Can Kocagil's repositories
Cognitive-Computational-Modelling-for-Spatio-Temporal-fMRI-in-Ventral-Temporal-Cortex
Multi-voxel pattern analyses methods based on ML & DL to decode the category of visual stimuli viewed by a human subject based on their recorded brain activity in fMRI form
TT-SPN---Object-Detection
Object Detection version of TT-SPN
Image-Captioning
Convolutional Language Model for Image Captioning
Music-Genre-Recognition-from-Audio-Tracks-and-Metadata
Music Genre Recognition from Audio Tracks and Metadata via Both Time & Frequency Domain Learning
BioStatistics
Differential Gene Expression, Phylogenetic tree, Sequence Alignments, Biostatistics, Bioinformatic
Facial-Landmark-Detection
Facial Keypoint Detection, Landmark Localization
SP-MaskR-CNN
Spatio-temporal Mask R-CNN for Video Instance Segmentation
Barbershop
Barbershop: GAN-based Image Compositing using Segmentation Masks (SIGGRAPH Asia 2021)
Binance-Manager
Robust, Scalable & Advanced Python Binance API
Columnar-Transposition
Columnar Transposition , Cryptography, Assembly
CompVision
Computer Vision Applications
Low-Memory-Transformer-Finetuning
Implementation of Gradient Accumulation for low-memory language modelling transformer fine tuning.
Neural-Networks
Neural Networks, Deep Learning, Computer Vision, Natural Language Processing, Python
Parallel-File-Downloader-CLI-App
Parallel Data Fetching from Web and Synchronize & Aggregate the Fetched Information by Order
script_buddy_v2
Script Buddy v2 is a film script text generation tool built using film scripts from the world's most popular film scripts and GPT2.
Sequence-Deep-Learning-from-Scratch
Time Series and Sequence Deep Learning Model Implementations from Scratch
sort
Simple, online, and realtime tracking of multiple objects in a video sequence.
swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
Tweet-Sentiment-Analyzer
Fully-Scratch Twitter Sentiment Analyzer Tool with Conventional ML and Sequence Deep Learning Models
vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch