NOTE: This model requires cropped face images to work properly.
Purpose
This model classifies a face into an age group (e.g., 0-2, 10-19 etc).
Architecture
This is a ResNet34 v1 with crop_type='random1', crop_size=[224, 224, 3] and downsample_size=[224, 2 * 224 + 1]. We also used Adam for the optimizer, with LR=0.0001 and decrease LR by 0.1 for every 30 epochs.
Intended Use
General purpose age classifier given a close-cropped face image.
Limitations
The model might not work very well on small (e.g., less than 50x50) or blurry images.
ID
Model Type ID
Visual Classifier
Input Type
image
Output Type
concepts
Description
Demographics model to use in conjunction with face recognition for predicting people's age from faces in images and video.