segmentation not working on TX2

15207127486 · October 18, 2019, 1:10pm

hello,
I get a error on the Jetson tx2 when trying to run an segmentation part of tutorial.
when I input :./segnet-console peds-001.jpg 001.jpg --model=networks/FCN-ResNet18-DeepScene-864x480/fcn_resnet18.onnx
error appears:
segNet – loading segmentation network model from:
– prototxt: (null)
– model: networks/FCN-ResNet18-DeepScene-864x480/fcn_resnet18.onnx
– labels: (null)
– colors: (null)
– input_blob ‘data’
– output_blob ‘score_fr_21classes’
– batch_size 1

[TRT] TensorRT version 5.0.6
[TRT] loading NVIDIA plugins…
[TRT] completed loading NVIDIA plugins.
[TRT] detected model format - ONNX (extension ‘.onnx’)
[TRT] desired precision specified for GPU: FASTEST
[TRT] requested fasted precision for device GPU without providing valid calibrator, disabling INT8
[TRT] native precisions detected for GPU: FP32, FP16
[TRT] selecting fastest native precision for GPU: FP16
[TRT] attempting to open engine cache file networks/FCN-ResNet18-DeepScene-864x480/fcn_resnet18.onnx.1.1.GPU.FP16.engine
[TRT] cache file not found, profiling network model on device GPU
[TRT] device GPU, loading /home/nvidia/kfr/DeepLearning/ImageRecognition/jetson-inference/build/aarch64/bin/ networks/FCN-ResNet18-DeepScene-864x480/fcn_resnet18.onnx

Input filename: networks/FCN-ResNet18-DeepScene-864x480/fcn_resnet18.onnx
ONNX IR version: 0.0.4
Opset version: 9
Producer name: pytorch
Producer version: 1.1
Domain:
Model version: 0
Doc string:

WARNING: ONNX model has a newer ir_version (0.0.4) than this parser was built against (0.0.3).
----- Parsing of ONNX model networks/FCN-ResNet18-DeepScene-864x480/fcn_resnet18.onnx is Done ----
[TRT] retrieved Input tensor “input_0”: 3x480x864
[TRT] device GPU, configuring CUDA engine
[TRT] device GPU, building FP16: ON
[TRT] device GPU, building INT8: OFF
[TRT] device GPU, building CUDA engine (this may take a few minutes the first time a network is loaded)
[TRT] device GPU, completed building CUDA engine
[TRT] network profiling complete, writing engine cache to networks/FCN-ResNet18-DeepScene-864x480/fcn_resnet18.onnx.1.1.GPU.FP16.engine
[TRT] device GPU, completed writing engine cache to networks/FCN-ResNet18-DeepScene-864x480/fcn_resnet18.onnx.1.1.GPU.FP16.engine
[TRT] device GPU, networks/FCN-ResNet18-DeepScene-864x480/fcn_resnet18.onnx loaded
[TRT] device GPU, CUDA engine context initialized with 2 bindings
[TRT] binding – index 0
– name ‘input_0’
– type FP32
– in/out INPUT
– # dims 3
– dim #0 3 (CHANNEL)
– dim #1 480 (SPATIAL)
– dim #2 864 (SPATIAL)
[TRT] binding – index 1
– name ‘output_0’
– type FP32
– in/out OUTPUT
– # dims 3
– dim #0 5 (CHANNEL)
– dim #1 15 (SPATIAL)
– dim #2 27 (SPATIAL)
[TRT] binding to input 0 data binding index: -1
[TRT] binding to input 0 data dims (b=1 c=0 h=0 w=0) size=0
[TRT] failed to alloc CUDA mapped memory for tensor input, 0 bytes
segNet – failed to initialize.
segnet-console: failed to initialize segnet

I appreciate any help out there.
Thanks.

dusty_nv · October 18, 2019, 2:31pm

Hi, since you specified the path to the model, you need to also specify the input and output layer names:

./segnet-console peds-001.jpg 001.jpg --model=networks/FCN-ResNet18-DeepScene-864x480/fcn_resnet18.onnx --input_blob=input_0 --output_blob=output_0

Or you can simply specify the shortcut to this model, “fcn-resnet18-deepscene-864x480”, and it will automatically know the layer names:

./segnet-console peds-001.jpg 001.jpg --model=fcn-resnet18-deepscene-864x480

See this table for the other shortcut names used with segnet, you don’t need to specify the path to the build-in models:
https://github.com/dusty-nv/jetson-inference/blob/master/docs/segnet-console-2.md#pre-trained-segmentation-models-available

15207127486 · October 19, 2019, 1:26am

hi,dusty_nv,When I try the second method：./segnet-console car1.jpeg car1resnet18_output.jpeg --network=fcn-resnet18-cityscapes-512x256 ，error appears:segnet-console: failed to initialize segnet
.
When I try the first method:./segnet-console peds-001.jpg 001.jpg --model=networks/FCN-ResNet18-MHP-640x360/fcn_resnet18.onnx --labels=networks/FCN-ResNet18-MHP-640x360/classes.txt --colors=networks/FCN-ResNet18-MHP-640x360/colors.txt --input_blob=input_0 --out_blob=output_0
He does not work either：segNet – loading segmentation network model from:
– prototxt: (null)
– model: networks/FCN-ResNet18-MHP-640x360/fcn_resnet18.onnx
– labels: networks/FCN-ResNet18-MHP-640x360/classes.txt
– colors: networks/FCN-ResNet18-MHP-640x360/colors.txt
– input_blob ‘input_0’
– output_blob ‘score_fr_21classes’
– batch_size 1

