All Projects → stratospark → UnityImageSynthesisTutorial1

stratospark / UnityImageSynthesisTutorial1

Licence: MIT license
Use Unity to generate synthetic images for deep learning image segmentation in PyTorch and fastai

Programming Languages

Jupyter Notebook
11667 projects
C#
18002 projects
ShaderLab
938 projects

Projects that are alternatives of or similar to UnityImageSynthesisTutorial1

segRetino
An implementation of the research paper "Retina Blood Vessel Segmentation Using A U-Net Based Convolutional Neural Network"
Stars: ✭ 23 (-75.27%)
Mutual labels:  image-segmentation
fastdownload
Easily download, verify, and extract archives
Stars: ✭ 35 (-62.37%)
Mutual labels:  fastai
ailia-models
The collection of pre-trained, state-of-the-art AI models for ailia SDK
Stars: ✭ 1,102 (+1084.95%)
Mutual labels:  image-segmentation
ZeroSimROSUnity
Robotic simulation in Unity with ROS integration.
Stars: ✭ 112 (+20.43%)
Mutual labels:  image-segmentation
BusterNet
No description or website provided.
Stars: ✭ 49 (-47.31%)
Mutual labels:  image-segmentation
Plant Disease Detection
Plant Disease Detector Web Application
Stars: ✭ 181 (+94.62%)
Mutual labels:  fastai
fiap-ml-visao-computacional
Repositório dos exemplos e desafios utilizados na disciplina de Visão Computacional do curso de MBA Machine Learning da FIAP
Stars: ✭ 33 (-64.52%)
Mutual labels:  image-segmentation
fastai-docker
Fast.AI course complete docker container for Paperspace and Gradient
Stars: ✭ 52 (-44.09%)
Mutual labels:  fastai
udacity-cvnd-projects
My solutions to the projects assigned for the Udacity Computer Vision Nanodegree
Stars: ✭ 36 (-61.29%)
Mutual labels:  image-segmentation
FAI-notes
Some notes, tutorials, and some experimentation with the fast.ai library (https://github.com/fastai/fastai)
Stars: ✭ 58 (-37.63%)
Mutual labels:  fastai
ulm-basenet
Implementation of ULMFit algorithm for text classification via transfer learning
Stars: ✭ 94 (+1.08%)
Mutual labels:  fastai
fastblog
My fastai blog
Stars: ✭ 20 (-78.49%)
Mutual labels:  fastai
Table-Detection-using-Deep-Learning
Table Detection using Deep Learning
Stars: ✭ 24 (-74.19%)
Mutual labels:  image-segmentation
Markov-Random-Field-Project
This project has two parts. In part one, we use markov random field to denoise an image. In Part two, we use similar model for image segmentation.
Stars: ✭ 97 (+4.3%)
Mutual labels:  image-segmentation
segmentation
Code for my master's thesis. Instance segmentation of fluorescence microscopy images with deep learning.
Stars: ✭ 38 (-59.14%)
Mutual labels:  image-segmentation
fastai slack
Get Slack notifications while training FastAI models
Stars: ✭ 14 (-84.95%)
Mutual labels:  fastai
encrypted-skin-cancer-detection
Detecting skin cancer in encrypted images with TensorFlow
Stars: ✭ 27 (-70.97%)
Mutual labels:  fastai
fasterai1
FasterAI: A repository for making smaller and faster models with the FastAI library.
Stars: ✭ 34 (-63.44%)
Mutual labels:  fastai
FCN-CTSCAN
A small TensorFlow project created to test some machine learning problems
Stars: ✭ 17 (-81.72%)
Mutual labels:  image-segmentation
fastai sequence tagging
sequence tagging for NER for ULMFiT
Stars: ✭ 21 (-77.42%)
Mutual labels:  fastai

Unity Image Synthesis

This project will help you get up to speed with generating synthetic training images in Unity. You don't need any experience with Unity, but experience with Python and the fastai library/course is recommended. By the end of the tutorial, you will have trained an image segmentation network that can recognize different 3d solids.

Read more details on my blog

Follow along with the video tutorial

Getting Started

  1. Clone the repo
  2. Open the project with Unity / Unity Hub (2018.3.2 recommended)
  3. Open up the "Solids" scene
  4. Create a "captures/train" and "captures/val" folders
  5. Open up the SceneControl object and enable Save/grayscale if you want to do fastai training. Otherwise, leave those disabled and just see the annotations within Unity.
  6. Press the Run button
  7. Create a secondary Game window and change the Display to Display 3 for layer based category annotations.
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].