模型里那个data.dat数据里面存储的啥东东，能打开看么？

DFL8938o9

开头是这些
€}q (X   iterq
J莐 X   optionsq}q(X
   resolutionqcnumpy.core.multiarray
scalar
qcnumpy
dtype
qX   i4qK K
噏Rq        (KX
   <q
NNNJJK tqbC
  q唓
RqX           face_typeqX
   fqX   models_opt_on_gpuq圶   archiqX   df-udqX   ae_dimsqhh        C
  q唓RqX   e_dimsqhh        C\   q唓RqX   d_dimsqhh        CH   q唓RqX   d_mask_dimsq hh        C   q!唓"Rq#X   masked_trainingq$圶           eyes_prioq%圶   uniform_yawq&塜
   lr_dropoutq'X
   nq(X   random_warpq)圶           gan_powerq*hhX   f8q+K K
噏,Rq-(Kh
NNNJJK tq.bC        q/唓0Rq1X   true_face_powerq2hh-C        q3唓4Rq5X   face_style_powerq6hh-C        q7唓8Rq9X   bg_style_powerq:hh-C        q;唓<Rq=X   ct_modeq>X   rctq?X   clipgradq@塜   pretrainqA塜   autobackup_hourqBK X   write_preview_historyqC塜   target_iterqDK X   random_flipqE圶
   batch_sizeqFKuX   loss_historyqG]qH(]qI(G@彝?  G@'宍   e]qJ(G@q     G@`?   e]qK(G@
k@   G@??  e]qL(G@)@   G@
€]€   e]qM(G@鼸€   G@%?   e]qN(G@        怷    G@
甙€   e]qO(G@
_@   G@??  e]qP(G@
"    G@
??  e]qQ(G@?    G@        b>?  e]qR(G@遺?  G@5傽   e]qS(G@貢@   G@
虡@   e]qT(G@
@   G@噜?  e]qU(G@?    G@?`   e]qV(G@|艪   G@            e]qW(G@g*€   G@駫€   e]qX(G@嚠?  G@裉€   e]qY(G@仄?  G@]墍   e]qZ(G@險`   G@o7?  e]q[(G@蘗?  G@D€   e]q\(G@T?   G@= ?  e]q](G@l?  G@?@   e]q^(G@rо   G@櫥€   e]q_(G@駺?  G@?    e]q`(G@D?   G@ ?   e]qa(G@_E€   G@
a    e]qb(G@9u    G@蕃?  e]qc(G@?@   G@C鶢   e]qd(G?懿?  G@zC?  e]qe(G@@z    G@.!@   e]qf(G@◤?  G@d觻   e]qg(G@鄝   G@k   e]qh(G@翏€   G@        ??  e]qi(G@_潬   G@f膧   e]qj(G@L|€   G@0篅   e]qk(G@P?   G@     e]ql(G@
€   G@岪   e]qm(G@熇   G@
询?  e]qn(G?H   G@
?   e]qo(G@ ?@   G@??  e]qp(G@多   G@
€   e]qq(G@委`   G@ ?  e]qr(G@葂@   G@
?  e]qs(G@>   G@`    e]qt(G@ 鷵€   G@    e]qu(G@桦?  G@.?   e]qv(G@@;?  G@??  e]qw(G@t?  G@F?  e]qx(G@??  G@橜`   e]qy(G@
?@   G@多   e]qz(G@@   G@掛€   e]q{(G@s蠤   G@.枥   e]q|(G@匍    G?5@   e]q}(G@
踻?  G@
~    e]q~(G@?@   G@N    e]q(G@ 蒿?  G@ ??  e]q€(G@|    G@
3弨   e]q?G@\s?  G@"@   e]q?G?}    G@
葊   e]q?G@ K    G@ 霥?  e]q?G@
f?   G?龁    e]q?G@ ?@   G@ 騼?  e]q?G@
J怖   G@ O\    e]q?G@
釶?  G@
媍    e]q?G@h€   G@皸?  e]q?G@M墍   G@ フ    e]q?G?/5@   G??   e]q?G@
⒚@   G?p?  e]q?G@ ?@   G@

