|
发表于 2022-3-2 22:29:36
|
显示全部楼层
完整的报错信息弹出来了。求大佬解读:
初始化模型: 80%|#########################################################6 | 4/5 [03:20<00:50, 50.22s/it]
Error: OOM when allocating tensor with shape[3840] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[node src_dst_opt/vs_inter_B/upscale1/conv1/bias_0/Assign (defined at G:\DFL-1120-030122\_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py:37) ]]
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.
Caused by op 'src_dst_opt/vs_inter_B/upscale1/conv1/bias_0/Assign', defined at:
File "threading.py", line 884, in _bootstrap
File "threading.py", line 916, in _bootstrap_inner
File "threading.py", line 864, in run
File "G:\DFL-1120-030122\_internal\DeepFaceLab\mainscripts\Trainer.py", line 58, in trainerThread
debug=debug)
File "G:\DFL-1120-030122\_internal\DeepFaceLab\models\ModelBase.py", line 193, in __init__
self.on_initialize()
File "G:\DFL-1120-030122\_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 328, in on_initialize
self.src_dst_opt.initialize_variables (self.src_dst_trainable_weights, vars_on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu')
File "G:\DFL-1120-030122\_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py", line 37, in initialize_variables
vs = { v.name : tf.get_variable ( f'vs_{v.name}'.replace(':','_'), v.shape, dtype=v.dtype, initializer=tf.initializers.constant(0.0), trainable=False) for v in trainable_weights }
File "G:\DFL-1120-030122\_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py", line 37, in <dictcomp>
vs = { v.name : tf.get_variable ( f'vs_{v.name}'.replace(':','_'), v.shape, dtype=v.dtype, initializer=tf.initializers.constant(0.0), trainable=False) for v in trainable_weights }
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 1479, in get_variable
aggregation=aggregation)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 1220, in get_variable
aggregation=aggregation)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 547, in get_variable
aggregation=aggregation)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 499, in _true_getter
aggregation=aggregation)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 911, in _get_single_variable
aggregation=aggregation)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 213, in __call__
return cls._variable_v1_call(*args, **kwargs)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 176, in _variable_v1_call
aggregation=aggregation)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 155, in <lambda>
previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 2495, in default_variable_creator
expected_shape=expected_shape, import_scope=import_scope)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 217, in __call__
return super(VariableMetaclass, cls).__call__(*args, **kwargs)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 1395, in __init__
constraint=constraint)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 1547, in _init_from_args
validate_shape=validate_shape).op
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\state_ops.py", line 223, in assign
validate_shape=validate_shape)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\gen_state_ops.py", line 64, in assign
use_locking=use_locking, name=name)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\util\deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 3300, in create_op
op_def=op_def)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 1801, in __init__
self._traceback = tf_stack.extract_stack()
ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[3840] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[node src_dst_opt/vs_inter_B/upscale1/conv1/bias_0/Assign (defined at G:\DFL-1120-030122\_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py:37) ]]
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.
Traceback (most recent call last):
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1334, in _do_call
return fn(*args)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1319, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1407, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[3840] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[{{node src_dst_opt/vs_inter_B/upscale1/conv1/bias_0/Assign}}]]
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.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "G:\DFL-1120-030122\_internal\DeepFaceLab\mainscripts\Trainer.py", line 58, in trainerThread
debug=debug)
File "G:\DFL-1120-030122\_internal\DeepFaceLab\models\ModelBase.py", line 193, in __init__
self.on_initialize()
File "G:\DFL-1120-030122\_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 623, in on_initialize
model.init_weights()
File "G:\DFL-1120-030122\_internal\DeepFaceLab\core\leras\layers\Saveable.py", line 104, in init_weights
nn.init_weights(self.get_weights())
File "G:\DFL-1120-030122\_internal\DeepFaceLab\core\leras\ops\__init__.py", line 48, in init_weights
nn.tf_sess.run (ops)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 929, in run
run_metadata_ptr)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1152, in _run
feed_dict_tensor, options, run_metadata)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1328, in _do_run
run_metadata)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1348, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[3840] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[node src_dst_opt/vs_inter_B/upscale1/conv1/bias_0/Assign (defined at G:\DFL-1120-030122\_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py:37) ]]
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.
Caused by op 'src_dst_opt/vs_inter_B/upscale1/conv1/bias_0/Assign', defined at:
File "threading.py", line 884, in _bootstrap
File "threading.py", line 916, in _bootstrap_inner
File "threading.py", line 864, in run
File "G:\DFL-1120-030122\_internal\DeepFaceLab\mainscripts\Trainer.py", line 58, in trainerThread
debug=debug)
File "G:\DFL-1120-030122\_internal\DeepFaceLab\models\ModelBase.py", line 193, in __init__
self.on_initialize()
File "G:\DFL-1120-030122\_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 328, in on_initialize
self.src_dst_opt.initialize_variables (self.src_dst_trainable_weights, vars_on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu')
File "G:\DFL-1120-030122\_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py", line 37, in initialize_variables
vs = { v.name : tf.get_variable ( f'vs_{v.name}'.replace(':','_'), v.shape, dtype=v.dtype, initializer=tf.initializers.constant(0.0), trainable=False) for v in trainable_weights }
File "G:\DFL-1120-030122\_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py", line 37, in <dictcomp>
vs = { v.name : tf.get_variable ( f'vs_{v.name}'.replace(':','_'), v.shape, dtype=v.dtype, initializer=tf.initializers.constant(0.0), trainable=False) for v in trainable_weights }
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 1479, in get_variable
aggregation=aggregation)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 1220, in get_variable
aggregation=aggregation)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 547, in get_variable
aggregation=aggregation)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 499, in _true_getter
aggregation=aggregation)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 911, in _get_single_variable
aggregation=aggregation)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 213, in __call__
return cls._variable_v1_call(*args, **kwargs)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 176, in _variable_v1_call
aggregation=aggregation)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 155, in <lambda>
previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 2495, in default_variable_creator
expected_shape=expected_shape, import_scope=import_scope)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 217, in __call__
return super(VariableMetaclass, cls).__call__(*args, **kwargs)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 1395, in __init__
constraint=constraint)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\variables.py", line 1547, in _init_from_args
validate_shape=validate_shape).op
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\state_ops.py", line 223, in assign
validate_shape=validate_shape)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\ops\gen_state_ops.py", line 64, in assign
use_locking=use_locking, name=name)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\util\deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 3300, in create_op
op_def=op_def)
File "G:\DFL-1120-030122\_internal\python-3.6.8\lib\site-packages\tensorflow\python\framework\ops.py", line 1801, in __init__
self._traceback = tf_stack.extract_stack()
ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[3840] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[node src_dst_opt/vs_inter_B/upscale1/conv1/bias_0/Assign (defined at G:\DFL-1120-030122\_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py:37) ]]
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. |
|