An implementation of paper `Real-time Convolutional Neural Networks for Emotion and Gender Classification` with PaddlePaddle.

Overview

简介

通过PaddlePaddle框架复现了论文 Real-time Convolutional Neural Networks for Emotion and Gender Classification 中提出的两个模型,分别是SimpleCNNMiniXception。利用 imdb_crop数据集训练模型,进行人脸性别分类,准确率均达到96%。

模型 准确率 输入尺寸
SimpleCNN 96.00% (48, 48, 3)
MiniXception 96.01% (64, 64, 1)

Requirements

scipy==1.2.1
paddlepaddle==2.1.2
numpy==1.20.1
opencv-python==3.4.10.37
pyyaml~=5.4.1
visualdl~=2.2.0
tqdm~=4.62.0

数据准备

我们在数据集imdb_crop (密码 mu2h)上训练模型,数据集也可以在这里下载。下载和解压数据后,不用对数据再做别的处理了,编辑配置文件conf.yamlconf2.yaml,两者分别是SimpleCNNMiniXception的配置文件,把 imdb_dir设置成数据集所在的目录。不用划分训练集和测试集,程序会自动划分,即使你不训练只测试。我们采取的数据集划分方式和论文作者的一样,先根据文件名对图片进行排序,前80%为训练集,后20%为测试集。

训练

在配置文件conf.yamlconf2.yaml里进行相关配置,mode设置成train,其它选项根据个人情况配置。

执行脚本

python train_gender_classfifier.py path_to_conf

比如

python train_gender_classfifier.py ./conf.yaml

path_to_conf 是可选的,默认是 ./conf.yaml,即训练SimpleCNN

测试

在配置文件conf.yamlconf2.yaml里进行相关配置,mode设置成val,另外要配置model_state_dictimdb_dir。训练和测试的imdb_dir是一样的,都是数据集解压后所在的目录,不用对数据进行任何修改。训练和测试的imdb_dir虽然一样,但是训练和测试取的是数据集的不同部分,在上文的数据准备中有提到数据集划分的方式。

执行脚本

python train_gender_classfifier.py path_to_conf

等结果就行了。

指标可视化

你可以通过 visuadl 可视化训练过程中指标(比如损失、准确率等)的变化。可以在配置文件里设置日志的输出目录log_dir,在训练的过程中,每个epoch的准确率、损失、学习率的信息会写到日志中,分trainval两个文件夹。

当要查看指标时,执行以下命令

visualdl --logdir your_logdir --host 127.0.0.1

your_logdir是你设置的日志目录。

然后在浏览器中访问

http://127.0.0.1:8040/

下面展示我们的模型的指标曲线图。

SimpleCNN

avatar

avatar

MiniXception

avatar

avatar

Deep Probabilistic Programming Course @ DIKU

Deep Probabilistic Programming Course @ DIKU

52 May 14, 2022
Concept drift monitoring for HA model servers.

{Fast, Correct, Simple} - pick three Easily compare training and production ML data & model distributions Goals Boxkite is an instrumentation library

98 Dec 15, 2022
Direct Multi-view Multi-person 3D Human Pose Estimation

Implementation of NeurIPS-2021 paper: Direct Multi-view Multi-person 3D Human Pose Estimation [paper] [video-YouTube, video-Bilibili] [slides] This is

Sea AI Lab 251 Dec 30, 2022
Differentiable Annealed Importance Sampling (DAIS)

Differentiable Annealed Importance Sampling (DAIS) This repository contains the code to reproduce the DAIS results from the paper Differentiable Annea

Guodong Zhang 6 Dec 26, 2021
Image data augmentation scheduler for albumentations transforms

albu_scheduler Scheduler for albumentations transforms based on PyTorch schedulers interface Usage TransformMultiStepScheduler import albumentations a

19 Aug 04, 2021
AlgoVision - A Framework for Differentiable Algorithms and Algorithmic Supervision

NeurIPS 2021 Paper "Learning with Algorithmic Supervision via Continuous Relaxations"