   e]q?G@
愰€   G?攢   e]q?G@ *?   G@
'焵   e]q?G??  G??D    e]q?G@ -哷   G?h?   e]q?G@Wy?  G@
洁   e]q?G@'R?  G@ ??  e]q?G@
6H@   G@ 泴@   e]q?G@
   G?}?  e]q?G@ &〡   G@y?  e]q?G@爏?  G?"€   e]q?G@=鬇   G@
z藸   e]q?G@        O?  G@犜`   e]q?G@ 罖   G@??  e]q?G@ 窖@   G??   e]q?G@
E?   G@?   e]q?G@
s^@   G?e€   e]q?G?lu    G@ B迉   e]q?G@>?   G@ (€   e]q?G@
?€   G@ ?    e]q?G@
卑@   G?i€   e]q?G@
r;?  G@?    e]q?G@ 俐@   G@
睝   e]q?G@ €v    G@Z    e]q?G@ C鳣   G@?    e]q?G@ Hh@   G?齶6@   e]q?G@
鵟@   G@
T芵   e]q?G?z?  G?N@   e]q?G@絫    G@燉    e]q?G@ =€   G?9?  e]q?G?齽扏   G@ =3    e]q?G?6`   G@ 5捓   e]q?G?/   G@ 6=    e]q?G@
?   G?騹   e]q?G??   G@
~e?  e]q?G@^    G@ ?€   e]q?G@ 違   G??   e]q?G@ 謤   G?龖鮜   e]q?G??徖   G@ U    e]q?G??%?  G?g@   e]q?G?龔€€   G??   e]q?G@ >臓   G??矤   e]q?G@
Z?   G@ B劆   e]q?G?皌    G?齰e€   e]q?G@J絸   G@牂@   e]q?G?I?  G@ -    e]q?G@ 捓   G??  e]q?G?饜    G@ も€   e]q?G?   G@ u衻   e]q?G@p<?  G@
.卫   e]q?G?緓?  G@ v?   e]q?G?嵗   G@ 鹾@   e]q?G?黲N?  G?鶮鹄   e]q?G?鵭阘   G?x@   e]q?G?鹯?   G@ St    e]q?G?鶵f@   G?#@   e]q?G?韚@   G@ 鑖?  e]q?G??        ?  G??纮   e]q?G??0`   G??   e]q?G?_`   G@瓘€   e]q?G@
7d`   G@?    e]q?G@ ,?  G?I   e]q?G@ 熰   G@ K`   e]q?G??€   G@         D`   e]q?G??z€   G?Q?   e]q?G?鞝   G?n€   e]q?G???   G??珋   e]q?G?瘝    G?茾   e]q?G?駺   G??€   e]q?G?Ι    G@ 樄@   e]q?G?€   G??   e]q?G?龎覢   G@
E世   e]q?G?鵺鯜   G?鶣锑   e]q?G?)   G@ ??  e]q?G?I    G?y    e]q?G?斂    G@?    e]q?G@e崂   G@Q€   e]q?G@ 蕱?  G?朼€   e]q?G?h€   G??還   e]q?G@ *脿   G??ㄠ   e]q?G?鹴尷   G?C?  e]q?G?龘礰   G?﨔t?  e]q?G?鎬   G???   e]q?G?鯼   G@ ?  e]q?G@ 扻?  G@ 俞    e]q?G@ ?    G?f,?  e]q?G?屶`   G?齞k    e]q?G??   G?y@   e]q?G?蕗   G??  e]q?G???   G?齋7@   e]q?G@ k    G?R鮻   e]q?G??f?  G??
?  e]q?G@山@   G@
偞`   e]q?G?   G?q@   e]q?G?j€   G@,?  e]q?G?綀    G??€€   e]q?G@
@   G?鷓U@   e]q?G??        @   G??縛   e]q?G??2    G??`   e]q?G?鼖蕗   G??蹳   e]q?G??    G? w€   e]q?G?M-@   G?箑   e]q?G?齦8    G??鶣   e]q?G?@   G@ 矒`   e]q?G@ 态€   G?鼼犂   e]q?G@
??  G?黦?   e]q?G?衫   G?鵇_?  e]q?G?鴑    G?p?  e]q?G@琠`   G@
E簚   e]q?G?/@   G@ r亦   e]q?G??€   G?k蜙   e]q?G?鰺雬   G?鼕     e]q?G?麵|?  G??€?  e]q?G?齋;    G?覢   e]q?G@ [:    G?p?   e]q(G?   G??   e]r
  (G?鷗 @   G??r    e]r