[TRT] TensorRT version 5.0.6
[TRT] loading NVIDIA plugins…
[TRT] completed loading NVIDIA plugins.
[TRT] detected model format - ONNX (extension ‘.onnx’)
[TRT] desired precision specified for GPU: FASTEST
[TRT] requested fasted precision for device GPU without providing valid calibrator, disabling INT8
[TRT] native precisions detected for GPU: FP32, FP16
[TRT] selecting fastest native precision for GPU: FP16
[TRT] attempting to open engine cache file networks/FCN-ResNet18-MHP-640x360/fcn_resnet18.onnx.1.1.GPU.FP16.engine
[TRT] cache file not found, profiling network model on device GPU
[TRT] device GPU, loading /home/nvidia/kfr/DeepLearning/ImageRecognition/jetson-inference/build/aarch64/bin/ networks/FCN-ResNet18-MHP-640x360/fcn_resnet18.onnx

Input filename: networks/FCN-ResNet18-MHP-640x360/fcn_resnet18.onnx
ONNX IR version: 0.0.4
Opset version: 9
Producer name: pytorch
Producer version: 1.1
Domain:
Model version: 0
Doc string:

WARNING: ONNX model has a newer ir_version (0.0.4) than this parser was built against (0.0.3).
----- Parsing of ONNX model networks/FCN-ResNet18-MHP-640x360/fcn_resnet18.onnx is Done ----
[TRT] retrieved Input tensor “input_0”: 3x360x640
[TRT] device GPU, configuring CUDA engine
[TRT] device GPU, building FP16: ON
[TRT] device GPU, building INT8: OFF
[TRT] device GPU, building CUDA engine (this may take a few minutes the first time a network is loaded)
[TRT] device GPU, completed building CUDA engine
[TRT] network profiling complete, writing engine cache to networks/FCN-ResNet18-MHP-640x360/fcn_resnet18.onnx.1.1.GPU.FP16.engine
[TRT] device GPU, completed writing engine cache to networks/FCN-ResNet18-MHP-640x360/fcn_resnet18.onnx.1.1.GPU.FP16.engine
[TRT] device GPU, networks/FCN-ResNet18-MHP-640x360/fcn_resnet18.onnx loaded
[TRT] device GPU, CUDA engine context initialized with 2 bindings
[TRT] binding – index 0
– name ‘input_0’
– type FP32
– in/out INPUT
– # dims 3
– dim #0 3 (CHANNEL)
– dim #1 360 (SPATIAL)
– dim #2 640 (SPATIAL)
[TRT] binding – index 1
– name ‘output_0’
– type FP32
– in/out OUTPUT
– # dims 3
– dim #0 21 (CHANNEL)
– dim #1 12 (SPATIAL)
– dim #2 20 (SPATIAL)
[TRT] binding to input 0 input_0 binding index: 0
[TRT] binding to input 0 input_0 dims (b=1 c=3 h=360 w=640) size=2764800
[TRT] binding to output 0 score_fr_21classes binding index: -1
[TRT] binding to output 0 score_fr_21classes dims (b=1 c=0 h=0 w=0) size=0
[TRT] failed to alloc CUDA mapped memory for tensor output, 0 bytes
segNet – failed to initialize.
segnet-console: failed to initialize segnet

