Milad Soltany's starred repositories
Complete-Python-3-Bootcamp
Course Files for Complete Python 3 Bootcamp Course on Udemy
Awesome-Diffusion-Models-in-Medical-Imaging
Diffusion Models in Medical Imaging (Published in Medical Image Analysis Journal)
Face-Detection
Face detection using yolov5
Awesome-Transformer-in-Medical-Imaging
[MedIA Journal] An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites
fourier-feature-networks
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
Two-Steps-GVF-Snake-Model
Active contours, or snakes, are widely used in medical image processing applications, mainly to locate the desired area boundaries. Gradient vector flow (GVF) field, like other methods of calculating external force fields, is proposed to address ordinary snake models’ problems, such as poor convergence in indentations and low accuracy in segmentation of objects owned weak borders. These problems are most pronounced in high-noise images, such as ultrasound images. In order to solve the problems more, we utilized the generalized gradient vector flow snake model using minimal surface and two steps converging using both vector based normalization and component-based normalization with distinct controlling parameters on active contour. We adopt minimal surface function to address the problem of low segmentation accuracy in other conventional methods. We also use two steps converging using both vector-based and component-based normalization with distinct controlling parameters to improve the snake curve converging into long and thin indentations plus higher accuracy in noisy and meandering areas. The results obtained and compared with other methods show that the proposed active contour model not only can converge better into long and thin indentations, along with maintaining weak boundaries but also shows higher accuracy in segmentation of tortuous areas, especially in noisy images.
dropconnect-tensorflow
An implementation of DropConnect Layer (Dense, Conv2D, and Wrapper(for all TensorFlow Layers)) in Tensorflow 2
Physics-based-neural-network
Physics-based neural network with Sine Activation Function
sincnet-tensorflow
An Implementation of SincNet using Tenorflow 2.x.
rotary-embedding-tensorflow
Implementation of Rotary Embeddings, from the Roformer paper, in Tensorflow
sparselayer-tensorflow
An implementation of Sparse Layers in TensorFlow 2. x.
LIGHT-SERNET
Light-SERNet: A lightweight fully convolutional neural network for speech emotion recognition
Conference-Acceptance-Rate
Acceptance rates for the major AI conferences
Autonomous-Car-Simulation-Based-on-AVIS-Engine-FIRA-2021
A code for implementing autonomous car software, including environment perception, lanes detection, identifying traffic signs, and controlling the vehicle with digital PID.
adversarial
Code and hyperparameters for the paper "Generative Adversarial Networks"
Autonomous-Vehicle-Environment-Perception
An Intelligent Modular Real-Time Vision-Based System for Environment Perception (NeurIPS 2022 Workshop)
Automatic-Parking
Python implementation of an automatic parallel parking system in a virtual environment, including path planning, path tracking, and parallel parking
Ad-Recommender-System
The 2020 Data Days Competition held at Sharif university of technology.