cuguilke / Microexpnet
Licence: mit
MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Frontal Face Images
Stars: ✭ 121
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Microexpnet
Channel Pruning
Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)
Stars: ✭ 979 (+709.09%)
Mutual labels: deep-neural-networks, model-compression
Model Compression Papers
Papers for deep neural network compression and acceleration
Stars: ✭ 296 (+144.63%)
Mutual labels: deep-neural-networks, model-compression
Condensa
Programmable Neural Network Compression
Stars: ✭ 129 (+6.61%)
Mutual labels: deep-neural-networks, model-compression
Knowledge Distillation Pytorch
A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility
Stars: ✭ 986 (+714.88%)
Mutual labels: deep-neural-networks, model-compression
Machine Learning Demystified
A weekly workshop series at ITP to teach machine learning with a focus on deep learning
Stars: ✭ 114 (-5.79%)
Mutual labels: deep-neural-networks
Hawq
Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.
Stars: ✭ 108 (-10.74%)
Mutual labels: model-compression
Video To Retail Platform
An intelligent multimodal-learning based system for video, product and ads analysis. Based on the system, people can build a lot of downstream applications such as product recommendation, video retrieval, etc.
Stars: ✭ 108 (-10.74%)
Mutual labels: deep-neural-networks
Deep learning object detection
A paper list of object detection using deep learning.
Stars: ✭ 10,334 (+8440.5%)
Mutual labels: deep-neural-networks
Awesome Model Compression
papers about model compression
Stars: ✭ 119 (-1.65%)
Mutual labels: model-compression
Ml Fraud Detection
Credit card fraud detection through logistic regression, k-means, and deep learning.
Stars: ✭ 117 (-3.31%)
Mutual labels: deep-neural-networks
Deepcpg
Deep neural networks for predicting CpG methylation
Stars: ✭ 113 (-6.61%)
Mutual labels: deep-neural-networks
Deep architect
A general, modular, and programmable architecture search framework
Stars: ✭ 110 (-9.09%)
Mutual labels: deep-neural-networks
Tfg Voice Conversion
Deep Learning-based Voice Conversion system
Stars: ✭ 115 (-4.96%)
Mutual labels: deep-neural-networks
Torch Dreams
Making neural networks more interpretable, for research and art 🔎 💻 :brain: 🎨
Stars: ✭ 102 (-15.7%)
Mutual labels: deep-neural-networks
Deephyper
DeepHyper: Scalable Asynchronous Neural Architecture and Hyperparameter Search for Deep Neural Networks
Stars: ✭ 117 (-3.31%)
Mutual labels: deep-neural-networks
Adversarialdnn Playground
VizSec17: Web-based visualization tool for adversarial machine learning / LiveDemo
Stars: ✭ 113 (-6.61%)
Mutual labels: deep-neural-networks
Onnx
Open standard for machine learning interoperability
Stars: ✭ 11,829 (+9676.03%)
Mutual labels: deep-neural-networks
Tf2
An Open Source Deep Learning Inference Engine Based on FPGA
Stars: ✭ 113 (-6.61%)
Mutual labels: model-compression
Gpnd
Generative Probabilistic Novelty Detection with Adversarial Autoencoders
Stars: ✭ 112 (-7.44%)
Mutual labels: deep-neural-networks
MicroExpNet
By Ilke Cugu, Eren Sener, Emre Akbas.
Table of Contents
Introduction
MicroExpNet is an extremely small (under 1MB) and fast (1851 FPS on i7 CPU) TensorFlow convolutional neural network model for facial expression recognition (FER) from frontal face images. This repository contains the codes described in the paper "MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Face Images" (https://arxiv.org/abs/1711.07011v4).
Full list of items
- MicroExpNet.py: The original source code of the proposed FER model
- exampleUsage.py: A script to get prediction from a pre-trained MicroExpNet for an unlabeled image
- Models: Pre-trained MicroExpNet models for CK+ and Oulu-CASIA datasets.
- Candidates: Candidate networks build in search of a better FER model
Citation
If you use these models in your research, please cite:
@inproceedings{cugu2019microexpnet,
title={MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Face Images},
author={Cugu, Ilke and Sener, Eren and Akbas, Emre},
booktitle={2019 Ninth International Conference on Image Processing Theory, Tools and Applications (IPTA)},
pages={1--6},
year={2019},
organization={IEEE}
}
API
MicroExpNet(x, y, teacherLogits, lr, nClasses, imgXdim, imgYdim, batchSize, keepProb, temperature, lambda_)
This is the class where the magic happens. Take a look at exampleUsage.py for a quick test drive.
Parameters
- x: Tensorflow placeholder for input images
- y: Tensorflow placeholder for one-hot labels (default: None -> unlabeled image testing)
- teacherLogits: Tensorflow placeholder for the logits of the teacher (default: None -> for standalone testing)
- lr: Learning rate (default: 1e-04)
- nClasses: Number of emotion classes (default: 8)
- imgXdim: Dimension of the image (default: 84)
- imgYdim: Dimension of the image (default: 84)
- batchSize: Batch size (default: 64)
- keepProb: Dropout (default: 1)
- temperature: The hyperparameter to soften the teacher's probability distributions (default: 8)
- lamba_: Weight of the soft targets (default: 0.5)
Models
We provide pre-trained MicroExpNet models for both CK+ and Oulu-CASIA.
In addition, one can find sample pre-trained teacher models which are derived from the original Keras implementation of Inception_v3:
Labels of the both models
0: neutral, 1: anger, 2: contempt, 3: disgust, 4: fear, 5: happy, 6: sadness, 7: surprise
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].