  (G?(    G??胬   e]r
  (G??X?  G?3@   e]r
  (G??b    G@ }'    e]r
  (G?:胬   G?橜   e]r
  (G?齾?   G?L@   e]r
  (G@ ?   G@ σ?  e]r
  (G@ 鼲   G@ 姱    e]r
  (G@
f   G@
⒈€   e]r       
  (G?鶁?  G?鶥瓳   e]r

  (G?黕2`   G?鸅?   e]r
  (G?匑   G?潃   e]r
  (G?鷟?  G?鴪r    e]r

  (G?Z?  G?鼦评   e]r
  (G??S?  G?黈f@   e]r
  (G?玎   G@ 担?  e]r
  (G?x€   G?麑?  e]r
  (G?撪   G??   e]r
  (G??粪   G?鷾?   e]r
  (G?鷃   G?鼀f€   e]r
  (G?_    G?顮   e]r
  (G?鼪d    G?麺渶   e]r
  (G?Q?  G?U    e]r
  (G?麌?  G?軤   e]r
  (G?j@   G@
q?   e]r
  (G?鶸胬   G?鷰?   e]r
  (G?骺簚   G?亦   e]r
  (G?[だ   G??P    e]r
  (G?鷸鍊   G???   e]r
  (G?隣:?  G?嵿   e]r
  (G?鼢e    G?鶢H@   e]r
  (G?鷵駺   G?鴲锑   e]r
  (G?鸜?  G?黌}?  e]r!
  (G???   G??蚡   e]r"
  (G?蟺   G?龑o€   e]r#
  (G?鰙}`   G?鼃.?  e]r$
  (G?鵰=@   G??e`   e]r%
  (G??a    G?麛?   e]r&
  (G?灎   G??虪   e]r'
  (G?k    G?]    e]r(
  (G?鼘?   G?ｓ    e]r)
  (G?    G??    e]r*
  (G?   G?芵   e]r+
  (G?鵅?   G??p@   e]r,
  (G??O@   G??   e]r-
  (G?凄   G?9@   e]r.
  (G??捓   G?鸑(?  e]r/
  (G?a?  G?鶏t?  e]r0
  (G?鹓誁   G?蹶S@   e]r1
  (G??死   G??  e]r2
  (G?鶙猔   G??\?  e]r3
  (G?`   G?-    e]r4
  (G??瀫   G?烜   e]r5
  (G??N?  G??`?  e]r6
  (G??粿   G???   e]r7
  (G?鼇芵   G?黁?   e]r8
  (G@
`懤   G@ 鮪?  e]r9
  (G?k    G?t    e]r:
  (G?麺謤   G??]?  e]r;
  (G?宍   G?   e]r<
  (G??   G??D€   e]r=
  (G?龔v?  G?     e]r>
  (G?麌闌   G?鼃?  e]r?
  (G?顎   G?奰   e]r@
  (G?個   G??   e]rA
  (G?粻   G??   e]rB
  (G?鐎   G?鮯尷   e]rC
  (G?鼮]@   G@
^€   e]rD
  (G?鸻m    G@ 0n    e]rE
  (G???   G??-?  e]rF
  (G?鸖?   G??暲   e]rG
  (G?範   G?<    e]rH
  (G@ Q/?  G?擲?  e]rI
  (G?    G?F    e]rJ
  (G?   G?鸂鵣   e]rK
  (G?褉   G??崂   e]rL
  (G??謇   G?碄   e]rM
  (G??T    G?鞅鵃   e]rN
  (G??c    G??]€   e]rO
  (G?瀈   G???   e]rP
  (G?鵒?   G?鰿?   e]rQ
  (G?€椑   G?鼫籂   e]rR
  (G?鑰   G?皐€   e]rS
  (G?j?  G?枢   e]rT
  (G??錪   G?鵔嬂   e]rU
  (G??欯   G?

