A treasure chest for visual classification and recognition powered by PaddlePaddle
-
Updated
May 30, 2024 - Python
A treasure chest for visual classification and recognition powered by PaddlePaddle
PyTorch implementation of 'ViT' (Dosovitskiy et al., 2020) and training it on CIFAR-10 and CIFAR-100
An open-source toolkit which is full of handy functions, including the most used models and utilities for deep-learning practitioners!
Image Classification Using Swin Transformer With RandAugment, CutMix, and MixUp
Implementation of an advanced Convolutional Neural Network (CNN) for large-scale pest recognition, incorporating augmentation techniques and regularizers for improved accuracy and generalization.
Official Codes and Pretrained Models for RecursiveMix
DualDet implementation using PyTorch
This is a data augmentation for object detection, using bounding boxes.
FastClassification is a tensorflow toolbox for class classification. It provides a training module with various backbones and training tricks towards state-of-the-art class classification.
Implementation of CutMix Augmentation with Keras.
Deep learning solution for Cassava Leaf Disease Classification, a Kaggle's Research Code Competition using Tensorflow.
This is a TensorFlow implementation of the following paper: DropBlock: A regularization method for convolutional networks
tensorflow2 implementation of SnapMix as described in SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data
SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data (AAAI 2021)
Official Pytorch implementation of CutMix regularizer
Implementation of modern data augmentation techniques in TensorFlow 2.x to be used in your training pipeline.
Tensorflow2/KerasのImageDataGenerator向けのcutmixの実装。
Tensorflow2(Keras)のImageDataGeneratorのJupyter上での実行例。
Keras implementation of CutMix regularizer
Add a description, image, and links to the cutmix topic page so that developers can more easily learn about it.
To associate your repository with the cutmix topic, visit your repo's landing page and select "manage topics."