【模型】分享一个200万迭代的 DeepFaceLab模型 F-DF128
================= Model Summary =================== ==
== Model name: df-128_SAEHD ==
== ==
== Current iteration: 2022706 ==
== ==
==--------------- Model Options ---------------==
== ==
== resolution: 128 ==
== face_type: f ==
== models_opt_on_gpu: True ==
== archi: df ==
== ae_dims: 256 ==
== e_dims: 64 ==
== d_dims: 64 ==
== d_mask_dims: 22 ==
== masked_training: True ==
== eyes_prio: False ==
== uniform_yaw: False ==
== lr_dropout: n ==
== 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: False ==
== autobackup_hour: 0 ==
== write_preview_history: False ==
== target_iter: 0 ==
== random_flip: True ==
== batch_size: 16 ==
== ==
==---------------- Running On -----------------==
== ==
== Device index: 0 ==
== Name: Tesla P100-PCIE-16GB ==
== VRAM: 15.90GB ==
== ==
=================================================
分享一个入门模型，早期的老模型，具体参数如上。
df架构的f脸128分辨率模型，适合4G显存的显卡使用，算是入门级模型。
全程BS开16跑200万，Tesla P100 16G显存计算卡训练，需要的请自取。
下载地址：https://pan.baidu.com/s/1NtRrXZU8CZrv3hwfH73uRg?pwd=6666
页:
[1]