There are no reviews yet. Be the first to send feedback to the community and the maintainers!
All-of-Statistics-Exercises
This repo documents some of my drafted solutions to the exercises from All of Statistics by Larry Wasserman. This repo only contains solutions to exercises that requires computer experiment. The book is a handy reference to most concepts of statistics.End2End-Controllable-Instagram-Captioning
An end-to-end approach to build an image captioning model with engaging captions and controllable attributesd435_module
Python module for Realsense D435i cameraTweakStory
Deployment repo for the trained stylised-controllable-image-captioning model.WGANGP-Presentation
Materials for my presentation on 17/07/2019 in Hong Kong Machine Learning Meetup. The topic is WGAN-GP (Wasserstein Generative Adversarial Network with Gradient Penalty)Keras-UNet-Foreground-Extraction
Using U-Net for foreground and background separation on biomedical imageDeepLearning-Navigation
Document my capstone project in master programmeULMFit-IMDB
extended analysis on ULMFit modeling from lesson 4, Practical Deep Learning for Coders (fast.ai)Divide_and_Conquer_Algo
This repository aims to document my learning progress on a MOOC course "Divide and Conquer, Sorting and Searching, and Randomized Algorithms" by Stanford UniversityCycleGAN-FastAI
as a proof-of-concept, test if CycleGAN can learn spatial variation from images with multiple MNIST digitsriven314.github.io
OBSOLETE, PLEASE GO TO https://github.com/riven314/alexlauwhSelfDrivingCar_Simulator
This repo documents my work on training a CNN model for self-driving car. I deployed fastai framework for model training. I experimented with different models, the first two being pretrained ResNet34 and the CNN proposed by NVIDIA in literature.FasterRCNN-Pipeline-Pytorch
Setup a pipeline for training (transfer learning) Faster-RCNN in PyTorch. Data are in VOC formatPerceptualLoss-FastAI
Implementing "Perceptual Losses for Real-Time Style Transfer and Super-Resolution" with FastAI framework. Apply hook (PyTorch mechanism) to calculate loss.Love Open Source and this site? Check out how you can help us