It doesn’t appear that Google AI pb file converts:
python3 -m tf2onnx.convert --input model-555139022817591296_tf-saved-model_2020-09-08T00_12_38.738Z_saved_model.pb --output model-555139022817591296_tf-saved-model_2020-09-08T00_12_38.738Z_saved_model.onnx
2020-09-09 01:10:05.757937: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.2
WARNING:tensorflow:Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them.
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tf2onnx/verbose_logging.py:76: The name tf.logging.set_verbosity is deprecated. Please use tf.compat.v1.logging.set_verbosity instead.
2020-09-09 01:10:13,493 - WARNING - From /usr/local/lib/python3.6/dist-packages/tf2onnx/verbose_logging.py:76: The name tf.logging.set_verbosity is deprecated. Please use tf.compat.v1.logging.set_verbosity instead.
2020-09-09 01:10:13.552905: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcuda.so.1
2020-09-09 01:10:13.562878: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:952] ARM64 does not support NUMA - returning NUMA node zero
2020-09-09 01:10:13.563061: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1634] Found device 0 with properties:
name: Xavier major: 7 minor: 2 memoryClockRate(GHz): 1.109
pciBusID: 0000:00:00.0
2020-09-09 01:10:13.563151: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.2
2020-09-09 01:10:13.643033: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10
2020-09-09 01:10:13.721577: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10
2020-09-09 01:10:13.833017: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10
2020-09-09 01:10:13.969823: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10
2020-09-09 01:10:14.050905: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10
2020-09-09 01:10:14.051776: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.8
2020-09-09 01:10:14.052726: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:952] ARM64 does not support NUMA - returning NUMA node zero
2020-09-09 01:10:14.053019: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:952] ARM64 does not support NUMA - returning NUMA node zero
2020-09-09 01:10:14.053120: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1762] Adding visible gpu devices: 0
2020-09-09 01:10:14.084200: W tensorflow/core/platform/profile_utils/cpu_utils.cc:98] Failed to find bogomips in /proc/cpuinfo; cannot determine CPU frequency
2020-09-09 01:10:14.086109: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0xf1d9b20 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-09-09 01:10:14.087209: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
2020-09-09 01:10:14.258334: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:952] ARM64 does not support NUMA - returning NUMA node zero
2020-09-09 01:10:14.260268: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x10817f20 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
2020-09-09 01:10:14.261386: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Xavier, Compute Capability 7.2
2020-09-09 01:10:14.262925: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:952] ARM64 does not support NUMA - returning NUMA node zero
2020-09-09 01:10:14.264119: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1634] Found device 0 with properties:
name: Xavier major: 7 minor: 2 memoryClockRate(GHz): 1.109
pciBusID: 0000:00:00.0
2020-09-09 01:10:14.264376: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.2
2020-09-09 01:10:14.264957: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10
2020-09-09 01:10:14.265051: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10
2020-09-09 01:10:14.265120: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10
2020-09-09 01:10:14.265186: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10
2020-09-09 01:10:14.265724: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10
2020-09-09 01:10:14.265818: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.8
2020-09-09 01:10:14.266055: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:952] ARM64 does not support NUMA - returning NUMA node zero
2020-09-09 01:10:14.266866: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:952] ARM64 does not support NUMA - returning NUMA node zero
2020-09-09 01:10:14.267550: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1762] Adding visible gpu devices: 0
2020-09-09 01:10:14.268168: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.2
2020-09-09 01:10:20.229699: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1175] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-09-09 01:10:20.229857: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1181] 0
2020-09-09 01:10:20.229925: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1194] 0: N
2020-09-09 01:10:20.230462: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:952] ARM64 does not support NUMA - returning NUMA node zero
2020-09-09 01:10:20.231777: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:952] ARM64 does not support NUMA - returning NUMA node zero
2020-09-09 01:10:20.232059: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1320] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4453 MB memory) -> physical GPU (device: 0, name: Xavier, pci bus id: 0000:00:00.0, compute capability: 7.2)
Traceback (most recent call last):
File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/usr/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/usr/local/lib/python3.6/dist-packages/tf2onnx/convert.py", line 171, in <module>
main()
File "/usr/local/lib/python3.6/dist-packages/tf2onnx/convert.py", line 125, in main
graph_def, inputs, outputs = tf_loader.from_graphdef(args.graphdef, args.inputs, args.outputs)
File "/usr/local/lib/python3.6/dist-packages/tf2onnx/tf_loader.py", line 147, in from_graphdef
graph_def.ParseFromString(f.read())
File "/usr/local/lib/python3.6/dist-packages/google/protobuf/message.py", line 199, in ParseFromString
return self.MergeFromString(serialized)
File "/usr/local/lib/python3.6/dist-packages/google/protobuf/internal/python_message.py", line 1134, in MergeFromString
if self._InternalParse(serialized, 0, length) != length:
File "/usr/local/lib/python3.6/dist-packages/google/protobuf/internal/python_message.py", line 1201, in InternalParse
pos = field_decoder(buffer, new_pos, end, self, field_dict)
File "/usr/local/lib/python3.6/dist-packages/google/protobuf/internal/decoder.py", line 738, in DecodeField
if value._InternalParse(buffer, pos, new_pos) != new_pos:
File "/usr/local/lib/python3.6/dist-packages/google/protobuf/internal/python_message.py", line 1201, in InternalParse
pos = field_decoder(buffer, new_pos, end, self, field_dict)
File "/usr/local/lib/python3.6/dist-packages/google/protobuf/internal/decoder.py", line 717, in DecodeRepeatedField
if value.add()._InternalParse(buffer, pos, new_pos) != new_pos:
File "/usr/local/lib/python3.6/dist-packages/google/protobuf/internal/python_message.py", line 1201, in InternalParse
pos = field_decoder(buffer, new_pos, end, self, field_dict)
File "/usr/local/lib/python3.6/dist-packages/google/protobuf/internal/decoder.py", line 872, in DecodeMap
if submsg._InternalParse(buffer, pos, new_pos) != new_pos:
File "/usr/local/lib/python3.6/dist-packages/google/protobuf/internal/python_message.py", line 1188, in InternalParse
buffer, new_pos, wire_type) # pylint: disable=protected-access
File "/usr/local/lib/python3.6/dist-packages/google/protobuf/internal/decoder.py", line 973, in _DecodeUnknownField
(data, pos) = _DecodeUnknownFieldSet(buffer, pos)
File "/usr/local/lib/python3.6/dist-packages/google/protobuf/internal/decoder.py", line 952, in _DecodeUnknownFieldSet
(data, pos) = _DecodeUnknownField(buffer, pos, wire_type)
File "/usr/local/lib/python3.6/dist-packages/google/protobuf/internal/decoder.py", line 977, in _DecodeUnknownField
raise _DecodeError('Wrong wire type in tag.')
google.protobuf.message.DecodeError: Wrong wire type in tag.