Command Used:
snpe-tensorflow-to-dlc --input_network /home/adas/testpb/saved_model/saved_model.pb --input_dim input_tensor 1,512,512,3 --out_node num_detections --out_node detection_classes --out_node detection_boxes --out_node detection_scores --output_path /home/adas/test.dlc
2021-05-10 17:23:27.161198: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0 2021-05-10 17:23:28.782960: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2021-05-10 17:23:28.783500: I tensorflow/compiler/jit/xla_gpu_device.cc:99] Not creating XLA devices, tf_xla_enable_xla_devices not set 2021-05-10 17:23:28.784295: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcuda.so.1 2021-05-10 17:23:28.813495: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2021-05-10 17:23:28.813845: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1720] Found device 0 with properties: pciBusID: 0000:01:00.0 name: Quadro M1200 computeCapability: 5.0 coreClock: 1.148GHz coreCount: 5 deviceMemorySize: 3.95GiB deviceMemoryBandwidth: 74.65GiB/s 2021-05-10 17:23:28.813883: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0 2021-05-10 17:23:28.816390: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublas.so.11 2021-05-10 17:23:28.816469: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublasLt.so.11 2021-05-10 17:23:28.817198: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcufft.so.10 2021-05-10 17:23:28.817411: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcurand.so.10 2021-05-10 17:23:28.817577: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'libcusolver.so.10'; dlerror: libcusolver.so.10: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/cuda-11.1/lib64:/usr/local/cuda-11.1/lib64:/home/saini/workspace/snpe/snpe-1.49.0.2587/lib/x86_64-linux-clang:/home/saini/workspace/snpe/snpe-1.49.0.2587/lib/x86_64-linux-clang:/usr/local/cuda-11.1/lib64:/usr/local/cuda-11.1/lib64:/usr/lib/x86_64-linux-gnu/:/usr/lib/x86_64-linux-gnu/ 2021-05-10 17:23:28.818134: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusparse.so.11 2021-05-10 17:23:28.818275: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudnn.so.8 2021-05-10 17:23:28.818286: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1757] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. Skipping registering GPU devices... 2021-05-10 17:23:28.851764: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1261] Device interconnect StreamExecutor with strength 1 edge matrix: 2021-05-10 17:23:28.851817: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1267] 0 2021-05-10 17:23:28.851840: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1280] 0: N 2021-05-10 17:23:28,881 - 183 - ERROR - Conversion FAILED! Traceback (most recent call last): File "/home/adas/workspace/snpe/snpe-1.49.0.2587/bin/x86_64-linux-clang/snpe-tensorflow-to-dlc", line 68, in main() File "/home/adas/workspace/snpe/snpe-1.49.0.2587/bin/x86_64-linux-clang/snpe-tensorflow-to-dlc", line 64, in main raise e File "/home/adas/workspace/snpe/snpe-1.49.0.2587/bin/x86_64-linux-clang/snpe-tensorflow-to-dlc", line 48, in main converter = TFConverterFrontend(session, args) File "/home/adas/workspace/snpe/snpe-1.49.0.2587/lib/python/qti/aisw/converters/tensorflow/tf_to_ir.py", line 320, in __init__ saved_model_tag, saved_model_signature_key) File "/home/adas/workspace/snpe/snpe-1.49.0.2587/lib/python/qti/aisw/converters/tensorflow/loader.py", line 60, in __init__ saved_model_tag, saved_model_signature_key) File "/home/adas/workspace/snpe/snpe-1.49.0.2587/lib/python/qti/aisw/converters/tensorflow/loader.py", line 155, in load graph_def = self.__import_graph(graph_path, session, out_node_names, saved_model_tag, saved_model_signature_key) File "/home/adas/workspace/snpe/snpe-1.49.0.2587/lib/python/qti/aisw/converters/tensorflow/loader.py", line 212, in __import_graph graph_def = cls.__import_from_frozen_graph(graph_path) File "/home/adas/workspace/snpe/snpe-1.49.0.2587/lib/python/qti/aisw/converters/tensorflow/loader.py", line 262, in __import_from_frozen_graph graph_def.ParseFromString(f.read()) google.protobuf.message.DecodeError: Error parsing message