Hafiz Latif's Projects
This is a repository containing code to Paper "Optimized High Resolution 3D Dense-U-Net Network for Brain and Spine Segmentation" published at MDPI Applied sciences journal - https://www.mdpi.com/2076-3417/9/3/404 .
A resource repository for 3D machine learning
Keras implementation of the paper "3D MRI brain tumor segmentation using autoencoder regularization" by Myronenko A. (https://arxiv.org/abs/1810.11654).
3D Unet biomedical segmentation model powered by tensorpack with fast io speed
Keras 3D U-Net Convolution Neural Network (CNN) designed for medical image segmentation
Fast and flexible AutoML with learning guarantees.
fast image augmentation library and easy to use wrapper around other libraries
Use of Attention Gates in a Convolutional Neural Network / Medical Image Classification and Segmentation
Image augmentation library in Python for machine learning.
A specially designed light version of Fast AutoAugment
Python package for Imputation Methods
A curated list of awesome Dash (plotly) resources
:whale: A curated list of Docker resources and projects
Awesome GAN for Medical Imaging
A curated list of awesome Jupyter projects, libraries and resources
:metal: awesome-semantic-segmentation
A curated list of awesome TensorFlow Lite models, samples, tutorials, tools and learning resources.
[MSG-GAN] Any body can GAN! Highly stable and robust architecture. Requires little to no hyperparameter tuning.
Network: FCN, U-Net, Unet+Resblock(DeepUNet), Squeeze+UNet, DenseNet+UNet(DenseUnet)...
Deep learning software to decode EEG or MEG signals
Master programming by recreating your favorite technologies from scratch.
The manuscript has been accepted in TMI.
mask R-CNN multi class classification example
DICOM Image Segmentation with CNNs in Tensorflow
Code for reproducing the results of our paper on CNN-based medical image segmentation
Python script for illustrating Convolutional Neural Networks (CNN) using Keras-like model definitions
Full Stack Deep Learning Online Course
Learning to apply core machine learning techniques — such as classification, perceptron, neural networks, support vector machines, hidden Markov models, and nonparametric models of clustering — as well as fundamental concepts such as feature selection, cross-validation and over-fitting. Programming machine learning algorithms to make sense of a wide range of data, such as genetic data, data used to perform customer segmentation or data used to predict the outcome of elections.
Learning how to apply advanced decision techniques such as real options, Monte Carlo simulation, network concepts from graph theory, probability theory and statistical physics to analyze and predict the behavior of social, economic and transportation networks. Examples include project portfolio management, pharmaceutical drug development, oil and gas investment decisions as well as philanthropic portfolio decisions requiring high-stake tradeoffs in highly uncertain environments.