Image Classification Using Swin Transformer With RandAugment, CutMix, and MixUp
Tensorflow2(Keras)のImageDataGeneratorのJupyter上での実行例。
This repository contains the code and the report for the coursework of INFR11031 Advanced Vision, a postgraduate course offered at The University of Edinburgh. The task was to train on limited and improve the accuracy of the ResNet-50 classifier on a small subset of the ImageNet dataset containing 50K training images and 50K test images. Achieve…
A compact PyTorch project for MNIST experiments that combines practical, sometimes underused techniques to achieve strong results
🧁 State-of-the-art hybrid ensemble for the impossible classification task • Swin-V2 + ConvNeXt with 12-pass saccadic TTA • 90%+ accuracy on muffin vs chihuahua challenge
📝 Enhance handwritten digit recognition using a compact ResNet-inspired PyTorch model with advanced techniques like MixUp and CutMix.
Add a description, image, and links to the mixup-cutmix topic page so that developers can more easily learn about it.
To associate your repository with the mixup-cutmix topic, visit your repo's landing page and select "manage topics."