Multi-tag task
jackskr666 opened this issue · comments
tags:
name: Bangs
tag_irrelevant_conditions_dim: 2
attributes:
-
name: 'with'
filename: datasets/Bangs_with.txt
-
name: 'without'
filename: datasets/Bangs_without.txt
-
name: Eyeglasses
tag_irrelevant_conditions_dim: 2
attributes:name: 'with' filename: datasets/Eyeglasses_with.txt
- name: 'without'
filename: datasets/Eyeglasses_without.txt
- name: 'without'
if I want to make experiment on Multi-tag task, how to replace Multi-tag task on celeba-hq.yaml setting?
Hi, here are the steps:
- please refer to (https://github.com/imlixinyang/HiSD/blob/main/preprocessors/celeba-hq.py) and modify it for your desired tags and attributes. You will get some datasets/Tag_attribute.txt files if succeed.
- modify the config file to use the your own datasets/Tag_attribute.txt files.
- train.
if I changing the style of hair while changing the style of glasses, so my custom.yaml modify follow the settings?
tags:
name: Eyeglasses_black
tag_irrelevant_conditions_dim: 2
attributes:
-
name: 'with'
filename: datasets/Eyeglasses_with.txt
-
name: 'without'
filename: datasets/Eyeglasses_without.txt
-
name: 'black'
filename: datasets/HairColor_black.txt
This config file is only for training. If you want to edit multiple tags in inference, you should edit code in here.
Thank you very much, I find facial age transformation in supplementary. How to generate age 7-9’/‘10-14’/‘15-19’/‘20-29’/‘30-39’/‘40-49’/‘50-69 in test.py?
Hi @jackskr666, sorry for the late reply.
For age transformation, we use the images from FFHQ dataset and the labels provided by FFHQ-aging. You may process them into the label structure of HiSD to reproduce this experiment.