DFL8938o9

后面还有很多内容 都是乱码

DFL8938o9

你应该是想研究研究想着直接把变形给新的模型使用吧

yangala

要在python里打开才看得到，正巧我早几天也好奇的看了看里面都有啥
# f = Path(r'D:\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\workspace\model\mm512_SAEHD_data.dat')
# resolution 512
# face_type wf
# models_opt_on_gpu True
# archi df-ud
# ae_dims 256
# e_dims 64
# d_dims 64
# d_mask_dims 22
# masked_training True
# uniform_yaw False
# adabelief True
# lr_dropout n
# random_warp False
# 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 1
# write_preview_history False
# target_iter 1000000
# random_flip False
# batch_size 1
# eyes_mouth_prio True
# gan_patch_size 64
# gan_dims 16
# random_src_flip False
# random_dst_flip False


# 编码器
f = Path(r'D:\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\workspace\model\mm512_SAEHD_encoder.npy')
# down1/downs_0/conv1/weight:0  shape =  (5, 5, 3, 64)
# down1/downs_0/conv1/bias:0  shape =  (64,)
# down1/downs_1/conv1/weight:0  shape =  (5, 5, 64, 128)
# down1/downs_1/conv1/bias:0  shape =  (128,)
# down1/downs_2/conv1/weight:0  shape =  (5, 5, 128, 256)
# down1/downs_2/conv1/bias:0  shape =  (256,)
# down1/downs_3/conv1/weight:0  shape =  (5, 5, 256, 512)
# down1/downs_3/conv1/bias:0  shape =  (512,)


# 中间层
f = Path(r'D:\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\workspace\model\mm512_SAEHD_inter.npy')
# dense1/weight:0  shape =  (524288, 256)   512*512*2 = 524288
# dense1/bias:0  shape =  (256,)
# dense2/weight:0  shape =  (256, 65536)    256*256 = 65536
# dense2/bias:0  shape =  (65536,)
# upscale1/conv1/weight:0  shape =  (3, 3, 256, 1024)
# upscale1/conv1/bias:0  shape =  (1024,)


# 解码器
# f = Path(r'D:\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\workspace\model\mm512_SAEHD_decoder_dst.npy')
# 18层
# upscale0/conv1/weight:0  shape =  (3, 3, 256, 2048)
# upscale0/conv1/bias:0  shape =  (2048,)
# upscale1/conv1/weight:0  shape =  (3, 3, 512, 1024)
# upscale1/conv1/bias:0  shape =  (1024,)
# upscale2/conv1/weight:0  shape =  (3, 3, 256, 512)
# upscale2/conv1/bias:0  shape =  (512,)

# res0/conv1/weight:0  shape =  (3, 3, 512, 512)
# res0/conv1/bias:0  shape =  (512,)
# res0/conv2/weight:0  shape =  (3, 3, 512, 512)
# res0/conv2/bias:0  shape =  (512,)
# res1/conv1/weight:0  shape =  (3, 3, 256, 256)
# res1/conv1/bias:0  shape =  (256,)
# res1/conv2/weight:0  shape =  (3, 3, 256, 256)
# res1/conv2/bias:0  shape =  (256,)
# res2/conv1/weight:0  shape =  (3, 3, 128, 128)
# res2/conv1/bias:0  shape =  (128,)
# res2/conv2/weight:0  shape =  (3, 3, 128, 128)
# res2/conv2/bias:0  shape =  (128,)

# out_conv/weight:0  shape =  (1, 1, 128, 3)
# out_conv/bias:0  shape =  (3,)

# upscalem0/conv1/weight:0  shape =  (3, 3, 256, 704)
# upscalem0/conv1/bias:0  shape =  (704,)
# upscalem1/conv1/weight:0  shape =  (3, 3, 176, 352)
# upscalem1/conv1/bias:0  shape =  (352,)
# upscalem2/conv1/weight:0  shape =  (3, 3, 88, 176)
# upscalem2/conv1/bias:0  shape =  (176,)

# out_convm/weight:0  shape =  (1, 1, 22, 1)
# out_convm/bias:0  shape =  (1,)
# out_conv1/weight:0  shape =  (3, 3, 128, 3)
# out_conv1/bias:0  shape =  (3,)
# out_conv2/weight:0  shape =  (3, 3, 128, 3)
# out_conv2/bias:0  shape =  (3,)
# out_conv3/weight:0  shape =  (3, 3, 128, 3)
# out_conv3/bias:0  shape =  (3,)

