GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → backnotprop → Fast Style Transfer Coreml

backnotprop / Fast Style Transfer Coreml

Licence: mit

Programming Languages

python
139335 projects - #7 most used programming language

Labels

iostensorflowcoremlstyle-transfer

Projects that are alternatives of or similar to Fast Style Transfer Coreml

mlmodelzoo
Build your iOS 11+ apps with the ready-to-use Core ML models below
Stars: ✭ 17 (-84.4%)
Mutual labels:  style-transfer, coreml
Pytorch Neural Style Transfer
Reconstruction of the original paper on neural style transfer (Gatys et al.). I've additionally included reconstruction scripts which allow you to reconstruct only the content or the style of the image - for better understanding of how NST works.
Stars: ✭ 106 (-2.75%)
Mutual labels:  style-transfer
Adaptive Style Transfer
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
Stars: ✭ 85 (-22.02%)
Mutual labels:  style-transfer
Nsfwdetector
A NSFW (aka porn) detector with CoreML
Stars: ✭ 1,364 (+1151.38%)
Mutual labels:  coreml
Unityvision Ios
This native plugin enables Unity to take advantage of specific features of Core-ML and Vision Framework on the iOS platform.
Stars: ✭ 85 (-22.02%)
Mutual labels:  coreml
Ios Learning Materials
📚Curated list of articles, web-resources, tutorials and code repositories that may help you dig a little bit deeper into iOS [and Apple Platforms].
Stars: ✭ 1,380 (+1166.06%)
Mutual labels:  coreml
Stif Indonesia
Implementation of "Semi-Supervised Low-Resource Style Transfer of Indonesian Informal to Formal Language with Iterative Forward-Translation".
Stars: ✭ 79 (-27.52%)
Mutual labels:  style-transfer
Fast Style Transfer
TensorFlow CNN for fast style transfer ⚡🖥🎨🖼
Stars: ✭ 10,240 (+9294.5%)
Mutual labels:  style-transfer
Style transfer
Data-parallel image stylization using Caffe.
Stars: ✭ 106 (-2.75%)
Mutual labels:  style-transfer
Arkit Sampler
Code examples for ARKit.
Stars: ✭ 1,334 (+1123.85%)
Mutual labels:  coreml
Face landmark dnn
Face Landmark Detector based on Mobilenet V1
Stars: ✭ 92 (-15.6%)
Mutual labels:  coreml
Deep Image Analogy
The source code of 'Visual Attribute Transfer through Deep Image Analogy'.
Stars: ✭ 1,296 (+1088.99%)
Mutual labels:  style-transfer
Sentimentcoremldemo
😃 iOS11 demo application for sentiment polarity analysis.
Stars: ✭ 104 (-4.59%)
Mutual labels:  coreml
Ios Openpose
OpenPose Example App
Stars: ✭ 85 (-22.02%)
Mutual labels:  coreml
Linguistic Style Transfer
Neural network parametrized objective to disentangle and transfer style and content in text
Stars: ✭ 106 (-2.75%)
Mutual labels:  style-transfer
Frostnet
FrostNet: Towards Quantization-Aware Network Architecture Search
Stars: ✭ 85 (-22.02%)
Mutual labels:  style-transfer
Coremldemo
A simple demo for Core ML
Stars: ✭ 90 (-17.43%)
Mutual labels:  coreml
Neural Style Transfer Papers
✏️ Neural Style Transfer: A Review
Stars: ✭ 1,372 (+1158.72%)
Mutual labels:  style-transfer
Exermote
Using Machine Learning to predict the type of exercise from movement data
Stars: ✭ 108 (-0.92%)
Mutual labels:  coreml
Yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
Stars: ✭ 19,914 (+18169.72%)
Mutual labels:  coreml
View All Similar Projects ➔

Fast Style Transfer, CoreML, TensorFlow

Create an iOS app — like Prisma — with CoreML, Fast Style Transfer, and TensorFlow.

Installation

git clone https://github.com/mdramos/fast-style-transfer-coreml.git

Dependencies

Note that you'll want to make the necessary adjustments for Fast-Style-Transfer and TensorFlow-CoreML. I write about these in my medium article. The adjusments are also available in this repo: fst and tf-coreml.

Models

You can train your own models using FST, and use my adjustments to convert them to CoreML models. I've already converted the pre-trained models from FST:

CoreML Models: https://drive.google.com/drive/folders/1CBSanBHbXC5-bJNTTk3-r1WSq56z0eKG?usp=sharing

iOS

Once you have your models, just import them into the Xcode project. The current setup looks for a particular set of models (wave, udnie, rain_princess, and la_muse)

License

Copyright (c) 2018 Michael Ramos. MIT on any of my code, but you'll need to abide by the Licences of the libraries used (FST, tf-coreml)

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].