Classify Skin cancer from the skin lesion images using Image classification. The dataset for the project is obtained from the Kaggle SIIM-ISIC-Melanoma-Classification competition.

💎A high level pipeline for face landmarks detection, it supports training, evaluating, exporting, inference(Python/C++) and 100+ data augmentations, can easily install via pip.

The service for the demonstration of transforms in Albumentations library

Lightweight & fast OCR models for license plate text recognition.

My solution to the Global Data Science Challenge

Clean, reproducible, boilerplate-free deep learning project template.

Object detection and instance segmentation on MaskRCNN with torchvision, albumentations, tensorboard and cocoapi. Supports custom coco datasets with positive/negative samples.

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

A high-performance image processing library designed to optimize and extend the Albumentations library with specialized functions for advanced image transformations. Perfect for developers working in computer vision who require efficient and scalable image augmentation.

CIFAR10 image recognition using ResNet architecture, Gradcam images

Sample implementation codes for a variety of popular image augmentation Python packages

Augmentation package for 3d data based on albumentaitons

Computer Vision State Of The Art Intuition Project in Pytorch; WIP

First position in Gran Canary Datathon 2021

Modification of PyTorch implementation of YOLOv3 Object Detection.

CSE465 Pattern Recognition and Neural Network Project

Image data augmentation scheduler for albumentations transforms

Implemented Unet++ models for medical image segmentation to detect and classify colorectal polyps.

Deep learning solution for Cassava Leaf Disease Classification, a Kaggle's Research Code Competition using Tensorflow.

This is a capstone project on a real dataset related to segmenting low-grade glioma. This capstone project is included in the UpSchool Machine Learning & Deep Learning Program in partnership with Google Developers.