Felix Petersen 76 Jan 01, 2023
Implementation of U-Net and SegNet for building segmentation

Specialized project Created by Katrine Nguyen and Martin Wangen-Eriksen as a part of our specialized project at Norwegian University of Science and Te

Martin.w-e 3 Dec 07, 2022
Generate indoor scenes with Transformers

SceneFormer: Indoor Scene Generation with Transformers Initial code release for the Sceneformer paper, contains models, train and test scripts for the

Chandan Yeshwanth 110 Dec 06, 2022
PyTorch implementation of the paper Dynamic Data Augmentation with Gating Networks

Dynamic Data Augmentation with Gating Networks This is an official PyTorch implementation of the paper Dynamic Data Augmentation with Gating Networks

九州大学 ヒューマンインタフェース研究室 3 Oct 26, 2022
[ICCV'21] Pri3D: Can 3D Priors Help 2D Representation Learning?

Pri3D: Can 3D Priors Help 2D Representation Learning? [ICCV 2021] Pri3D leverages 3D priors for downstream 2D image understanding tasks: during pre-tr

Ji Hou 124 Jan 06, 2023
[NeurIPS 2021 Spotlight] Aligning Pretraining for Detection via Object-Level Contrastive Learning

SoCo [NeurIPS 2021 Spotlight] Aligning Pretraining for Detection via Object-Level Contrastive Learning By Fangyun Wei*, Yue Gao*, Zhirong Wu, Han Hu,

Yue Gao 139 Dec 14, 2022
A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run.

Minimal Hand A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run. This project provides the

Yuxiao Zhou 824 Jan 07, 2023
Generalized Data Weighting via Class-level Gradient Manipulation

Generalized Data Weighting via Class-level Gradient Manipulation This repository is the official implementation of Generalized Data Weighting via Clas

18 Nov 12, 2022
Measures input lag without dedicated hardware, performing motion detection on recorded or live video

What is InputLagTimer? This tool can measure input lag by analyzing a video where both the game controller and the game screen can be seen on a webcam

Bruno Gonzalez 4 Aug 18, 2022
Code of Periodic Activation Functions Induce Stationarity

Periodic Activation Functions Induce Stationarity This repository is the official implementation of the methods in the publication: L. Meronen, M. Tra

AaltoML 12 Jun 07, 2022
Face Mask Detection on Image and Video using tensorflow and keras

Face-Mask-Detection Face Mask Detection on Image and Video using tensorflow and keras Train Neural Network on face-mask dataset using tensorflow and k

Nahid Ebrahimian 12 Nov 11, 2022
Notebooks for my "Deep Learning with TensorFlow 2 and Keras" course

Deep Learning with TensorFlow 2 and Keras – Notebooks This project accompanies my Deep Learning with TensorFlow 2 and Keras trainings. It contains the

Aurélien Geron 1.9k Dec 15, 2022
[ICCV 2021 (oral)] Planar Surface Reconstruction from Sparse Views

Planar Surface Reconstruction From Sparse Views Linyi Jin, Shengyi Qian, Andrew Owens, David F. Fouhey University of Michigan ICCV 2021 (Oral) This re

Linyi Jin 89 Jan 05, 2023
object detection; robust detection; ACM MM21 grand challenge; Security AI Challenger Phase VII

赛题背景 在商品知识产权领域,知识产权体现为在线商品的设计和品牌。不幸的是,在每一天,存在着非法商户通过一些对抗手段干扰商标识别来逃避侵权,这带来了很高的知识产权风险和财务损失。为了促进先进的多媒体人工智能技术的发展,以保护企业来之不易的创作和想法免受恶意使用和剽窃,因此提出了鲁棒性标识检测挑战赛

65 Dec 22, 2022
High-Resolution Image Synthesis with Latent Diffusion Models

Latent Diffusion Models Requirements A suitable conda environment named ldm can be created and activated with: conda env create -f environment.yaml co

CompVis Heidelberg 5.6k Jan 04, 2023