Reteaua neuronala CitNet

One-stage and two-stage face detection models

This project aims to improve the performance of the classification algorithm by implementing state-of-the-art model: EfficientNet in place of VGG-16.

Glume pubescence classification of wheat using convolutional neural networks

Project 7 of the course "Specialization Data Science" that updated to the app

Food Vision Big™, using all of the data from the Food101 dataset. Beat the DeepFood paper : https://www.researchgate.net/publication/304163308_DeepFood_Deep_Learning-Based_Food_Image_Recognition_for_Computer-Aided_Dietary_Assessment

This project is for FYP usage.

one-stage and two-stage detectors and segmentation-based detectors

Skin lesion (Melanoma) cancer detector

Mask Monitoring System

Ear recognition using CNN based on EfficientNet-B0 (Assignment 3 for Image Based Biometry course at University of Ljubljana)

Driver's Drowsiness Prediction Using CNN Architechtures

Classification of Liver fat with a voting classifier

Automation of model training and ensemble creation for making predictions in a Kaggle competition submission.

Predicting image classes can now be achieved without extensive training, thanks to the advancements in transformer-based models.

Specifying a tightly cropped bounding box centered on the instance.

Repo. for 2023 AICOSS Hackathon Contest

Repo for the "APTOS 2019 Blindness Detection" competition on Kaggle, to share my approach to solving the problem.

Leaf disease classification on kaggle