All Projects → iwantooxxoox → Keras Openface

iwantooxxoox / Keras Openface

Licence: apache-2.0
Keras-OpenFace is a project converting OpenFace from Torch implementation to a Keras version

Projects that are alternatives of or similar to Keras Openface

Ios Coreml Mnist
Real-time Number Recognition using Apple's CoreML 2.0 and MNIST -
Stars: ✭ 74 (-86.25%)
Mutual labels:  jupyter-notebook, coreml
Pytorch Learners Tutorial
PyTorch tutorial for learners
Stars: ✭ 97 (-81.97%)
Mutual labels:  jupyter-notebook, torch
Coreml Training
Source code for my blog post series "On-device training with Core ML"
Stars: ✭ 77 (-85.69%)
Mutual labels:  jupyter-notebook, coreml
Build Ocr
Build an OCR for iOS apps
Stars: ✭ 17 (-96.84%)
Mutual labels:  jupyter-notebook, coreml
Orn
Oriented Response Networks, in CVPR 2017
Stars: ✭ 207 (-61.52%)
Mutual labels:  jupyter-notebook, torch
Har Keras Coreml
Human Activity Recognition (HAR) with Keras and CoreML
Stars: ✭ 23 (-95.72%)
Mutual labels:  jupyter-notebook, coreml
Beauty.torch
Understanding facial beauty with deep learning.
Stars: ✭ 90 (-83.27%)
Mutual labels:  jupyter-notebook, torch
Posenet Coreml
I checked the performance by running PoseNet on CoreML
Stars: ✭ 143 (-73.42%)
Mutual labels:  coreml, mobilenet
Ios Coreml Yolo
Almost Real-time Object Detection using Apple's CoreML and YOLO v1 -
Stars: ✭ 153 (-71.56%)
Mutual labels:  jupyter-notebook, coreml
Mnist draw
This is a sample project demonstrating the use of Keras (Tensorflow) for the training of a MNIST model for handwriting recognition using CoreML on iOS 11 for inference.
Stars: ✭ 139 (-74.16%)
Mutual labels:  jupyter-notebook, coreml
Keras Idiomatic Programmer
Books, Presentations, Workshops, Notebook Labs, and Model Zoo for Software Engineers and Data Scientists wanting to learn the TF.Keras Machine Learning framework
Stars: ✭ 720 (+33.83%)
Mutual labels:  jupyter-notebook, mobilenet
Php Opencv Examples
Tutorial for computer vision and machine learning in PHP 7/8 by opencv (installation + examples + documentation)
Stars: ✭ 333 (-38.1%)
Mutual labels:  torch, mobilenet
Netron
Visualizer for neural network, deep learning, and machine learning models
Stars: ✭ 17,193 (+3095.72%)
Mutual labels:  torch, coreml
Shapedetector keras coreml
Deep learning installed Shape Detector using Keras and CoreML 📱
Stars: ✭ 25 (-95.35%)
Mutual labels:  jupyter-notebook, coreml
Swiftopenpose
tf-openpose Based iOS Project
Stars: ✭ 215 (-60.04%)
Mutual labels:  coreml, mobilenet
Deep Dream In Pytorch
Pytorch implementation of the DeepDream computer vision algorithm
Stars: ✭ 90 (-83.27%)
Mutual labels:  jupyter-notebook, torch
Face landmark dnn
Face Landmark Detector based on Mobilenet V1
Stars: ✭ 92 (-82.9%)
Mutual labels:  coreml, mobilenet
Tensorflow realtime multi Person pose estimation
Multi-Person Pose Estimation project for Tensorflow 2.0 with a small and fast model based on MobilenetV3
Stars: ✭ 129 (-76.02%)
Mutual labels:  jupyter-notebook, mobilenet
Adaptiveattention
Implementation of "Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning"
Stars: ✭ 303 (-43.68%)
Mutual labels:  jupyter-notebook, torch
Torch2coreml
Torch7 -> CoreML
Stars: ✭ 363 (-32.53%)
Mutual labels:  torch, coreml

Keras-OpenFace

Keras-OpenFace is a project converting OpenFace from it's original Torch implementation to a Keras version

If you are only interested in using pre-trained model

Load the Keras OpenFace model(Accuracy: 0.938+-0.013)

from keras.models import load_model
from keras.utils import CustomObjectScope
import tensorflow as tf
with CustomObjectScope({'tf': tf}):
  model = load_model('./model/nn4.small2.v1.h5')

Running the whole convertion process and look into Kears-Openface-convertion.ipynb

$ jupyter notebook

CoreML-OpenFace

Pre-trained CoreML version of OpenFace in model/openface.coreml which you can easily integrate OpenFace into your iOS application.

License

Unless otherwise stated, the source code, notebook files, and trained Tensorflow and Keras model files are licensed under the Apache 2.0 License.

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].