Custom model ERROR on segmentation

[jsshin98]

Hi, Dusty.

I retrained fcn_resnet18 using your pytorch-segmentation project page. I successfully exported onnx file and tried to run the model on live streaming. However, I am getting this error : cannot find binding of given name : data.

How can I fix this error?:( I already checked that it worked fine on your provided pretrained onnx file.

I simply type ./segnet.py --network=<MYNETWORKPATH> /dev/video0 Here is my log

`[TRT] device GPU, loaded /jetson-inference/data/networks/FCN-ResNet18-Pascal-VOC-320x320/fcn_resnet18_base.onnx [TRT] [MemUsageChange] Init CUDA: CPU +0, GPU +0, now: CPU 376, GPU 7871 (MiB) [TRT] Loaded engine size: 23 MiB [TRT] Deserialization required 10760 microseconds. [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +22, now: CPU 0, GPU 22 (MiB) [TRT] Total per-runner device persistent memory is 15872 [TRT] Total per-runner host persistent memory is 50496 [TRT] Allocated activation device memory of size 4915200 [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +5, now: CPU 0, GPU 27 (MiB) [TRT]
[TRT] CUDA engine context initialized on device GPU: [TRT] -- layers 25 [TRT] -- maxBatchSize 1 [TRT] -- deviceMemory 4915200 [TRT] -- bindings 2 [TRT] binding 0 -- index 0 -- name 'input_0' -- type FP32 -- in/out INPUT -- # dims 4 -- dim #0 1 -- dim #1 3 -- dim #2 320 -- dim #3 320 [TRT] binding 1 -- index 1 -- name 'output_0' -- type FP32 -- in/out OUTPUT -- # dims 4 -- dim #0 1 -- dim #1 21 -- dim #2 10 -- dim #3 10 [TRT]
[TRT] 3: Cannot find binding of given name: data [TRT] failed to find requested input layer data in network [TRT] device GPU, failed to create resources for CUDA engine [TRT] failed to create TensorRT engine for /jetson-inference/data/networks/FCN-ResNet18-Pascal-VOC-320x320/fcn_resnet18_base.onnx, device GPU [TRT] segNet -- failed to load. jetson.inference -- segNet failed to load network Traceback (most recent call last): File "./segnet.py", line 56, in net = jetson.inference.segNet(opt.network, sys.argv) Exception: jetson.inference -- segNet failed to load network

[jsshin98]

I also put some arguments following other issues. ./segnet.py --network=/jetson-inference/data/networks/FCN-ResNet18-Pascal-VOC-320x320/fcn_resnet18_base.onnx --labels=/jetson-inference/data/networks/FCN-ResNet18-Pascal-VOC-320x320/classes.txt --input-blob=input_0 --output-cvg=scores --output-bbox=boxes /dev/video0

Then, I got other errors like this. [TRT] device GPU, loaded /jetson-inference/data/networks/FCN-ResNet18-Pascal-VOC-320x320/fcn_resnet18_base.onnx [TRT] [MemUsageChange] Init CUDA: CPU +0, GPU +0, now: CPU 376, GPU 8010 (MiB) [TRT] Loaded engine size: 23 MiB [TRT] Deserialization required 20075 microseconds. [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +22, now: CPU 0, GPU 22 (MiB) [TRT] Total per-runner device persistent memory is 15872 [TRT] Total per-runner host persistent memory is 50496 [TRT] Allocated activation device memory of size 4915200 [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +5, now: CPU 0, GPU 27 (MiB) [TRT]
[TRT] CUDA engine context initialized on device GPU: [TRT] -- layers 25 [TRT] -- maxBatchSize 1 [TRT] -- deviceMemory 4915200 [TRT] -- bindings 2 [TRT] binding 0 -- index 0 -- name 'input_0' -- type FP32 -- in/out INPUT -- # dims 4 -- dim #0 1 -- dim #1 3 -- dim #2 320 -- dim #3 320 [TRT] binding 1 -- index 1 -- name 'output_0' -- type FP32 -- in/out OUTPUT -- # dims 4 -- dim #0 1 -- dim #1 21 -- dim #2 10 -- dim #3 10 [TRT]
[TRT] binding to input 0 input_0 binding index: 0 [TRT] binding to input 0 input_0 dims (b=1 c=3 h=320 w=320) size=1228800 [TRT] 3: Cannot find binding of given name: score_fr_21classes [TRT] failed to find requested output layer score_fr_21classes in network [TRT] device GPU, failed to create resources for CUDA engine [TRT] failed to create TensorRT engine for /jetson-inference/data/networks/FCN-ResNet18-Pascal-VOC-320x320/fcn_resnet18_base.onnx, device GPU [TRT] segNet -- failed to load. jetson.inference -- segNet failed to load network

[jsshin98]

Oh I solved it by changing my command. Thanks for your wonderful code!

[dusty-nv]

Hi @jsshin98, thanks, yes I was going to recommend using --output-blob=output_0 instead.