24 skills found
albumentations-team / AlbumentationsFast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
iver56 / Torch AudiomentationsFast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
albumentations-team / AutoalbumentAutoML for image augmentation. AutoAlbument uses the Faster AutoAugment algorithm to find optimal augmentation policies. Documentation - https://albumentations.ai/docs/autoalbument/
Evizero / Augmentor.jlA fast image augmentation library in Julia for machine learning.
qsyao / Cuda Spatial DeformA fast tool to do image augmentation on GPU(especially elastic_deform), can be helpful to research on Medical Image.
goodok / Fastai Sparse3D augmentation and transforms of 2D/3D sparse data, such as 3D triangle meshes or point clouds in Euclidean space. Extension of the Fast.ai library to train Sub-manifold Sparse Convolution Networks
Lallapallooza / Fast Audiomentations⚡ Blazing fast audio augmentation in Python, powered by GPU for high-efficiency processing in machine learning and audio analysis tasks.
kbhujbal / LungGuardianAI Pneumonia Detection From Chest Xrays With Transfer LearningState-of-the-Art Pneumonia detection from chest X-rays system using EfficientNetV2 + FPN + Faster R-CNN. Features Focal Loss, Weighted Box Fusion, Mosaic Augmentation & StratifiedGroupKFold. Built for RSNA Pneumonia Detection Challenge. Achieves competitive mAP with mixed-precision training.
shashankag14 / Fine Tune Object DetectorA step-by-step PyTorch guide for improved vehicle type 2D object detection based on Faster-RCNN using transfer learning and data augmentation.
viig99 / EsolafastFast C++ implementation of ESOLA using KFRLib, can be used for online time-stretch augmentation during SpeechToText training.
500swapnil / Keras Efficientnet SSDA pure Tensorflow+Keras TPU trainable implementation of SSD (Single Shot MultiBox Detector) using different backbones of EfficientNet which can be replaced with any ImageNet backbone. Tested on the PASCAL_VOC dataset. Implemented several low level data preprocessing and augmentations in pure tf functions for faster computation.
Shahaf-Yamin / Radar Moving Target Classification Via CNNRadar-based classification of ground moving targetsrelies on Doppler information. Therefore, the classification be-tween humans and animals is a challenging task due to theirsimilar Doppler signatures. This work proposes a Deep Learning-based approach for ground moving radar targets classification.The proposed algorithm learns the radar targets’ micro-Dopplersignatures in the 2D fast-time slow-time domain of radar echoes.This work shows that the convolutional neural network (CNN)can achieve high classification performance. Also, it shows thatefficient data augmentation and regularization significantly im-prove classification performance and reduce over-fit.
moshuilanting / Fast Context Scene Graph GenerationFast Contextual Scene Graph Generation with Unbiased Context Augmentation
IbrokhimN / HangulAI ModelAI model for recognizing Korean Hangul characters using a CNN in PyTorch. Incorporates data augmentation, batch normalization, dropout, and AdamW optimizer. Supports scalable training, early stopping, and fast inference for OCR and language-learning applications.
jcgy / SprinklesImage augmentation function - fast.ai
chokkyvista / IPM3FSource code and data for the paper "Nonparametric Max-Margin Matrix Factorization for Collaborative Prediction" accepted to NIPS'2012 and "Fast Max-Margin Matrix Factorization with Data Augmentation" accepted to ICML'2013
mhariat / Fast PBA AutoAugmentUsing Fast-AutoAugment and Population Based Augmentation to train deep neural networks on CIFAR-100 (w/ Pytorch)..
Engineero / Tf SprinklesFast and efficient sprinkles augmentation implemented in TensorFlow
masoudMZB / Text Wizard Fatsapi NLP ProjectNLP Visualization/Augmentation techniques using fast api to implement.
zaczzy / Augmentationsmall data augmentation for faster-rcnn
