🔥🔥NSFW implement in pytorch（色情图&性感图识别，本程序经过了线上大数据集测试，性能优异效果良好）🔥🔥

Multiclass image classification using Convolutional Neural Network

Encoder-decoder architecture using ResNet and transposed ResNet (resnet 50, resnet 101)

realtime violence detection from videos using cnn-lstm model

A model inspired from the famous Show and Tell Model is implemented for automatic image captioning.

랜드마크 자동태그 기반 스마트 여행기록 SNS입니다 :-)

Weeds detection application using transfer learning (resnet101) and some tips powered by Fastai library

Sistema inteligente basado en Deep Learning para el proceso de clasificación de residuos

Implementation of the paper, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks", NeurIPS 2015 by Ren et al

Convolutional Neural Networks on Image Classification using a genetic algorithm for optimization

Implementation of some basic Image Annotation methods (using various loss functions & threshold optimization) on Corel-5k dataset with PyTorch library

An complete flutter based app for blind people incorporating Nepali currency detection, OCR and Environment Captioning for enhancing day to day activities of visually impaired person.

Top 5% on Kaggle leaderboard using fast.ai library and resnet50 along with transfer learning.

This repository hosts the Cervical Cancer Image Classification project, a comprehensive effort aimed at improving the classification accuracy of Squamous Cell Carcinoma (SCC) through advanced deep learning models and ensemble techniques. The project utilizes the Herlev dataset.

Transfer Learning using PyTorch

Crowd counting and analysing techniques using Convolutional Neural Network (ResNet 101). It can process both photos and videos as inputs.

Explore my comprehensive collection of AI models for blood cancer detection. Leveraging deep learning and medical imaging, these models aim to revolutionize early diagnosis and treatment, making a significant impact on the battle against blood cancers. #AI #HealthcareInnovation

Nepali Handwritten Character Image Classification through Deep Learning.

This project is a system created to use feature extraction methods and pre-trained models to find similarities between photos retrieved from different sources.

Deep learning approach to detect vacant spots from a stationary video feed of a parking lot