|
|
楼主 |
发表于 2022-10-3 15:40:19
|
显示全部楼层
本帖最后由 q350555108 于 2022-10-3 15:51 编辑
喜讯，做了以下修改，跑起来了！！！！
Running trainer.
Choose one of saved models, or enter a name to create a new model.
[r] : rename
[d] : delete
[0] : new - latest
:
0
Loading new_SAEHD model...
Choose one or several GPU idxs (separated by comma).
[CPU] : CPU
[0] : NVIDIA GeForce RTX 3070 Laptop GPU
[0] Which GPU indexes to choose? :
0
Press enter in 2 seconds to override model settings.
[0] Autobackup every N hour ( 0..24 ?:help ) :
0
[n] Write preview history ( y/n ?:help ) :
n
[0] Target iteration :
0
[n] Flip SRC faces randomly ( y/n ?:help ) :
n
[y] Flip DST faces randomly ( y/n ?:help ) :
y
[4] Batch_size ( ?:help ) : 8
8
[y] Masked training ( y/n ?:help ) :
y
[n] Eyes and mouth priority ( y/n ?:help ) :
n
[y] Uniform yaw distribution of samples ( y/n ?:help ) :
y
[y] Blur out mask ( y/n ?:help ) :
y
[y] Place models and optimizer on GPU ( y/n ?:help ) :
y
[n] Use AdaBelief optimizer? ( y/n ?:help ) :
n
[n] Use learning rate dropout ( n/y/cpu ?:help ) :
n
[n] Enable random warp of samples ( y/n ?:help ) :
n
[0.1] Random hue/saturation/light intensity ( 0.0 .. 0.3 ?:help ) :
0.1
[0.0] GAN power ( 0.0 .. 5.0 ?:help ) :
0.0
[0.0] Face style power ( 0.0..100.0 ?:help ) :
0.0
[0.0] Background style power ( 0.0..100.0 ?:help ) :
0.0
[none] Color transfer for src faceset ( none/rct/lct/mkl/idt/sot ?:help ) :
none
[n] Enable gradient clipping ( y/n ?:help ) :
n
[n] Enable pretraining mode ( y/n ?:help ) :
n
Initializing models: 100%|###############################################################| 5/5 [00:02<00:00, 2.21it/s]
Loaded 12022 packed faces from D:\deep\DeepFaceLab_NVIDIA_RTX3000_series\workspace\data_src\aligned
Sort by yaw: 100%|##################################################################| 128/128 [00:00<00:00, 583.76it/s]
Loading samples: 100%|############################################################| 1689/1689 [00:03<00:00, 497.32it/s]
Sort by yaw: 100%|#################################################################| 128/128 [00:00<00:00, 4138.85it/s]
======================== Model Summary ========================
== ==
== Model name: new_SAEHD ==
== ==
== Current iteration: 4717152 ==
== ==
==---------------------- Model Options ----------------------==
== ==
== resolution: 224 ==
== face_type: wf ==
== models_opt_on_gpu: True ==
== archi: liae-udt ==
== ae_dims: 512 ==
== e_dims: 64 ==
== d_dims: 64 ==
== d_mask_dims: 32 ==
== masked_training: True ==
== eyes_mouth_prio: False ==
== uniform_yaw: True ==
== blur_out_mask: True ==
== adabelief: False ==
== lr_dropout: n ==
== random_warp: False ==
== random_hsv_power: 0.1 ==
== 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_src_flip: False ==
== random_dst_flip: True ==
== batch_size: 8 ==
== gan_power: 0.0 ==
== gan_patch_size: 28 ==
== gan_dims: 32 ==
== ==
==----------------------- Running On ------------------------==
== ==
== Device index: 0 ==
== Name: NVIDIA GeForce RTX 3070 Laptop GPU ==
== VRAM: 5.35GB ==
== ==
===============================================================
Starting. Press "Enter" to stop training and save model.
[15:51:01][#4717220][0459ms][0.1188][0.0954]
|
|
|Archiver|手机版|deepfacelab中文网
|网站地图
发表于 2022-10-3 15:22:18
很考验片源的相似度。df感觉就是直接糊了个面具上去，而这个就像是两个人生下来的孩子。练下去会慢慢有改善的，不过你可以先看看原丹的效果，大概极限就是那样了。（还有一开始可以src互练效果快点）