test运行失败

Question

test运行失败

importfreedom opened this issue 3 years ago · comments

我将example文件夹放在了AiSpeech文件夹下，执行example/ueExample/FaceGoodLiveLink.exe。并且确保麦克风已正常链接，但是虚拟人物没有任何的反应，人物的嘴唇没有任务动作。
得到以下错误提示：
2022-01-22 17:53:37.267016: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll
2022-01-22 17:53:37.751174: E tensorflow/stream_executor/cuda/cuda_blas.cc:238] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2022-01-22 17:53:37.751374: E tensorflow/stream_executor/cuda/cuda_blas.cc:238] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2022-01-22 17:53:37.752340: E tensorflow/stream_executor/cuda/cuda_blas.cc:238] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2022-01-22 17:53:37.752457: E tensorflow/stream_executor/cuda/cuda_blas.cc:238] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2022-01-22 17:53:37.755998: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2022-01-22 17:53:39.230418: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
2022-01-22 17:53:39.230887: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
2022-01-22 17:53:39.231089: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
2022-01-22 17:53:39.231184: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
2022-01-22 17:53:39.231703: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
2022-01-22 17:53:39.231795: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
2022-01-22 17:53:39.231886: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
2022-01-22 17:53:39.232217: E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
Exception in thread Thread-3:
Traceback (most recent call last):
File "D:\Anconda\envs\work\lib\site-packages\tensorflow_core\python\client\session.py", line 1365, in _do_call
return fn(*args)
File "D:\Anconda\envs\work\lib\site-packages\tensorflow_core\python\client\session.py", line 1350, in _run_fn
target_list, run_metadata)
File "D:\Anconda\envs\work\lib\site-packages\tensorflow_core\python\client\session.py", line 1443, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.UnknownError: 2 root error(s) found.
(0) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
[[{{node conv2d/Conv2D}}]]
[[dense_1/BiasAdd/_11]]
(1) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
[[{{node conv2d/Conv2D}}]]
0 successful operations.
0 derived errors ignored.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\Anconda\envs\work\lib\threading.py", line 926, in _bootstrap_inner
self.run()
File "D:\Anconda\envs\work\lib\threading.py", line 870, in run
self._target(*self._args, **self._kwargs)
File "D:/Github_Code/Audio2Face/code/test/AiSpeech/zsmeif.py", line 93, in worker
output_data = get_weight(output_lpc)
File "D:\Github_Code\Audio2Face\code\test\AiSpeech\lib\tensorflow\input_lpc_output_weight.py", line 40, in get_weight
self.input_keep_prob_tensor: 1.0
File "D:\Anconda\envs\work\lib\site-packages\tensorflow_core\python\client\session.py", line 956, in run
run_metadata_ptr)
File "D:\Anconda\envs\work\lib\site-packages\tensorflow_core\python\client\session.py", line 1180, in _run
feed_dict_tensor, options, run_metadata)
File "D:\Anconda\envs\work\lib\site-packages\tensorflow_core\python\client\session.py", line 1359, in _do_run
run_metadata)
File "D:\Anconda\envs\work\lib\site-packages\tensorflow_core\python\client\session.py", line 1384, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.UnknownError: 2 root error(s) found.
(0) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
[[node conv2d/Conv2D (defined at \Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\ops.py:1748) ]]
[[dense_1/BiasAdd/_11]]
(1) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
[[node conv2d/Conv2D (defined at \Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\ops.py:1748) ]]
0 successful operations.
0 derived errors ignored.

Original stack trace for 'conv2d/Conv2D':
File "/Github_Code/Audio2Face/code/test/AiSpeech/zsmeif.py", line 83, in
pb_weights_animation = WeightsAnimation(pbfile_path)
File "\Github_Code\Audio2Face\code\test\AiSpeech\lib\tensorflow\input_lpc_output_weight.py", line 24, in init
tf.import_graph_def(self.graph_def, name='')
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\util\deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\importer.py", line 405, in import_graph_def
producer_op_list=producer_op_list)
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\importer.py", line 517, in _import_graph_def_internal
_ProcessNewOps(graph)
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\importer.py", line 243, in _ProcessNewOps
for new_op in graph._add_new_tf_operations(compute_devices=False): # pylint: disable=protected-access
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\ops.py", line 3561, in _add_new_tf_operations
for c_op in c_api_util.new_tf_operations(self)
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\ops.py", line 3561, in
for c_op in c_api_util.new_tf_operations(self)
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\ops.py", line 3451, in _create_op_from_tf_operation
ret = Operation(c_op, self)
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1748, in init
self._traceback = tf_stack.extract_stack()

