All Projects → d-li14 → Face Attribute Prediction

d-li14 / Face Attribute Prediction

Licence: mit
Face Attribute Prediction on CelebA benchmark with PyTorch Implementation

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Face Attribute Prediction

Transfer Learning Conv Ai
🦄 State-of-the-Art Conversational AI with Transfer Learning
Stars: ✭ 1,217 (+1222.83%)
Mutual labels:  neural-networks
Variational Capsule Routing
Official Pytorch code for (AAAI 2020) paper "Capsule Routing via Variational Bayes", https://arxiv.org/pdf/1905.11455.pdf
Stars: ✭ 84 (-8.7%)
Mutual labels:  neural-networks
Vvedenie Mashinnoe Obuchenie
📝 Подборка ресурсов по машинному обучению
Stars: ✭ 1,282 (+1293.48%)
Mutual labels:  neural-networks
Tensorflow seq2seq chatbot
Stars: ✭ 81 (-11.96%)
Mutual labels:  neural-networks
Dltk
Deep Learning Toolkit for Medical Image Analysis
Stars: ✭ 1,249 (+1257.61%)
Mutual labels:  neural-networks
Knet.jl
Koç University deep learning framework.
Stars: ✭ 1,260 (+1269.57%)
Mutual labels:  neural-networks
Abigsurvey
A collection of 500+ survey papers on Natural Language Processing (NLP) and Machine Learning (ML)
Stars: ✭ 1,203 (+1207.61%)
Mutual labels:  neural-networks
Deeplearninganimepapers
A list of papers and other resources on deep learning with anime style images.
Stars: ✭ 1,307 (+1320.65%)
Mutual labels:  neural-networks
Sonnet
TensorFlow-based neural network library
Stars: ✭ 9,129 (+9822.83%)
Mutual labels:  neural-networks
Awesome Medical Imaging
Awesome list of software that I use to do research in medical imaging.
Stars: ✭ 87 (-5.43%)
Mutual labels:  neural-networks
Attend infer repeat
A Tensorfflow implementation of Attend, Infer, Repeat
Stars: ✭ 82 (-10.87%)
Mutual labels:  neural-networks
Neural Networks
brief introduction to Python for neural networks
Stars: ✭ 82 (-10.87%)
Mutual labels:  neural-networks
Backpropaganda
A simple JavaScript neural network framework.
Stars: ✭ 86 (-6.52%)
Mutual labels:  neural-networks
Deepsmiles
DeepSMILES - A variant of SMILES for use in machine-learning
Stars: ✭ 80 (-13.04%)
Mutual labels:  neural-networks
Ennui
An Elegant Neural Network User Interface to build drag-and-drop neural networks, train in the browser, visualize during training, and export to Python.
Stars: ✭ 90 (-2.17%)
Mutual labels:  neural-networks
Wav2letter
Speech Recognition model based off of FAIR research paper built using Pytorch.
Stars: ✭ 78 (-15.22%)
Mutual labels:  neural-networks
Pumas.jl
Pharmaceutical Modeling and Simulation for Nonlinear Mixed Effects (NLME), Quantiative Systems Pharmacology (QsP), Physiologically-Based Pharmacokinetics (PBPK) models mixed with machine learning
Stars: ✭ 84 (-8.7%)
Mutual labels:  neural-networks
Tageditor
🏖TagEditor - Annotation tool for spaCy
Stars: ✭ 92 (+0%)
Mutual labels:  neural-networks
Riddle
Race and ethnicity Imputation from Disease history with Deep LEarning
Stars: ✭ 91 (-1.09%)
Mutual labels:  neural-networks
Pytorch Openai Transformer Lm
🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
Stars: ✭ 1,268 (+1278.26%)
Mutual labels:  neural-networks

face-attribute-prediction

Face Attribute Prediction on CelebA benchmark with PyTorch Implemantation, heavily borrowed from my MobileNetV2 implementation.

Dependencies

  • Anaconda3 (Python 3.6+, with Numpy etc.)
  • PyTorch 0.4+
  • tensorboard, tensorboardX

Dataset

CelebA dataset is a large-scale face dataset with attribute-based annotations. Cropped and aligned face regions are utilized as the training source. For the pre-processed data and specific split, please feel free to contact me: [email protected]

Features

  • Both ResNet and MobileNet as the backbone for scalability
  • Each of the 40 annotated attributes predicted with multi-head networks
  • Achieve ~92% average accuracy, comparative to state-of-the-art
  • Fast convergence (5~10 epochs) through finetuning the ImageNet pre-trained models
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].