Our algorithm supports editing hairstyles and hair color individually or jointly, and conditional input can come either from the graphic or from the text domain.

Pre -trained model

Download the previously trained model at the following link. The HairClip model contains the entire architecture, including the weights of the converter and decoder.

The main learning script can be found in Scripts/Train.py.

Intermediate learning outcomes are preserved in Opts.exp_dir. This includes control points, outputs and outputs of tests.

In addition, if you have Tensorboard, you can visualize Tensorboard magazines at OPTS.exp_Dir/Logs.

Web Demo:

#machinelearning #artificialintelligence #ai #datascience #programming #Deechnology #Deeuplearning #bigData #bigdata