Exception in thread Thread-2:
Traceback (most recent call last):
File "D:\Anconda\envs\work\lib\site-packages\tensorflow_core\python\client\session.py", line 1365, in _do_call
return fn(*args)
File "D:\Anconda\envs\work\lib\site-packages\tensorflow_core\python\client\session.py", line 1350, in _run_fn
target_list, run_metadata)
File "D:\Anconda\envs\work\lib\site-packages\tensorflow_core\python\client\session.py", line 1443, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.UnknownError: 2 root error(s) found.
(0) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
[[{{node conv2d/Conv2D}}]]
[[dense_1/BiasAdd/_11]]
(1) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
[[{{node conv2d/Conv2D}}]]
0 successful operations.
0 derived errors ignored.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\Anconda\envs\work\lib\threading.py", line 926, in _bootstrap_inner
self.run()
File "D:\Anconda\envs\work\lib\threading.py", line 870, in run
self._target(*self._args, **self._kwargs)
File "D:/Github_Code/Audio2Face/code/test/AiSpeech/zsmeif.py", line 93, in worker
output_data = get_weight(output_lpc)
File "D:\Github_Code\Audio2Face\code\test\AiSpeech\lib\tensorflow\input_lpc_output_weight.py", line 40, in get_weight
self.input_keep_prob_tensor: 1.0
File "D:\Anconda\envs\work\lib\site-packages\tensorflow_core\python\client\session.py", line 956, in run
run_metadata_ptr)
File "D:\Anconda\envs\work\lib\site-packages\tensorflow_core\python\client\session.py", line 1180, in _run
feed_dict_tensor, options, run_metadata)
File "D:\Anconda\envs\work\lib\site-packages\tensorflow_core\python\client\session.py", line 1359, in _do_run
run_metadata)
File "D:\Anconda\envs\work\lib\site-packages\tensorflow_core\python\client\session.py", line 1384, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.UnknownError: 2 root error(s) found.
(0) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
[[node conv2d/Conv2D (defined at \Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\ops.py:1748) ]]
[[dense_1/BiasAdd/_11]]
(1) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
[[node conv2d/Conv2D (defined at \Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\ops.py:1748) ]]
0 successful operations.
0 derived errors ignored.

Original stack trace for 'conv2d/Conv2D':
File "/Github_Code/Audio2Face/code/test/AiSpeech/zsmeif.py", line 83, in
pb_weights_animation = WeightsAnimation(pbfile_path)
File "\Github_Code\Audio2Face\code\test\AiSpeech\lib\tensorflow\input_lpc_output_weight.py", line 24, in init
tf.import_graph_def(self.graph_def, name='')
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\util\deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\importer.py", line 405, in import_graph_def
producer_op_list=producer_op_list)
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\importer.py", line 517, in _import_graph_def_internal
_ProcessNewOps(graph)
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\importer.py", line 243, in _ProcessNewOps
for new_op in graph._add_new_tf_operations(compute_devices=False): # pylint: disable=protected-access
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\ops.py", line 3561, in _add_new_tf_operations
for c_op in c_api_util.new_tf_operations(self)
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\ops.py", line 3561, in
for c_op in c_api_util.new_tf_operations(self)
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\ops.py", line 3451, in _create_op_from_tf_operation
ret = Operation(c_op, self)
File "\Anconda\envs\work\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1748, in init
self._traceback = tf_stack.extract_stack()

Nero · Answer 1 · Sun Jan 23 2022 12:14:20 GMT+0800 (China Standard Time)

从报错上看是因为cudnn内存开辟失败了，你可以先将python脚本先运行起来，再开UE程序试试。并且保证GPU是1060 6G以上

Pearson Zhao · Answer 2 · Tue Jan 25 2022 14:20:36 GMT+0800 (China Standard Time)

@SZNero 这个好像都是运行在windows下的吧，本地没有显卡，能运行在服务器吗？

Nero · Answer 3 · Wed Feb 16 2022 10:26:43 GMT+0800 (China Standard Time)

可以，但是你得自己改写流程，就是前面的ASR和TTS阶段。