LIAE-UD_384_wf_304万迭代次数_高参预训练模型
最近在论坛上寻找了很久,想找一个适合的预处理模型,但却没有找到满足需求的。只能自己动手,开始了预训练之旅!
这是真正的预训练,正式训练后步数会清零的那种。
预训练模型的好处就是你可以快速训练 src,快速训练自己的直播丹
================== Model Summary ===================
== ==
== Model name: 384wf_SAEHD ==
== ==
== Current iteration: 3004097 ==
== ==
==---------------- Model Options -----------------==
== ==
== resolution: 384 ==
== face_type: wf ==
== models_opt_on_gpu: True ==
== archi: liae-ud ==
== ae_dims: 352 ==
== e_dims: 102 ==
== d_dims: 102 ==
== d_mask_dims: 32 ==
== masked_training: True ==
== eyes_mouth_prio: False ==
== uniform_yaw: True ==
== adabelief: True ==
== lr_dropout: n ==
== random_warp: False ==
== true_face_power: 0.0 ==
== face_style_power: 0.0 ==
== bg_style_power: 0.0 ==
== ct_mode: none ==
== clipgrad: True ==
== pretrain: True ==
== autobackup_hour: 1 ==
== write_preview_history: False ==
== target_iter: 0 ==
== random_src_flip: False ==
== random_dst_flip: False ==
== batch_size: 8 ==
== gan_power: 0.0 ==
== gan_patch_size: 80 ==
== gan_dims: 16 ==
== blur_out_mask: False ==
== random_hsv_power: 0.0 ==
== ==
==------------------ Running On ------------------==
== ==
== Device index: 0 ==
== Name: NVIDIA GeForce RTX 4090 ==
== VRAM: 20.85GB ==
== ==
***本内容需购买可见***
谢谢楼主分享 谢谢分享 直播模型应该不错 感谢分享模型,阿姨嘎多 谢谢分享 55555555555555555 谢谢分享 谢谢楼主分享 谢谢楼主分享 111111111111
页:
[1]
2