Year: 2019
Type: preprint
Abstract: This Zenodo upload contains the original pre-trained models to reproduce the results of Deep Automodulators. For downloading these models automatically, as well as possible updates to the models, see Github: https://github.com/AaltoVision/automodulator Datasets and image resolution associated with the models: FFHQ 512x512: 42420000_state.pth FFHQ 256x256: 34740000_state.pth CelebAHQ 256x256: 31877148_state.pth LSUN Bedrooms 256x256: 27574284_state.pth LSUN Cars 256x256: 32057140_state.pth
Source: arXiv (Cornell University)
Institution: Aalto University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funders: Nvidia, China Scholarship Council
OpenAlex ID: W2996026030