# upscalem3/conv1/weight:0  shape =  (3, 3, 44, 88)
# upscalem3/conv1/bias:0  shape =  (88,)





# 优化器的参数
f = Path(r'D:\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series\workspace\model\mm512_SAEHD_src_dst_opt.npy')
# iters:0
#
# ms_encoder/down1/downs_0/conv1/weight_0:0  shape =  (5, 5, 3, 64)
# ms_encoder/down1/downs_0/conv1/bias_0:0  shape =  (64,)
# ms_encoder/down1/downs_1/conv1/weight_0:0  shape =  (5, 5, 64, 128)
# ms_encoder/down1/downs_1/conv1/bias_0:0  shape =  (128,)
# ms_encoder/down1/downs_2/conv1/weight_0:0  shape =  (5, 5, 128, 256)
# ms_encoder/down1/downs_2/conv1/bias_0:0  shape =  (256,)
# ms_encoder/down1/downs_3/conv1/weight_0:0  shape =  (5, 5, 256, 512)
# ms_encoder/down1/downs_3/conv1/bias_0:0  shape =  (512,)

# ms_inter/dense1/weight_0:0  shape =  (524288, 256)
# ms_inter/dense1/bias_0:0  shape =  (256,)
# ms_inter/dense2/weight_0:0  shape =  (256, 65536)
# ms_inter/dense2/bias_0:0  shape =  (65536,)
# ms_inter/upscale1/conv1/weight_0:0  shape =  (3, 3, 256, 1024)
# ms_inter/upscale1/conv1/bias_0:0  shape =  (1024,)

