snapml-templates
This repository provides training notebooks for Lens Studio templates powered with Snap ML. Each notebook allows to train a model which then can be brought into Lens Studio project.
Templates
Style Transfer
Allows you to train Style Transfer model based on provided image.
- Notebook
- Dataset: COCO dataset
- Template Guide
Classification
Provides an example of binary classification
- Notebook
- Dataset: CelebA
- Template Guide
Object Detection
Provides an example of the car detection
- Notebook
- Dataset: COCO
- Template Guide
Custom Segmentation
Provides an example of pizza segmentation
- Notebook
- Dataset: COCO
- Template Guide
Keyword Detection
Provides an example of training a model that classifies spectrogram images generated from audio.
- Notebook
- Dataset: SpeechCommands
- Template Guide
Image-to-Image Translation
Demonstrates how to train and compress popular image-to-image networks like CycleGAN and Pix2Pix so that we could achieve real time performance on mobile devices.
- Notebook
- Template Guide (This model is compatible with Style Transfer Template)
Multi Class Classification with Quantization
Demonstrates how to train an image classification models with Keras and TFLite model maker and quantize them using TensorFlow
License
A license file is included with each folder project. The full license can be found here: https://lensstudio.snapchat.com/template-license