Cataract detection model

Deep Neural Network Architectures with dlib

A deep learning-based model for image (species) classification tasks

Multiclass image classification using Convolutional Neural Network

Block-by-block implementation from scratch of CNNs and GANs using PyTorch, with language models to be added later.

Image Captioning System using VggNet and LSTM Encoder-Decoder architecture

vanilla vqa_v1 PyTorch implementation

A comprehensive study evaluating 10 CNN image classification models for optimal performance in medical image recognition.

This project is a real-time traffic sign recognition system built using Python, OpenCV, and a pre-trained CNN model, capable of detecting and recognizing traffic signs from images.

U-Net Like Pretrained Model For Human Body Segmentation

In this repo, I implemented VGGNet, MobileNet and AlexNet and compared their performance on Emotion Detection Task using AffectNet dataset.

CBAM: Convolutional Block Attention Module for CIFAR100 on VGG19

Implementing Classic CNN Architectures (AlexNet, VGG, ResNet, GoogLeNet) in PyTorch.

Non-local Modeling for Image Quality Assessment

Here is pytorch implementation of VGG16 from scratch. It was trained on animal dataset for animal classification. It is a pratical project for basic skills in computer vision.

Teachable Machine provides an intuitive and user-friendly way to create machine learning models for images classification tasks. It allows you to train models directly in your browser by providing examples of different classes and labeling them accordingly. The models can then be exported and used in various applications.

Insights and Analysis - Using Various Deep Learning Architectures on Image Classification Datasets

This repository is based on a project completed as part of the Deep Learning Specialization on Coursera by DeepLearning.AI.

까먹으면 다시 보려고 정리합니다.

This repository aims to provide a valuable resource for individuals interested in learning and mastering TensorFlow, an open-source machine learning framework developed by Google.