Glasses Detector#

About#

Package for processing images with different types of glasses and their parts. It provides a quick way to use the pre-trained models for 3 kinds of tasks, each being divided to multiple categories, for instance, classification of sunglasses or segmentation of glasses frames (see Features for more details):

Classification

๐Ÿ‘“ transparent ๐Ÿ•ถ๏ธ opaque ๐Ÿฅฝ any โžฟ shadows

Detection

๐Ÿค“ worn ๐Ÿ‘“ standalone ๐Ÿ‘€ eye-area

Segmentation

๐Ÿ˜Ž full ๐Ÿ–ผ๏ธ frames ๐Ÿฆฟ legs ๐Ÿ” lenses ๐Ÿ‘ฅ shadows


The processing can be launched via the command line or written in a Python script. Based on the selected task, an image or a directory of images will be processed and corresponding predictions, e.g., labels or masks, will be generated.

See also

Refer to GitHub repository for information about the datasets used and how to train or test your own models. Model fitting and evaluation can be simply launched through terminal with commands integrated from PyTorch Lightning CLI.

Contents#

Indices and Tables#