nmakes / ethnicity-detection-v1

Comparing the effectiveness of Deep Convolutional Neural Networks for detecting ethnicity of a person in face images

Ethnicity Detection Using Convolutional Neural Networks

We train 4 CNN architectures for 30 epochs and comapre the classification scores. The data used is taken from UTKFace dataset. Each network achieves 75%+ peak accuracy in classification.

Cite

Venkat, N., Srivastava, S. (2018). Ethnicity Detection using Deep Convolutional Neural Networks. DOI: 10.13140/RG.2.2.34591.20642

Download the report here.

STEP 1: Getting the models and train-test split

You can download models and train-test split here

STEP 2: Installing Requirements

python3 -m pip install -r requirements.txt

STEP 3: Running

Executing the code for training and testing

python3 main.py

Executing the code to view results on the trained models

python3 accuracies.py