Initializing models: 100%|###############################################################| 5/5 [00:13<00:00, 2.62s/it]
Loading samples: 100%|############################################################| 2542/2542 [00:03<00:00, 648.06it/s]
Loading samples: 100%|##########################################################| 22446/22446 [00:32<00:00, 682.23it/s]
==================== Model Summary =====================
== ==
== Model name: new_SAEHD ==
== ==
== Current iteration: 5199210 ==
== ==
==------------------ Model Options -------------------==
== ==
== resolution: 256 ==
== face_type: f ==
== models_opt_on_gpu: True ==
== archi: df-d ==
== ae_dims: 256 ==
== e_dims: 64 ==
== d_dims: 64 ==
== d_mask_dims: 22 ==
== masked_training: True ==
== uniform_yaw: False ==
== lr_dropout: n ==
== random_warp: True ==
== 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: 0 ==
== write_preview_history: False ==
== target_iter: 0 ==
== random_flip: True ==
== batch_size: 22 ==
== eyes_mouth_prio: False ==
== adabelief: True ==
== gan_patch_size: 16 ==
== gan_dims: 16 ==
== ==
==-------------------- Running On --------------------==
== ==
== Device index: 0 ==
== Name: NVIDIA GeForce GTX 1060 6GB ==
== VRAM: 6.00GB ==
== ==
========================================================
Starting. Press "Enter" to stop training and save model.
Error: 2 root error(s) found.
(0) Resource exhausted: OOM when allocating tensor with shape[22,44,128,128] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[node DepthToSpace_7 (defined at F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\DeepFaceLab\core\leras\ops\__init__.py:336) ]]
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.
[[concat_36/concat/_491]]
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.
(1) Resource exhausted: OOM when allocating tensor with shape[22,44,128,128] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[node DepthToSpace_7 (defined at F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\DeepFaceLab\core\leras\ops\__init__.py:336) ]]
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.
Errors may have originated from an input operation.
Input Source operations connected to node DepthToSpace_7:
LeakyRelu_21 (defined at F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\DeepFaceLab\core\leras\archis\DeepFakeArchi.py:58)
Input Source operations connected to node DepthToSpace_7:
LeakyRelu_21 (defined at F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\DeepFaceLab\core\leras\archis\DeepFakeArchi.py:58)
Original stack trace for 'DepthToSpace_7':
File "threading.py", line 884, in _bootstrap
File "threading.py", line 916, in _bootstrap_inner
File "threading.py", line 864, in run
File "F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\DeepFaceLab\mainscripts\Trainer.py", line 59, in trainerThread
debug=debug)
File "F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\DeepFaceLab\models\ModelBase.py", line 191, in __init__
self.on_initialize()
File "F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 372, in on_initialize
gpu_pred_src_src, gpu_pred_src_srcm = self.decoder_src(gpu_src_code)
File "F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\DeepFaceLab\core\leras\models\ModelBase.py", line 117, in __call__
return self.forward(*args, **kwargs)
File "F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\DeepFaceLab\core\leras\archis\DeepFakeArchi.py", line 200, in forward
m = self.upscalem2(m)
File "F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\DeepFaceLab\core\leras\models\ModelBase.py", line 117, in __call__
return self.forward(*args, **kwargs)
File "F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\DeepFaceLab\core\leras\archis\DeepFakeArchi.py", line 59, in forward
x = nn.depth_to_space(x, 2)
File "F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\DeepFaceLab\core\leras\ops\__init__.py", line 336, in depth_to_space
return tf.depth_to_space(x, size, data_format=nn.data_format)
File "F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\python-3.6.8\lib\site-packages\tensorflow\python\util\dispatch.py", line 201, in wrapper
return target(*args, **kwargs)
File "F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\array_ops.py", line 3913, in depth_to_space
return gen_array_ops.depth_to_space(input, block_size, data_format, name=name)
File "F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 1636, in depth_to_space
data_format=data_format, name=name)
File "F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 750, in _apply_op_helper
attrs=attr_protos, op_def=op_def)
File "F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 3536, in _create_op_internal
op_def=op_def)
File "F:\DeepFaceLab\DeepFaceLab_NVIDIA\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 1990, in __init__
self._traceback = tf_stack.extract_stack()
|Archiver|手机版|deepfacelab中文网
|网站地图
发表于 2021-4-5 11:10:10
发表于 2021-4-5 14:18:57
