Scribd
Upload
124 views

New SAEHD Summary

The model summary describes a model named new_SAEHD that is currently at iteration 1000000. It has a resolution of 288 pixels, uses a wf face type, and is optimized to run on GPUs. It uses an autoencoder architecture with 384 dimensions for the encoder and decoder.

Uploaded by

Daniel Sousa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
124 views

New SAEHD Summary

The model summary describes a model named new_SAEHD that is currently at iteration 1000000. It has a resolution of 288 pixels, uses a wf face type, and is optimized to run on GPUs. It uses an autoencoder architecture with 384 dimensions for the encoder and decoder.

Uploaded by

Daniel Sousa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 1

================= Model Summary =================

== ==
== Model name: new_SAEHD ==
== ==
== Current iteration: 1000000 ==
== ==
==--------------- Model Options ---------------==
== ==
== resolution: 288 ==
== face_type: wf ==
== models_opt_on_gpu: True ==
== archi: df ==
== ae_dims: 384 ==
== e_dims: 92 ==
== d_dims: 72 ==
== d_mask_dims: 22 ==
== masked_training: True ==
== eyes_prio: False ==
== lr_dropout: False ==
== random_warp: True ==
== gan_power: 0.0 ==
== true_face_power: 0.0 ==
== face_style_power: 0.0 ==
== bg_style_power: 0.0 ==
== ct_mode: none ==
== clipgrad: False ==
== pretrain: True ==
== autobackup_hour: 0 ==
== write_preview_history: False ==
== target_iter: 1000000 ==
== random_flip: True ==
== batch_size: 4 ==
== ==
==---------------- Running On -----------------==
== ==
== Device index: 0 ==
== Name: Tesla P100-PCIE-16GB ==
== VRAM: 15.90GB ==
== ==
=================================================

You might also like