# ms_decoder_src/upscale0/conv1/weight_0:0  shape =  (3, 3, 256, 2048)
# ms_decoder_src/upscale0/conv1/bias_0:0  shape =  (2048,)
# ms_decoder_src/upscale1/conv1/weight_0:0  shape =  (3, 3, 512, 1024)
# ms_decoder_src/upscale1/conv1/bias_0:0  shape =  (1024,)
# ms_decoder_src/upscale2/conv1/weight_0:0  shape =  (3, 3, 256, 512)
# ms_decoder_src/upscale2/conv1/bias_0:0  shape =  (512,)
# ms_decoder_src/res0/conv1/weight_0:0  shape =  (3, 3, 512, 512)
# ms_decoder_src/res0/conv1/bias_0:0  shape =  (512,)
# ms_decoder_src/res0/conv2/weight_0:0  shape =  (3, 3, 512, 512)
# ms_decoder_src/res0/conv2/bias_0:0  shape =  (512,)
# ms_decoder_src/res1/conv1/weight_0:0  shape =  (3, 3, 256, 256)
# ms_decoder_src/res1/conv1/bias_0:0  shape =  (256,)
# ms_decoder_src/res1/conv2/weight_0:0  shape =  (3, 3, 256, 256)
# ms_decoder_src/res1/conv2/bias_0:0  shape =  (256,)
# ms_decoder_src/res2/conv1/weight_0:0  shape =  (3, 3, 128, 128)
# ms_decoder_src/res2/conv1/bias_0:0  shape =  (128,)
# ms_decoder_src/res2/conv2/weight_0:0  shape =  (3, 3, 128, 128)
# ms_decoder_src/res2/conv2/bias_0:0  shape =  (128,)
# ms_decoder_src/out_conv/weight_0:0  shape =  (1, 1, 128, 3)
# ms_decoder_src/out_conv/bias_0:0  shape =  (3,)
# ms_decoder_src/upscalem0/conv1/weight_0:0  shape =  (3, 3, 256, 704)
# ms_decoder_src/upscalem0/conv1/bias_0:0  shape =  (704,)
# ms_decoder_src/upscalem1/conv1/weight_0:0  shape =  (3, 3, 176, 352)
# ms_decoder_src/upscalem1/conv1/bias_0:0  shape =  (352,)
# ms_decoder_src/upscalem2/conv1/weight_0:0  shape =  (3, 3, 88, 176)
# ms_decoder_src/upscalem2/conv1/bias_0:0  shape =  (176,)
# ms_decoder_src/out_convm/weight_0:0  shape =  (1, 1, 22, 1)
# ms_decoder_src/out_convm/bias_0:0  shape =  (1,)
# ms_decoder_src/out_conv1/weight_0:0  shape =  (3, 3, 128, 3)
# ms_decoder_src/out_conv1/bias_0:0  shape =  (3,)
# ms_decoder_src/out_conv2/weight_0:0  shape =  (3, 3, 128, 3)
# ms_decoder_src/out_conv2/bias_0:0  shape =  (3,)
# ms_decoder_src/out_conv3/weight_0:0  shape =  (3, 3, 128, 3)
# ms_decoder_src/out_conv3/bias_0:0  shape =  (3,)
# ms_decoder_src/upscalem3/conv1/weight_0:0  shape =  (3, 3, 44, 88)
# ms_decoder_src/upscalem3/conv1/bias_0:0  shape =  (88,)
# ms_decoder_dst/upscale0/conv1/weight_0:0  shape =  (3, 3, 256, 2048)
# ms_decoder_dst/upscale0/conv1/bias_0:0  shape =  (2048,)
# ms_decoder_dst/upscale1/conv1/weight_0:0  shape =  (3, 3, 512, 1024)
# ms_decoder_dst/upscale1/conv1/bias_0:0  shape =  (1024,)
# ms_decoder_dst/upscale2/conv1/weight_0:0  shape =  (3, 3, 256, 512)
# ms_decoder_dst/upscale2/conv1/bias_0:0  shape =  (512,)
# ms_decoder_dst/res0/conv1/weight_0:0  shape =  (3, 3, 512, 512)
# ms_decoder_dst/res0/conv1/bias_0:0  shape =  (512,)
# ms_decoder_dst/res0/conv2/weight_0:0  shape =  (3, 3, 512, 512)
# ms_decoder_dst/res0/conv2/bias_0:0  shape =  (512,)
# ms_decoder_dst/res1/conv1/weight_0:0  shape =  (3, 3, 256, 256)
# ms_decoder_dst/res1/conv1/bias_0:0  shape =  (256,)
# ms_decoder_dst/res1/conv2/weight_0:0  shape =  (3, 3, 256, 256)
# ms_decoder_dst/res1/conv2/bias_0:0  shape =  (256,)
# ms_decoder_dst/res2/conv1/weight_0:0  shape =  (3, 3, 128, 128)
# ms_decoder_dst/res2/conv1/bias_0:0  shape =  (128,)
# ms_decoder_dst/res2/conv2/weight_0:0  shape =  (3, 3, 128, 128)
# ms_decoder_dst/res2/conv2/bias_0:0  shape =  (128,)
# ms_decoder_dst/out_conv/weight_0:0  shape =  (1, 1, 128, 3)
# ms_decoder_dst/out_conv/bias_0:0  shape =  (3,)
# ms_decoder_dst/upscalem0/conv1/weight_0:0  shape =  (3, 3, 256, 704)
# ms_decoder_dst/upscalem0/conv1/bias_0:0  shape =  (704,)
# ms_decoder_dst/upscalem1/conv1/weight_0:0  shape =  (3, 3, 176, 352)
# ms_decoder_dst/upscalem1/conv1/bias_0:0  shape =  (352,)
# ms_decoder_dst/upscalem2/conv1/weight_0:0  shape =  (3, 3, 88, 176)
# ms_decoder_dst/upscalem2/conv1/bias_0:0  shape =  (176,)
# ms_decoder_dst/out_convm/weight_0:0  shape =  (1, 1, 22, 1)
# ms_decoder_dst/out_convm/bias_0:0  shape =  (1,)
# ms_decoder_dst/out_conv1/weight_0:0  shape =  (3, 3, 128, 3)
# ms_decoder_dst/out_conv1/bias_0:0  shape =  (3,)
# ms_decoder_dst/out_conv2/weight_0:0  shape =  (3, 3, 128, 3)
# ms_decoder_dst/out_conv2/bias_0:0  shape =  (3,)
# ms_decoder_dst/out_conv3/weight_0:0  shape =  (3, 3, 128, 3)
# ms_decoder_dst/out_conv3/bias_0:0  shape =  (3,)
# ms_decoder_dst/upscalem3/conv1/weight_0:0  shape =  (3, 3, 44, 88)
# ms_decoder_dst/upscalem3/conv1/bias_0:0  shape =  (88,)

