j-kim
October 18, 2018, 7:59am
1
Hi.
Recently, TensorRT for Windows is released, so I’m testing TensorRT on Windows10.
I am using C++ CaffeParser to use TensorRT engine build from caffe model,
but the following error has come out.
Error location
engine = builder-> buildCudaEngine (* network);
Error
[2018-10-18 07: 45: 04 ERROR] c: \ p4sw \ sw \ gpgpu \ MachineLearning \ DIT \ release \ 5.0 \ builder \ cudnnBuilderUtils.cpp (255) - Cuda Error in nvinfer 1 :: cudnn :: findFastestTactic: 77
[2018-10-18 07: 45: 04 ERROR] c: \ p4sw \ sw \ gpgpu \ MachineLearning \ DIT \ release \ 5.0 \ engine \ runtime.cpp (30) - Cuda Error in nvinfer 1 :: `anonymous-namespace ’ :: DefaultAllocator :: free: 77
By the way Ubuntu handles it well with the same code.
Is there any solution?
My Environment:
Windows10 64-bit
Geforce 1080Ti
Nvidia Driver Version: 416.16
TensorRT 5RC for Windows
CUDA10, cuDNN7.3.1
NVES
October 18, 2018, 5:19pm
2
Hello,
it’d help us debug this if you can provide a small repro package that contains the source, model, and dataset that exhibits the symptom.
j-kim
October 24, 2018, 7:06am
3
Hi.
Thank you for reply.
I’m sorry. It was my mistake.
It was a misconfiguration of Caffe’s Deconvoution layer.
Thanks.
Hi,
I have the same problem. Could you explain your solution in a little more detail ?
Thank you very much.
j-kim
December 13, 2018, 5:17am
5
Hello.
I converted onnx model to caffe model using onnx2caffe below and used it for TensorRT.
Set caffe’s deconvolution setting to “bilinear”
I solved it when I did it.
Thanks.
Hi,
My caffe model’s deconvolution’s type is “bilinear”,but it have this problem.
this is my layer:
layer {
name: "upscore"
type: "Deconvolution"
bottom: "score_fr"
top: "upscore"
param {
lr_mult: 0.0
}
convolution_param {
num_output: 21
bias_term: false
kernel_size: 63
group: 21
stride: 32
weight_filler {
type: "bilinear"
}
}
}
e…I don’t know what to do. It feels like TENSORRT made this mistake.
j-kim
December 13, 2018, 6:10am
7
Hi.
I set Deconvolution parameters as follows.
factor = int(node.attrs["height_scale"])
node_name = node.name
input_name = str(node.inputs[0])
output_name = str(node.outputs[0])
channels = graph.channel_dims[input_name]
layer = myf("Deconvolution", node_name, [input_name], [output_name],
convolution_param=dict(
num_output=channels,
kernel_size= (2 * factor - factor % 2),
stride=factor,
pad=int(np.ceil((factor - 1) / 2.)),
group=channels,
bias_term=False,
weight_filler=dict(type="bilinear")
),
param=dict(
lr_mult=0,
decay_mult=0,
))
Please check.
Thanks.