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 → shekit → mirror-selfie

shekit / mirror-selfie

Licence: other
Removing the phone from the notorious mirror selfie using deep learning

Programming Languages

Jupyter Notebook
11667 projects

Labels

deep-learningtensorflowkerasjupyter-notebookkeras-tensorflow

Projects that are alternatives of or similar to mirror-selfie

Deep-Quality-Value-Family
Official implementation of the paper "Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning Algorithms": https://arxiv.org/abs/1909.01779 To appear at the next NeurIPS2019 DRL-Workshop
Stars: ✭ 12 (-67.57%)
Mutual labels:  keras-tensorflow
Deep-Learning-Course
Deep Learning with TensorFlow and Keras
Stars: ✭ 13 (-64.86%)
Mutual labels:  keras-tensorflow
mpc-DL-controller
Deep Neural Network architecture as a predictive optimal controller for {HVAC+Solar cell + battery} disturbance afflicted system vs classic Model Predictive Control
Stars: ✭ 37 (+0%)
Mutual labels:  keras-tensorflow
keras-yolo3-facedetection
Real-time face detection model using YOLOv3 with Keras
Stars: ✭ 13 (-64.86%)
Mutual labels:  keras-tensorflow
stocktwits-sentiment
Stocktwits market sentiment analysis in Python with Keras and TensorFlow.
Stars: ✭ 23 (-37.84%)
Mutual labels:  keras-tensorflow
fashion-parser
Fashion item segmentation with deep learning
Stars: ✭ 22 (-40.54%)
Mutual labels:  keras-tensorflow
gcnn keras
Graph convolution with tf.keras
Stars: ✭ 47 (+27.03%)
Mutual labels:  keras-tensorflow
Lecture-3-Linear-Models
ICDSS Machine Learning Workshop Series: Linear Models
Stars: ✭ 19 (-48.65%)
Mutual labels:  keras-tensorflow
Bebop-Autonomy-Vision
An autonomous, vision-based Bebop drone.
Stars: ✭ 24 (-35.14%)
Mutual labels:  keras-tensorflow
Konverter
Convert simple Keras models to pure Python 🐍+ NumPy
Stars: ✭ 34 (-8.11%)
Mutual labels:  keras-tensorflow
keras-complex
Keras-Tensorflow implementation of complex-valued convolutional neural networks
Stars: ✭ 96 (+159.46%)
Mutual labels:  keras-tensorflow
Rus-SpeechRecognition-LSTM-CTC-VoxForge
Распознавание речи русского языка используя Tensorflow, обучаясь на базе Voxforge
Stars: ✭ 50 (+35.14%)
Mutual labels:  keras-tensorflow
MAX-Audio-Classifier
Identify sounds in short audio clips
Stars: ✭ 115 (+210.81%)
Mutual labels:  keras-tensorflow
One-Shot-Learning
Matching Networks Tensorflow 2 Implementation for few-shot AD diagnosis
Stars: ✭ 22 (-40.54%)
Mutual labels:  keras-tensorflow
Text and Audio classification with Bert
Text Classification in Turkish Texts with Bert
Stars: ✭ 34 (-8.11%)
Mutual labels:  keras-tensorflow
dl-relu
Deep Learning using Rectified Linear Units (ReLU)
Stars: ✭ 20 (-45.95%)
Mutual labels:  keras-tensorflow
Detection-of-Small-Flying-Objects-in-UAV-Videos
Code for paper "Detection of Flying Honeybees in UAV Videos"
Stars: ✭ 47 (+27.03%)
Mutual labels:  keras-tensorflow
book-ml
書籍「今すぐ試したい！機械学習・深層学習（ディープラーニング）画像認識プログラミングレシピ」のソースコードを配布するレポジトリです。
Stars: ✭ 29 (-21.62%)
Mutual labels:  keras-tensorflow
pytorch2keras
PyTorch to Keras model convertor
Stars: ✭ 788 (+2029.73%)
Mutual labels:  keras-tensorflow
extra keras datasets
📃🎉 Additional datasets for tensorflow.keras
Stars: ✭ 20 (-45.95%)
Mutual labels:  keras-tensorflow
View All Similar Projects ➔

Mirror Selfie

Removing the phone from the notorious mirror selfie using deep learning

Demo Video

Full Video

How to run

The notebooks were created and run in Google colab. A google colab runtime resets every 12 hours. You can link it to your google drive to help with file persistence.

  • mirror_selfie.ipynb - detect masks and do inpainting based on your trained model
  • training_inpainting.ipynb - train the inpainting model on your own dataset

Code is based on the following work:

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].