This thread has been locked.
If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.
工具与软件:
https://github.com/TexasInstruments/edgeai-tidl-tools 是我目前使用的 GitHub 链接。
我正在尝试在具有 x86_64的计算机上编译库、然后在 TDA4VM 电路板上推送推理。
到目前为止、我遇到了编译错误:
Operating System: Ubuntu 22.04.4 LTS
Kernel: Linux 6.5.0-45-generic
目前、编译挂起在这里...
~/edgeai-tidl-tools$ source ./scripts/run_python_examples.sh X64 Architecture Running 4 Models - ['cl-tfl-mobilenet_v1_1.0_224', 'ss-tfl-deeplabv3_mnv2_ade20k_float', 'od-tfl-ssd_mobilenet_v2_300_float', 'od-tfl-ssdlite_mobiledet_dsp_320x320_coco'] Running_Model : cl-tfl-mobilenet_v1_1.0_224 Process Process-1: Running_Model : ss-tfl-deeplabv3_mnv2_ade20k_float Process Process-2: Running_Model : od-tfl-ssd_mobilenet_v2_300_float Traceback (most recent call last): Traceback (most recent call last): File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/gort/edgeai-tidl-tools/examples/osrt_python/tfl/tflrt_delegate.py", line 183, in run_model experimental_delegates=[tflite.load_delegate(os.path.join(tidl_tools_path, 'tidl_model_import_tflite.so'), delegate_options)]) File "/home/gort/edgeai-tidl-tools/examples/osrt_python/tfl/tflrt_delegate.py", line 183, in run_model experimental_delegates=[tflite.load_delegate(os.path.join(tidl_tools_path, 'tidl_model_import_tflite.so'), delegate_options)]) File "/home/gort/edgeai-tidl-tools/lib/python3.10/site-packages/tflite_runtime/interpreter.py", line 166, in load_delegate delegate = Delegate(library, options) File "/home/gort/edgeai-tidl-tools/lib/python3.10/site-packages/tflite_runtime/interpreter.py", line 166, in load_delegate delegate = Delegate(library, options) File "/home/gort/edgeai-tidl-tools/lib/python3.10/site-packages/tflite_runtime/interpreter.py", line 73, in __init__ self._library = ctypes.pydll.LoadLibrary(library) File "/home/gort/edgeai-tidl-tools/lib/python3.10/site-packages/tflite_runtime/interpreter.py", line 73, in __init__ self._library = ctypes.pydll.LoadLibrary(library) File "/usr/lib/python3.10/ctypes/__init__.py", line 452, in LoadLibrary return self._dlltype(name) File "/usr/lib/python3.10/ctypes/__init__.py", line 452, in LoadLibrary return self._dlltype(name) File "/usr/lib/python3.10/ctypes/__init__.py", line 374, in __init__ self._handle = _dlopen(self._name, mode) File "/usr/lib/python3.10/ctypes/__init__.py", line 374, in __init__ self._handle = _dlopen(self._name, mode) OSError: /home/gort/edgeai-tidl-tools/tidl_tools/tidl_model_import_tflite.so: cannot open shared object file: No such file or directory OSError: /home/gort/edgeai-tidl-tools/tidl_tools/tidl_model_import_tflite.so: cannot open shared object file: No such file or directory Exception ignored in: <function Delegate.__del__ at 0x784a9b1331c0> Exception ignored in: <function Delegate.__del__ at 0x784a9b1331c0> Traceback (most recent call last): Traceback (most recent call last): File "/home/gort/edgeai-tidl-tools/lib/python3.10/site-packages/tflite_runtime/interpreter.py", line 109, in __del__ File "/home/gort/edgeai-tidl-tools/lib/python3.10/site-packages/tflite_runtime/interpreter.py", line 109, in __del__ if self._library is not None: if self._library is not None: AttributeError: 'Delegate' object has no attribute '_library' AttributeError: 'Delegate' object has no attribute '_library' Process Process-3: Traceback (most recent call