# vs_encoder/down1/downs_0/conv1/weight_0:0  shape =  (5, 5, 3, 64)
# vs_encoder/down1/downs_0/conv1/bias_0:0  shape =  (64,)
# vs_encoder/down1/downs_1/conv1/weight_0:0  shape =  (5, 5, 64, 128)
# vs_encoder/down1/downs_1/conv1/bias_0:0  shape =  (128,)
# vs_encoder/down1/downs_2/conv1/weight_0:0  shape =  (5, 5, 128, 256)
# vs_encoder/down1/downs_2/conv1/bias_0:0  shape =  (256,)
# vs_encoder/down1/downs_3/conv1/weight_0:0  shape =  (5, 5, 256, 512)
# vs_encoder/down1/downs_3/conv1/bias_0:0  shape =  (512,)

# vs_inter/dense1/weight_0:0  shape =  (524288, 256)
# vs_inter/dense1/bias_0:0  shape =  (256,)
# vs_inter/dense2/weight_0:0  shape =  (256, 65536)
# vs_inter/dense2/bias_0:0  shape =  (65536,)
# vs_inter/upscale1/conv1/weight_0:0  shape =  (3, 3, 256, 1024)
# vs_inter/upscale1/conv1/bias_0:0  shape =  (1024,)

# vs_decoder_src/upscale0/conv1/weight_0:0  shape =  (3, 3, 256, 2048)
# vs_decoder_src/upscale0/conv1/bias_0:0  shape =  (2048,)
# vs_decoder_src/upscale1/conv1/weight_0:0  shape =  (3, 3, 512, 1024)
# vs_decoder_src/upscale1/conv1/bias_0:0  shape =  (1024,)
# vs_decoder_src/upscale2/conv1/weight_0:0  shape =  (3, 3, 256, 512)
# vs_decoder_src/upscale2/conv1/bias_0:0  shape =  (512,)
# vs_decoder_src/res0/conv1/weight_0:0  shape =  (3, 3, 512, 512)
# vs_decoder_src/res0/conv1/bias_0:0  shape =  (512,)
# vs_decoder_src/res0/conv2/weight_0:0  shape =  (3, 3, 512, 512)
# vs_decoder_src/res0/conv2/bias_0:0  shape =  (512,)
# vs_decoder_src/res1/conv1/weight_0:0  shape =  (3, 3, 256, 256)
# vs_decoder_src/res1/conv1/bias_0:0  shape =  (256,)
# vs_decoder_src/res1/conv2/weight_0:0  shape =  (3, 3, 256, 256)
# vs_decoder_src/res1/conv2/bias_0:0  shape =  (256,)
# vs_decoder_src/res2/conv1/weight_0:0  shape =  (3, 3, 128, 128)
# vs_decoder_src/res2/conv1/bias_0:0  shape =  (128,)
# vs_decoder_src/res2/conv2/weight_0:0  shape =  (3, 3, 128, 128)
# vs_decoder_src/res2/conv2/bias_0:0  shape =  (128,)
# vs_decoder_src/out_conv/weight_0:0  shape =  (1, 1, 128, 3)
# vs_decoder_src/out_conv/bias_0:0  shape =  (3,)
# vs_decoder_src/upscalem0/conv1/weight_0:0  shape =  (3, 3, 256, 704)
# vs_decoder_src/upscalem0/conv1/bias_0:0  shape =  (704,)
# vs_decoder_src/upscalem1/conv1/weight_0:0  shape =  (3, 3, 176, 352)
# vs_decoder_src/upscalem1/conv1/bias_0:0  shape =  (352,)
# vs_decoder_src/upscalem2/conv1/weight_0:0  shape =  (3, 3, 88, 176)
# vs_decoder_src/upscalem2/conv1/bias_0:0  shape =  (176,)
# vs_decoder_src/out_convm/weight_0:0  shape =  (1, 1, 22, 1)
# vs_decoder_src/out_convm/bias_0:0  shape =  (1,)
# vs_decoder_src/out_conv1/weight_0:0  shape =  (3, 3, 128, 3)
# vs_decoder_src/out_conv1/bias_0:0  shape =  (3,)
# vs_decoder_src/out_conv2/weight_0:0  shape =  (3, 3, 128, 3)
# vs_decoder_src/out_conv2/bias_0:0  shape =  (3,)
# vs_decoder_src/out_conv3/weight_0:0  