df256_wf自闭2.0万能神丹迭代次数清零
迭代次数已经清零,但是不影响底丹效果,自闭2.0底丹,万能模型,刚学的时候花300买的,在此基础上训练快速训练成型================= Model Summary =================
== ==
== Model name: ZIBI2.0_SAEHD ==
== ==
== Current iteration: 0 ==
== ==
==--------------- Model Options ---------------==
== ==
== resolution: 256 ==
== face_type: wf ==
== models_opt_on_gpu: True ==
== archi: df-ud ==
== ae_dims: 320 ==
== e_dims: 88 ==
== d_dims: 66 ==
== d_mask_dims: 22 ==
== masked_training: True ==
== eyes_mouth_prio: False ==
== uniform_yaw: False ==
== 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: False ==
== autobackup_hour: 2 ==
== write_preview_history: False ==
== target_iter: 0 ==
== random_src_flip: False ==
== random_dst_flip: False ==
== batch_size: 16 ==
== gan_power: 0.0 ==
== gan_patch_size: 32 ==
== gan_dims: 16 ==
== use_fp16: False ==
== ==
==---------------- Running On -----------------==
== ==
== Device index: 0 ==
== Name: Tesla V100-SXM2-16GB ==
== VRAM: 14.41GB ==
== ==
***本内容需购买可见***
自闭的丹 应该不错,感谢分享 谢谢楼主分享 好东西,等我攒攒灵石再买 感谢分享 谢谢楼主分享 感谢分享 没钱的穷鬼路过 谢谢楼主分享 谢谢分享
页:
[1]
2