MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification

Source code for ACL 2022 Paper "Prompt-based Data Augmentation for Low-Resource NLU Tasks"

A large high-quality corpus of Chinese synonyms 一个大型、高质量的中文同义词语料库。

No description provided.

Source codes for the paper "Local Additivity Based Data Augmentation for Semi-supervised NER"

MalDataGen is an advanced Python framework for generating and evaluating synthetic tabular datasets using modern generative models, including diffusion and adversarial architectures.

Build a CNN based model which can accurately detect melanoma

[CVPR 2025] PyTorch implementation of Diff-II

适用于目标检测VOC格式的数据增强工具包，包含各种像素级增广方式和形变增广，如：rotate、crop、rotation、flip、tile、滑动窗口、mosaic等；数据格式转换：coco_2_voc、xml_for_u_yolo等

画像データ拡張ライブラリAlbumentationsのJupyter上での実行例。

Code for "Planning and Generating Natural and Diverse Disfluent Texts as Augmentation for Disfluency Detection"

American Sign Language to English real time Conversion App

Training and evaluating skin type images using (CNN) models via transfer learning, along with personalized recommendations based on classified skin type predictions generated by OpenAI's language model.

Advanced Digit Recognition System using a Hybrid Modern-CNN (ResNet + ConvNeXt) & Ensemble Inference Engine. Features a robust OpenCV preprocessing pipeline and FastAPI backend.

SyntheticOcean: Open-Source Library for Generating Synthetic Tabular Data + SynDataGen (Framework for Synthetic Data Generation)

Tensorflow2/KerasのImageDataGenerator向けのmixupの実装。

Implement secure transaction system using keras deep learning model for recogination and , intergrated otp verification and jwt authentication for enhancing the more security

Thyroid Nodule image Classification based on Geometric and Morphological Features

Automatic Data Augmentation for Deep Learning techniques

A simple python-script to augment an annotated dataset in JPG/XML Format as used by LabelIMG (https://github.com/tzutalin/labelImg) and now Label Studio. The script will rotate the images 4 times and mirror the resulting images and the annotations making for an expansion by the factor of 8.

Tensorflow2(Keras)のImageDataGeneratorのJupyter上での実行例。

Image Data Augmentation using Keras.

Developed phase recognition models based on MobileNetV2 to classify frames from Hernia surgery videos.

This repository presents a gemstone classification project employing Transfer Learning with MobileNetV2, processing a dataset comprising 3200+ images spanning 87 classes. TensorFlow and Keras facilitated data preprocessing, augmentation, and model training. Through fine-tuning and leveraging pre-trained features.

Major Project in Final Year B.Tech (IT). Live Stream Sign Language Detection using Deep Learning.

It a project on classification of species of snake into venomous and non-venomous using a Deep learning model. This repository consists of whole journey from using CNN to using transfer learning with MobileNetV2 as pre trained model

When Active Learning and Data Augmentation meet at Object Detection

Developed a deep learning model for the detection of melanoma.

Flower Classification with CNN & Data Augmentation

In a virtual painting task, participants indicated which surface ridges appeared to be caused by the hidden object and which were due to the drapery. The goal of this project was to implement the paper and offer insights into whether a Deep Neural Network (DNN) can outperform humans in producing results.