shape =  (3, 3, 128, 3)
# vs_decoder_src/out_conv3/bias_0:0  shape =  (3,)
# vs_decoder_src/upscalem3/conv1/weight_0:0  shape =  (3, 3, 44, 88)
# vs_decoder_src/upscalem3/conv1/bias_0:0  shape =  (88,)
# vs_decoder_dst/upscale0/conv1/weight_0:0  shape =  (3, 3, 256, 2048)
# vs_decoder_dst/upscale0/conv1/bias_0:0  shape =  (2048,)
# vs_decoder_dst/upscale1/conv1/weight_0:0  shape =  (3, 3, 512, 1024)
# vs_decoder_dst/upscale1/conv1/bias_0:0  shape =  (1024,)
# vs_decoder_dst/upscale2/conv1/weight_0:0  shape =  (3, 3, 256, 512)
# vs_decoder_dst/upscale2/conv1/bias_0:0  shape =  (512,)
# vs_decoder_dst/res0/conv1/weight_0:0  shape =  (3, 3, 512, 512)
# vs_decoder_dst/res0/conv1/bias_0:0  shape =  (512,)
# vs_decoder_dst/res0/conv2/weight_0:0  shape =  (3, 3, 512, 512)
# vs_decoder_dst/res0/conv2/bias_0:0  shape =  (512,)
# vs_decoder_dst/res1/conv1/weight_0:0  shape =  (3, 3, 256, 256)
# vs_decoder_dst/res1/conv1/bias_0:0  shape =  (256,)
# vs_decoder_dst/res1/conv2/weight_0:0  shape =  (3, 3, 256, 256)
# vs_decoder_dst/res1/conv2/bias_0:0  shape =  (256,)
# vs_decoder_dst/res2/conv1/weight_0:0  shape =  (3, 3, 128, 128)
# vs_decoder_dst/res2/conv1/bias_0:0  shape =  (128,)
# vs_decoder_dst/res2/conv2/weight_0:0  shape =  (3, 3, 128, 128)
# vs_decoder_dst/res2/conv2/bias_0:0  shape =  (128,)
# vs_decoder_dst/out_conv/weight_0:0  shape =  (1, 1, 128, 3)
# vs_decoder_dst/out_conv/bias_0:0  shape =  (3,)
# vs_decoder_dst/upscalem0/conv1/weight_0:0  shape =  (3, 3, 256, 704)
# vs_decoder_dst/upscalem0/conv1/bias_0:0  shape =  (704,)
# vs_decoder_dst/upscalem1/conv1/weight_0:0  shape =  (3, 3, 176, 352)
# vs_decoder_dst/upscalem1/conv1/bias_0:0  shape =  (352,)
# vs_decoder_dst/upscalem2/conv1/weight_0:0  shape =  (3, 3, 88, 176)
# vs_decoder_dst/upscalem2/conv1/bias_0:0  shape =  (176,)
# vs_decoder_dst/out_convm/weight_0:0  shape =  (1, 1, 22, 1)
# vs_decoder_dst/out_convm/bias_0:0  shape =  (1,)
# vs_decoder_dst/out_conv1/weight_0:0  shape =  (3, 3, 128, 3)
# vs_decoder_dst/out_conv1/bias_0:0  shape =  (3,)
# vs_decoder_dst/out_conv2/weight_0:0  shape =  (3, 3, 128, 3)
# vs_decoder_dst/out_conv2/bias_0:0  shape =  (3,)
# vs_decoder_dst/out_conv3/weight_0:0  shape =  (3, 3, 128, 3)
# vs_decoder_dst/out_conv3/bias_0:0  shape =  (3,)
# vs_decoder_dst/upscalem3/conv1/weight_0:0  shape =  (3, 3, 44, 88)
# vs_decoder_dst/upscalem3/conv1/bias_0:0  shape =  (88,)

1111111

不懂帮顶

plotchen

不懂帮顶

比昂

yangala 发表于 2021-9-13 17:49
要在python里打开才看得到，正巧我早几天也好奇的看了看里面都有啥
# f = Path(r'D:\DeepFaceLab\Deep ...

请问如何打开的

yangala

比昂 发表于 2021-9-13 21:06
请问如何打开的

这。。。挺复杂的，先配置好vscode或者pycharm，然后找到加载模型的代码，然后插入打印的语句。。。

xiaoxue

yangala 发表于 2021-9-13 17:49
要在python里打开才看得到，正巧我早几天也好奇的看了看里面都有啥
# f = Path(r'D:\DeepFaceLab\Deep ...

牛，非常感谢

dsyrock

dat文件就是放了这个模型的各个你自己设定的参数