DF_UD_416_wf_160w迭代次数_高分辨率模型

8761611 · 发表于 2023-10-4 10:00:13

从某站购买后的外网模型，分享到论坛给大家，经过测试质量不错

=============== Model Summary ===============
==                                        ==
==          Model name: DF-UD416WF_SAEHD ==
==                                        ==
==    Current iteration: 1601351       ==
==                                        ==
==------------- Model Options -------------==
==                                        ==
==          resolution: 416             ==
==          face_type: wf             ==
==    models_opt_on_gpu: True          ==
==                archi: df-ud          ==
==             ae_dims: 400             ==
==             e_dims: 80             ==
==             d_dims: 80             ==
==          d_mask_dims: 26             ==
==    masked_training: True          ==
==    eyes_mouth_prio: False          ==
==          uniform_yaw: False          ==
==       blur_out_mask: False          ==
==          adabelief: True          ==
==          lr_dropout: y             ==
==          random_warp: False          ==
==    random_hsv_power: 0.0             ==
==    true_face_power: 0.0             ==
==    face_style_power: 0.0             ==
==       bg_style_power: 0.0             ==
==             ct_mode: none          ==
==             clipgrad: True          ==
==             pretrain: False          ==
==    autobackup_hour: 0             ==
== write_preview_history: False          ==
==          target_iter: 0             ==
==    random_src_flip: False          ==
==    random_dst_flip: False          ==
==          batch_size: 4             ==
==          gan_power: 0.01          ==
==       gan_patch_size: 60             ==
==             gan_dims: 30             ==
==                                        ==
==-------------- Running On ---------------==
==                                        ==
==       Device index: 0             ==
==                Name: A100-SXM4-40GB ==
==                VRAM: 37.47GB       ==
==                                        ==
=============================================

付费内容

亲爱的游客您好！如果您要查看本帖隐藏内容请向楼主支付22灵石

立即购买

购买记录

710498801 · 发表于 2023-10-7 22:59:06

谢谢楼主分享

红大哥 · 发表于 2023-11-11 21:33:25

感谢分享

sensebb · 发表于 2023-12-10 18:44:34

512的有好的分享吗

爱玛 · 发表于 2024-1-29 08:40:58

感谢分享

爱玛 · 发表于 2024-1-29 11:56:11

启动中. 目标迭代: 2000000. 按 "Enter" 停止训练并保存进度.
Error: 2 root error(s) found.
  (0) Resource exhausted: OOM when allocating tensor with shape[8,112,192,192] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
      [[node Conv2D_60 (defined at E:\DeepAi\DeepFaceLab_NV30_221111_CN\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:101) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

      [[concat_5/concat/_1475]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

  (1) Resource exhausted: OOM when allocating tensor with shape[8,112,192,192] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
      [[node Conv2D_60 (defined at E:\DeepAi\DeepFaceLab_NV30_221111_CN\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:101) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

0 successful operations.
0 derived errors ignored.

我买了，为什么会报错呢？  是不是假货啊？？？？  楼主

yelin8258 · 发表于 2024-5-18 23:42:50

3080 显卡训练不了阿怎么回事？

meiyouruguo · 发表于 2024-8-9 10:50:39

爱玛发表于 2024-1-29 11:56
启动中. 目标迭代: 2000000. 按 "Enter" 停止训练并保存进度.
Error: 2 root error(s) found.
(0) Resour ...

==       Device index: 0             ==
==                Name: A100-SXM4-40GB ==
==                VRAM: 37.47GB       ==

你看看别人的显卡,看看自己电脑的显卡,你发的错误包含 OOM 是因为显存不足

mjy9921129 · 发表于 2024-9-29 13:53:01

把参数调低应该可以

		自动登录	找回密码
密码			立即注册

DF_UD_416_wf_160w迭代次数_高分辨率模型

突出会员

丹神