I am trying to tune Mobilenet_V1 ONNX model for arm64 using the below command:
tvmc tune --target “llvm -mcpu=cortex-a57 -mtriple=aarch64-linux-android -mattr=’+neon’” --target-llvm-mcpu cortex-a57 --number 3 --repeat 3 -o Mobilenet_v1_arm64_cpu.json …/…/models/Mobilenet_v1_1.0_224.onnx
The following error is coming: [15:20:44] /home/test/srividya/TVM/tvm2/tvm/src/target/target_kind.cc:164: Warning: Unable to detect CUDA version, default to “-mcpu=sm_20” instead [15:20:44] /home/test/srividya/TVM/tvm2/tvm/src/target/target_kind.cc:190: Warning: Unable to detect ROCm compute arch, default to “-mcpu=gfx900” instead [15:20:44] /home/test/srividya/TVM/tvm2/tvm/src/target/target_kind.cc:204: Warning: Unable to detect ROCm version, assuming >= 3.5 [15:20:44] /home/test/srividya/TVM/tvm2/tvm/src/target/target_kind.cc:164: Warning: Unable to detect CUDA version, default to “-mcpu=sm_20” instead [15:20:44] /home/test/srividya/TVM/tvm2/tvm/src/target/target_kind.cc:190: Warning: Unable to detect ROCm compute arch, default to “-mcpu=gfx900” instead [15:20:44] /home/test/srividya/TVM/tvm2/tvm/src/target/target_kind.cc:204: Warning: Unable to detect ROCm version, assuming >= 3.5 [15:20:45] /home/test/srividya/TVM/tvm2/tvm/src/target/target_kind.cc:164: Warning: Unable to detect CUDA version, default to “-mcpu=sm_20” instead [15:20:45] /home/test/srividya/TVM/tvm2/tvm/src/target/target_kind.cc:190: Warning: Unable to detect ROCm compute arch, default to “-mcpu=gfx900” instead [15:20:45] /home/test/srividya/TVM/tvm2/tvm/src/target/target_kind.cc:204: Warning: Unable to detect ROCm version, assuming >= 3.5 [Task 1/20] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/50) | 0.00 s/usr/bin/python3: No module named tvm.exec.popen_worker Traceback (most recent call last): File “/home/test/.local/bin/tvmc”, line 11, in load_entry_point(‘tvm==0.8.dev1914+g523eb12a1’, ‘console_scripts’, ‘tvmc’)() File “/home/test/.local/lib/python3.8/site-packages/tvm-0.8.dev1914+g523eb12a1-py3.8-linux-x86_64.egg/tvm/driver/tvmc/main.py”, line 94, in main sys.exit(_main(sys.argv[1:])) File “/home/test/.local/lib/python3.8/site-packages/tvm-0.8.dev1914+g523eb12a1-py3.8-linux-x86_64.egg/tvm/driver/tvmc/main.py”, line 87, in _main return args.func(args) File “/home/test/.local/lib/python3.8/site-packages/tvm-0.8.dev1914+g523eb12a1-py3.8-linux-x86_64.egg/tvm/driver/tvmc/autotuner.py”, line 266, in drive_tune tune_model( File “/home/test/.local/lib/python3.8/site-packages/tvm-0.8.dev1914+g523eb12a1-py3.8-linux-x86_64.egg/tvm/driver/tvmc/autotuner.py”, line 486, in tune_model tune_tasks(tasks, tuning_records, **tuning_options) File “/home/test/.local/lib/python3.8/site-packages/tvm-0.8.dev1914+g523eb12a1-py3.8-linux-x86_64.egg/tvm/driver/tvmc/autotuner.py”, line 687, in tune_tasks tuner_obj.tune( File “/home/test/.local/lib/python3.8/site-packages/tvm-0.8.dev1914+g523eb12a1-py3.8-linux-x86_64.egg/tvm/autotvm/tuner/xgboost_tuner.py”, line 105, in tune super(XGBTuner, self).tune(*args, **kwargs) File “/home/test/.local/lib/python3.8/site-packages/tvm-0.8.dev1914+g523eb12a1-py3.8-linux-x86_64.egg/tvm/autotvm/tuner/tuner.py”, line 112, in tune measure_batch = create_measure_batch(self.task, measure_option) File “/home/test/.local/lib/python3.8/site-packages/tvm-0.8.dev1914+g523eb12a1-py3.8-linux-x86_64.egg/tvm/autotvm/measure/measure.py”, line 282, in create_measure_batch attach_objects = runner.set_task(task) File “/home/test/.local/lib/python3.8/site-packages/tvm-0.8.dev1914+g523eb12a1-py3.8-linux-x86_64.egg/tvm/autotvm/measure/measure_methods.py”, line 441, in set_task tracker = Tracker(port=9000, port_end=10000, silent=True) File “/home/test/.local/lib/python3.8/site-packages/tvm-0.8.dev1914+g523eb12a1-py3.8-linux-x86_64.egg/tvm/rpc/tracker.py”, line 451, in init self.port, self.stop_key = self.proc.recv() File “/home/test/.local/lib/python3.8/site-packages/tvm-0.8.dev1914+g523eb12a1-py3.8-linux-x86_64.egg/tvm/contrib/popen_pool.py”, line 260, in recv raise self._child_process_error() ChildProcessError: Subprocess terminated Done.
I am facing same error for resnet50-v2-7.onnx model.
Please help me to understand what is the issue.