last): File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/gort/edgeai-tidl-tools/examples/osrt_python/tfl/tflrt_delegate.py", line 183, in run_model experimental_delegates=[tflite.load_delegate(os.path.join(tidl_tools_path, 'tidl_model_import_tflite.so'), delegate_options)]) File "/home/gort/edgeai-tidl-tools/lib/python3.10/site-packages/tflite_runtime/interpreter.py", line 166, in load_delegate delegate = Delegate(library, options) File "/home/gort/edgeai-tidl-tools/lib/python3.10/site-packages/tflite_runtime/interpreter.py", line 73, in __init__ self._library = ctypes.pydll.LoadLibrary(library) File "/usr/lib/python3.10/ctypes/__init__.py", line 452, in LoadLibrary return self._dlltype(name) File "/usr/lib/python3.10/ctypes/__init__.py", line 374, in __init__ self._handle = _dlopen(self._name, mode) OSError: /home/gort/edgeai-tidl-tools/tidl_tools/tidl_model_import_tflite.so: cannot open shared object file: No such file or directory Exception ignored in: <function Delegate.__del__ at 0x784a9b1331c0> Traceback (most recent call last): File "/home/gort/edgeai-tidl-tools/lib/python3.10/site-packages/tflite_runtime/interpreter.py", line 109, in __del__ if self._library is not None: AttributeError: 'Delegate' object has no attribute '_library' Running_Model : od-tfl-ssdlite_mobiledet_dsp_320x320_coco Process Process-4: Traceback (most recent call last): File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/gort/edgeai-tidl-tools/examples/osrt_python/tfl/tflrt_delegate.py", line 183, in run_model experimental_delegates=[tflite.load_delegate(os.path.join(tidl_tools_path, 'tidl_model_import_tflite.so'), delegate_options)]) File "/home/gort/edgeai-tidl-tools/lib/python3.10/site-packages/tflite_runtime/interpreter.py", line 166, in load_delegate delegate = Delegate(library, options) File "/home/gort/edgeai-tidl-tools/lib/python3.10/site-packages/tflite_runtime/interpreter.py", line 73, in __init__ self._library = ctypes.pydll.LoadLibrary(library) File "/usr/lib/python3.10/ctypes/__init__.py", line 452, in LoadLibrary return self._dlltype(name) File "/usr/lib/python3.10/ctypes/__init__.py", line 374, in __init__ self._handle = _dlopen(self._name, mode) OSError: /home/gort/edgeai-tidl-tools/tidl_tools/tidl_model_import_tflite.so: cannot open shared object file: No such file or directory Exception ignored in: <function Delegate.__del__ at 0x784a9b1331c0> Traceback (most recent call last): File "/home/gort/edgeai-tidl-tools/lib/python3.10/site-packages/tflite_runtime/interpreter.py", line 109, in __del__ if self._library is not None: AttributeError: 'Delegate' object has no attribute '_library'
我不是很清楚如何完成的事情,超过这种停顿。 有人对从何处开始调试输出有任何建议吗?
Seth
噢、我更改了编译器。。。
这可能与编译错误有关。 我将把它改回来、看看能走多远。
Seth
好的...所以 Docker 脚本构建得足够好、没有错误。
Seth
尊敬的 Seth:
是的、我们建议使用 Docker 映像并运行安装文档中列出的安装脚本来安装所需的依赖项。
这样做是否解决了您的问题?
此致!
Asha
Asha、您好!
我叫 Seth。 该问题尚未完全解决、因为我尚未尝试更新 TDA4VM 以从存储库进行推理构建。
我是否也应该在 TDA4VM 上使用 Docker、或者更适合只使用 SOC=am68pa 进行构建、然后让 Docker 处理所有内容、最后尝试将源代码放在 TDA4VM 上?
Seth
P.S.我将继续努力使它发挥作用。 如果有任何人有任何光荣作为从 TDA4VM 的输出,请分享.
尊敬的 Seth:
编译仅发生在主机 PC 上。 您可以将模型工件放置在 TDA4VM 上、并在 EVM 上使用相同的脚本运行。 有关步骤、请参阅此处的说明: https://github.com/TexasInstruments/edgeai-tidl-tools/tree/master/examples/osrt_python
此致!
Asha
感谢您让我理解。 我会进行尝试并在完成后进行回复。
Seth
谢谢你。 我被误认为如何建造和使用该产品。 现在、我想我可以离开这个 e2e 聊天客户端/论坛。
Seth
P.S.如果我遇到问题、我将重新尝试连接。 谢谢你。