million on the number of trainable parameters.

This project uses PyTorch to classify bone fractures. As well as fine-tuning some famous CNN architectures (like VGG 19, MobileNetV3, RegNet,...), we designed our own architecture. Additionally, we used Transformer architectures (such as Vision Transformer and Swin Transformer). This dataset is Bone Fracture Multi-Region X-ray, available on Kaggle.