Dear TI Team
We are testing a custom segmentation model on TDA4VM board .
For Layer/s compatibility and accuracy check, we inferred the model first on the PC Emulation mode before inferring on the target. In PC Emulation mode, we are able to infer and generate the results successfully , but in target mode we are not able to generate the required output.
During the course of debugging , we are able to generate output until the layer "AveragePool_82 " in target and after that execution is "Stuck" in Conv_83 layer (Ref .Fig 1 - below for layer details ) .this blocks the generation of final layer output .
I have attached the model layer information where target inference is stuck and also import and inference configuration used .. Kindly help us to resolve the issue..
Fig 1: Layer at which processing is "Stuck"-
Import configuration -
modelType = 2
numParamBits = 16
numFeatureBits = 16
quantizationStyle = 3
inputNetFile = "XX.onnx"
outputNetFile = "XX.bin"
outputParamsFile = "XX_"
inWidth = 1024
inHeight = 1024
inNumChannels = 3
inFileFormat = 2
inDataFormat = 1
inElementType = 1
inDataNorm = 1
inMean = 123.675 116.28 103.53
inScale = 0.017124754 0.017507003 0.017429194
inData = "input.txt"
postProcType = 3
writeOutput = 2
debugTraceLevel = 1
writeTraceLevel = 3
Inference configuration -
inFileFormat = 2
postProcType = 3
numFrames = 1
netBinFile = XX.bin
ioConfigFile = XX.bin
inData = tinput.txt
outData = yy.bin
Versions used :-
SDK: ti-processor-sdk-rtos-j721e-evm-07_01_00_11
TVM version: REL.TIDL.J7.01.03.00.11
OS : Ubuntu 18.04
Thanks and regards
VasanthKumar.V.M
