Программы по дисциплине "Современные методы глубокого машинного обучения" 6 семестра ФИТ НГУ
-
Updated
May 23, 2024 - Jupyter Notebook
Программы по дисциплине "Современные методы глубокого машинного обучения" 6 семестра ФИТ НГУ
DSen2-CR: A network for removing clouds from Sentinel-2 images. This repo contains the model code, written in Python/Keras, as well as links to pre-trained checkpoints and the SEN12MS-CR dataset.
This is a model for detecting the crop disease detection using ResNet50. The dataset images are annoted in Roboflow and called in the program through it's api.
Deep learning model to predict the normal flow between two consecutive frames, being the normal flow the projection of the optical flow on the gradient directions.
ChurnNet: Deep Learning Enhanced Customer Churn Prediction in Telecommunication Industry
Final project assigned for the Introduction to Image Processing (EE 475) course in the Spring 2023 semester.
Residual Neural Network Object Detector written for Pycocotool's library. Model implements custom skip block connections and uses a custom dataset loader for image classification object detection.
NLP methods is practiced including GPT, Machine-translation, Q&A models
GAN based Super resolution media engine
Code and data for our research work on "Comparative assessment of image super-resolution techniques for spatial downscaling of IMD Gridded Rainfall Data"
Pokemon Classification Contest
Deep Neural Networks for music genre classification as a proxy for multiple analytical studies
Designed a smaller architecture implemented from the paper Deep Residual Learning for Image Recognition and achieved 93.65% accuracy.
Residual learning: A new paradigm to improve deep learning-based segmentation of the left ventricle in magnetic resonance imaging cardiac images
CNN implementation of article 'Segmentation of Drilled Holes in Texture Wooden Furniture Panels Using Deep Neural Network' by Rytis Augustauskas, Arūnas Lipnickas and Tadas Surgailis
3D residual neural network that predicts age based on brain MRI images (implemented using TensorFlow 2).
Uses pediatric x-rays and data to build a classification model that can predict whether or not a patient has pneumonia.
Keras Functional API implementation of the 50-layer residual neural network (ResNet-50) and its application to sign language digit recognition
HResNet with Attention for HSI classification
Add a description, image, and links to the residual-neural-network topic page so that developers can more easily learn about it.
To associate your repository with the residual-neural-network topic, visit your repo's landing page and select "manage topics."