Description
I’d like to turn my TPN network to TensorRT model, and make it successfully. However, when I serialize it, it reported the following error,
"terminate called after throwing an instance of ‘nvinfer1::AssertionFailure’
what(): std::exception
Aborted (core dumped)
It occured in this part of code:
IConvolutionLayer* branch0 = network->addConvolutionNd(*branch0a->getOutput(0), 256, Dims3{ 3,1,1 }, weightMap[“necks.temporal_modulation_ops.0.conv.weight”], emptywts);
branch0->setNbGroups(32);
branch0->setStrideNd(Dims3{ 1,1,1 });
branch0->setPaddingNd(Dims3{ 1,0,0 });
assert(branch0);
But before this layer, I have the same 3d convolution and batchnorm, and it has normal output. Also, this layer’s weight is not 0. Could anyone find out what happened?
Blockquote
Environment
TensorRT Version:
GPU Type:
Nvidia Driver Version:
CUDA Version:
CUDNN Version:
Operating System + Version:
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):
Relevant Files
Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)
Steps To Reproduce
Please include:
- Exact steps/commands to build your repro
- Exact steps/commands to run your repro
- Full traceback of errors encountered