search

Ghustwb / MobileNet-SSD-TensorRT

Accelerate mobileNet-ssd with tensorRT
188 stars 91 forks source link

Weights for layer conv0 doesn't exist #8

Closed ghost closed 5 years ago

ghost commented 5 years ago

I run your code in tx1, when run mobilenet.bin and find this error, how to debug this error

Ghustwb commented 5 years ago

Regenerating the cache file

ghost commented 5 years ago

[libprotobuf ERROR google/protobuf/io/coded_stream.cc:207] A protocol message was rejected because it was too big (more than 0 bytes). To increase the limit (or to disable these warnings), see CodedInputStream::SetTotalBytesLimit() in google/protobuf/io/coded_stream.h. Weights for layer conv0 doesn't exist CaffeParser: ERROR: Attempting to access NULL weights Weights for layer conv0 doesn't exist CaffeParser: ERROR: Attempting to access NULL weights Parameter check failed at: ../builder/Network.cpp::addConvolution::40, condition: kernelWeights.values != NULL error parsing layer type Convolution index 0 mobileNet: /home/nvidia/Desktop/MobileNet-SSD-TensorRT-master/tensorNet.cpp:105: bool TensorNet::caffeToTRTModel(const char, const char, const std::vector<std::__cxx11::basic_string >&, unsigned int, std::ostream&): Assertion `blobNameToTensor != nullptr' failed.

ghost commented 5 years ago

when I run your code and find this error, do you mean re run mobilenet.bin? I think maybe protobuf's problem but I find protobuf is newest version in tx1

itkt commented 5 years ago

I have this problem. How you solved it?