convert inception_resnet_v1 to dlc failed, need help!
Join Date: 16 Mar 18
Posts: 3
Posted: Tue, 2018-05-08 01:35
hi!
I'am trying to convert inception_resnet_v1 network to dlc, but I got this error:
ERROR - Conversion failed: ElementWise resolver must implement broadcast method.
I think there may have operation not support by snpe, But I don't know which node or opreration cause this error,I need help!!!
I use snpe1.15.0, here is my operation:
cool@cool-System-Product-Name:~/SourceCode/snpe-1.15.0/bin/x86_64-linux-clang$ ./snpe-tensorflow-to-dlc --graph faceRecognize/sixth.pb -i input_tensor 112,112,3 --out_node embeddings --dlc faceModel/sixth.dlc
2018-05-08 16:27:21.491796: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2018-05-08 16:27:21.583136: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:895] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-05-08 16:27:21.583412: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1105] Found device 0 with properties:
name: GeForce GTX 1070 major: 6 minor: 1 memoryClockRate(GHz): 1.7845
pciBusID: 0000:01:00.0
totalMemory: 7.92GiB freeMemory: 7.83GiB
2018-05-08 16:27:21.583427: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1195] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0, compute capability: 6.1)
2018-05-08 16:27:44,665 - 123 - ERROR - Conversion failed: ElementWise resolver must implement broadcast method.