Training StackGAN++ to Generate Images with Better Quality
Follow the step-by-step process of training StackGAN++ for good-quality image generation.
We'll cover the following
The authors of StackGAN++ have open sourced the
Steps to train StackGAN++
Follow these steps to train StackGAN++ on the CUB-200-2011 dataset. Follow the following steps:
Install the required libraries.
Download the
.source code of StackGAN++ https://github.com/hanzhanggit/StackGAN-v2
⚠️ The dataset is intended only for non-commercial research and educational use.
Download the
and put theCUB-200-2011 dataset https://www.vision.caltech.edu/datasets/cub_200_2011/ CUB_200_2011
folder in thedata/birds directory
, so that the images are located at paths such asdata/birds/CUB_200_2011/images/001.Black_footed_Albatross/Black_Footed_Albatross_0001_796111.jpg
. The compressed file that needs to be downloaded is about 1.1 GB in size.Download the
and move it topre-trained text embeddings https://drive.google.com/file/d/0B0ywwgffWnLLSW84ZXRjdXhObzQ/view?resourcekey=0-1NIY4Hno0B-vhYVrUHGfLQ data/birds
. Make sure to rename thetext_c10
folder totext
.
Get hands-on with 1200+ tech skills courses.