|
|
星级打分
平均分:NAN 参与人数:0 我的评分:未评
本帖最后由 kayagood 于 2021-11-3 23:04 编辑
求教给位老师这个错误是什么原因？（问题已解决是虚拟内存设置太小了）
运行merge SAEHD最开始都没问题，吃个饭回来就发现报错了。
配置：显卡3060 12G 系统WIN10 21H1 硬件加速已开启 内存16G
[CPU] : CPU
[0] : NVIDIA GeForce RTX 3060
[0] 选择哪一个设备？ :
0
初始化模型: 100%|########################################################################| 9/9 [00:03<00:00, 2.79it/s]
Loaded 422 packed faces from F:\clzl\DeepFaceLab_NVIDIA_RTX3000_series\workspace\data_src\aligned
Sort by yaw: 100%|################################################################| 128/128 [00:00<00:00, 10694.21it/s]
实例加载中: 100%|###################################################################| 783/783 [00:01<00:00, 482.44it/s]
Sort by yaw: 100%|#################################################################| 128/128 [00:00<00:00, 4583.70it/s]
================== Model Summary ===================
== ==
== Model name: f128_SAEHD ==
== ==
== Current iteration: 929646 ==
== ==
==---------------- Model Options -----------------==
== ==
== resolution: 128 ==
== face_type: f ==
== models_opt_on_gpu: True ==
== archi: df ==
== ae_dims: 256 ==
== e_dims: 64 ==
== d_dims: 64 ==
== d_mask_dims: 22 ==
== masked_training: True ==
== uniform_yaw: True ==
== lr_dropout: y ==
== random_warp: False ==
== gan_power: 0.1 ==
== true_face_power: 0.01 ==
== face_style_power: 1.0 ==
== bg_style_power: 0.0 ==
== ct_mode: lct ==
== clipgrad: True ==
== pretrain: False ==
== autobackup_hour: 0 ==
== write_preview_history: False ==
== target_iter: 0 ==
== random_flip: True ==
== batch_size: 4 ==
== adabelief: False ==
== 猫の汉化: 猫猫YES ==
== 出售仙丹: QQ564646676 ==
== 免费教程: 人脸素材 ==
== 大神答疑: 进阶技巧 ==
== 人脸素材: 请访问dfldata.xyz ==
== eyes_mouth_prio: False ==
== gan_patch_size: 16 ==
== gan_dims: 16 ==
== ==
==------------------ Running On ------------------==
== ==
== Device index: 0 ==
== Name: NVIDIA GeForce RTX 3060 ==
== VRAM: 10.25GB ==
== ==
====================================================
Deepfake中文网：www.deepfaker.xyz
公众号：托尼是塔克
=============================================
启动中. 按 "Enter" 停止训练并保存进度。
保存时间|迭代次数|单次时间|源损失|目标损失
Error:
Traceback (most recent call last):
File "F:\clzl\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\mainscripts\Trainer.py", line 169, in trainerThread
model_save()
File "F:\clzl\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\mainscripts\Trainer.py", line 68, in model_save
model.save()
File "F:\clzl\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\models\ModelBase.py", line 393, in save
self.onSave()
File "F:\clzl\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 728, in onSave
model.save_weights ( self.get_strpath_storage_for_file(filename) )
File "F:\clzl\DeepFaceLab_NVIDIA_RTX3000_series\_internal\DeepFaceLab\core\leras\layers\Saveable.py", line 59, in save_weights
d_dumped = pickle.dumps (d, 4)
MemoryError
==================================
搞定！！！
==================================
请按任意键继续. . .
|
|
|Archiver|手机版|deepfacelab中文网
|网站地图
发表于 2021-11-1 19:41:43
楼主