stratospark/UnityImageSynthesisTutorial1
Use Unity to generate synthetic images for deep learning image segmentation in PyTorch and fastai
This project helps you create realistic training images for machine learning models that identify different objects within pictures. You feed in 3D models of objects, and it generates a large dataset of images with corresponding labels, which can then be used to train an image segmentation network. This is for anyone who needs to teach a computer to recognize specific objects in images but lacks enough real-world examples.
102 stars. No commits in the last 6 months.
Use this if you need to train an image segmentation model to identify objects, but you don't have enough real-world images or struggle with manually labeling your data.
Not ideal if you already have a large, labeled dataset of real-world images or if your project doesn't involve identifying specific objects within images.
Stars
102
Forks
22
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 21, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/stratospark/UnityImageSynthesisTutorial1"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
asus4/tf-lite-unity-sample
TensorFlow Lite Samples on Unity
Syn-McJ/TFClassify-Unity
An example of using Tensorflow with Unity for image classification and object detection.
Syn-McJ/TFClassify-Unity-Barracuda
An example of using Tensorflow and ONNX models with Unity Barracuda inference engine for image...
doughtmw/HoloLens2-Machine-Learning
Using deep learning models for image classification directly on the HoloLens 2.
Unity-Technologies/datasetinsights
Synthetic Dataset Insights