Emirhan Bilgiç's repositories
Deepfake_Detection
The project focuses on comparing various methods for detecting deepfakes and evaluating their effectiveness across different datasets. Also tries zero-shot BLIP to detect manipulations.
brain_tumour_segmentation
This repository contains the implementation of various techniques to segment brain tumors from MRI images.
Emirhans_Method_Deepfake
BLIP is a VLP (Vision-Language Pre-training) framework that excels in both vision-language understanding and generation tasks using a multimodal mixture of encoder-decoder model and a novel captioning and filtering method for handling noisy data. In this project, we will try to use BLIP in deepfake detection
sorting_algorithms
This repository includes different sorting algorithms. The purpose is to show different approaches.
euler-solutions
This repository was created to show different solutions to Project Euler problems with different approaches.
next-frame-prediction
This project aims to make image data contribute to temporality. In addition to 3D CNN structure, ConvLSTM2D, PredRNN, the combination of 2D CNN and Tabular data has been tested and compiled in this repo. Cloudiness prediction using satellite data of EUMETSAT is aimed.
AI_Slides_SIMMAG
Includes a compilation slide on generative models and transformer models such as chatGPT.
Alzheimer-s-Detection
This repository contains code for detecting Alzheimer's patients from linguistic cues.
cog-realvisxl-v2.0
Attempt at cog wrapper for SG161222/RealVisXL_V2.0
cog-sdxl
Stable Diffusion XL training and inference as a cog model
DCGAN-DALLE
Implementation of a DCGAN from scratch for image generation, benchmarked against DALL-E with multilingual support through Google Translate API integration.
Electronics_and_Communication_Engineering_ITU
Here you can find the documents, assignments, projects and questions of the courses I enrolled.
flexible_neural_nets
This project implements a multi-layer neural network from scratch, using only fundamental Python libraries such as NumPy. The architecture is designed with flexibility in mind, allowing users to easily adjust the number of layers and neurons within those layers.
gpt-3.5-turbo_data_augmentation
Data Augmentation Code with gpt-3.5-turbo model
pytorch-learn-reinforcement-learning
A collection of various RL algorithms like policy gradients, DQN and PPO. The goal of this repo will be to make it a go-to resource for learning about RL. How to visualize, debug and solve RL problems. I've additionally included playground.py for learning more about OpenAI gym, etc.
ResNet-50_basic_struct
ResNet50 is a convolutional neural network that is 50 layers deep, and is a variant from the ResNet (Residual Network) family.
SolvingImbalancedClasses-FinalThesis
Final Thesis on Solving Imbalanced Classes Problem
tree_algorithms
This repository has some staple tree algorithm problems.