All models are placed nvidia@nvidia:~/kfr/DeepLea total 166276
drwxr-xr-x 23 nvidia nvidia drwxr-xr-x 4 nvidia nvidia drwxr-xr-x 2 nvidia nvidia -rw-r–r-- 1 nvidia -rw-r–r-- 1 nvidia -rw-rw-r-- 1 nvidia nvidia -rw-r–r-- 1 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxrwxr-x 2 nvidia nvidia drwxr-xr-x 3 nvidia nvidia -rw-rw-r-- 1 nvidia -rw-r–r-- 1 nvidia drwxrwxr-x 2 nvidia nvidia drwxr-xr-x 3 nvidia nvidia drwxr-xr-x 2 nvidia nvidia -rw-r–r-- 1 nvidia nvidia -rw-r–r-- 1 nvidia nvidia -rw-r–r-- 1 nvidia nvidia inside the networks like this：
rning/ImageRecognition/jetson-inference/data/networks$ ll
4096 Oct 18 08:54 ./
4096 Sep 23 23:02 …/
4096 Oct 17 04:19 20191016-145253-52f9_epoch_30.0/
nvidia 53533754 Jun 18 13:57 bvlc_googlenet.caffemodel
nvidia 17797624 Oct 17 21:03 bvlc_googlenet.caffemodel.1.1.GPU.FP16.engine
159 Aug 16 14:44 classes.txt
229 Sep 4 15:18 colors.txt
4096 Oct 17 22:44 DetectNet-COCO-Airplane/
4096 Oct 14 23:43 DetectNet-COCO-Bottle/
4096 Oct 14 23:15 DetectNet-COCO-Dog/
4096 Sep 24 23:48 facenet-120/
4096 Oct 17 04:08 FCN-Alexnet-Aerial-FPV-720p/
4096 Oct 17 23:05 FCN-Alexnet-Cityscapes-HD/
4096 Oct 17 05:49 FCN-Alexnet-Cityscapes-SD/
4096 Oct 18 04:04 FCN-Alexnet-Pascal-VOC/
4096 Oct 17 23:16 FCN-Alexnet-SYNTHIA-Summer-HD/
4096 Sep 4 15:29 FCN-ResNet18-Cityscapes-1024x512/
4096 Oct 18 07:29 FCN-ResNet18-Cityscapes-2048x1024/
4096 Oct 18 21:18 FCN-ResNet18-Cityscapes-512x256/
4096 Sep 16 13:23 FCN-ResNet18-DeepScene-576x320/
4096 Oct 18 08:44 FCN-ResNet18-DeepScene-864x480/
4096 Oct 18 21:15 FCN-ResNet18-MHP-640x360/
4096 Oct 18 07:14 ‘FCN-ResNet18-MHP-640x360 (1)’/
nvidia 47137244 Aug 21 13:33 fcn_resnet18.onnx
nvidia 51577848 Oct 18 07:02 fcn_resnet18.onnx.1.1.GPU.FP16.engine
4096 Aug 30 14:44 FCN-ResNet18-SUN-RGBD-640x512/
4096 Oct 18 07:14 ‘FCN-ResNet18-SUN-RGBD-640x512 (1)’/
4096 Oct 17 21:11 GoogleNet/
35776 Jun 18 13:57 googlenet_noprob.prototxt
35861 Jun 18 13:57 googlenet.prototxt
31675 Jun 18 13:53 ilsvrc12_synset_words.txt

what I should do now?Thanks for your help.

15207127486 · October 19, 2019, 1:51am

when I input this:./segnet-console --model=fcn-resnet18-cityscapes peds-001.jpg output.jpg
Displayed on the screen：
segNet – loading segmentation network model from:
– prototxt: (null)
– model: fcn-resnet18-cityscapes
– labels: (null)
– colors: (null)
– input_blob ‘data’
– output_blob ‘score_fr_21classes’
– batch_size 1

[TRT] TensorRT version 5.0.6
[TRT] loading NVIDIA plugins…
[TRT] completed loading NVIDIA plugins.
[TRT] detected model format - custom (extension ‘.fcn-resnet18-cityscapes’)
[TRT] model format ‘custom’ not supported by jetson-inference
segNet – failed to initialize.
segnet-console: failed to initialize segnet

15207127486 · October 19, 2019, 10:51am

hi，dusty。I solved this problem by recompiling the project and the results look pretty good.
Thanks for your help.

dusty_nv · October 19, 2019, 2:38pm

OK thanks, glad you got it working. Just FYI, I noticed in the command you posted above you used --out-blob (when it should be --output-blob), so that is why it may not have been working at the time:

# --out_blob incorrect
./segnet-console peds-001.jpg 001.jpg --model=networks/FCN-ResNet18-MHP-640x360/fcn_resnet18.onnx --labels=networks/FCN-ResNet18-MHP-640x360/classes.txt --colors=networks/FCN-ResNet18-MHP-640x360/colors.txt --input_blob=input_0 --out_blob=output_0

# should have been --output_blob=output_0
./segnet-console peds-001.jpg 001.jpg --model=networks/FCN-ResNet18-MHP-640x360/fcn_resnet18.onnx --labels=networks/FCN-ResNet18-MHP-640x360/classes.txt --colors=networks/FCN-ResNet18-MHP-640x360/colors.txt --input_blob=input_0 --output_blob=output_0

Topic		Replies	Views
Jetson-inference segnet-console by uff, UffParser: Parser error: Invalid number of Dimensions 0 Jetson TX2	8	924	October 18, 2021
Jetson TX2 Tensorrt l4t-tensorflow NGC Segmentation fault at build trt graphconverterV2 Jetson TX2 tensorrt	4	471	May 17, 2023
Some PyTorch model with slicing operation fails on inference TensorRT tensorrt , pytorch , onnx , deepstream	2	1418	January 7, 2022
ONNX model with Jetson-Inference using GPU Jetson Xavier NX tensorrt , jetson-inference , onnx	38	5589	October 18, 2021
Segmentation fault with Multi-Label Classification for Image Tagging tutorial Jetson AGX Orin jetson-inference	2	15	December 9, 2024
the TensortRt server can`t run a pretrained model after converting from onnx to caffe2 TensorRT	7	1279	February 18, 2019
I do not get any performance improvement after using TensorRT provider for object detection model Jetson Nano tensorrt , onnx	7	1381	July 12, 2022
Detectnet-console failed to profile custom model on TX2 Jetson TX2	6	1014	October 18, 2021
Failed to load detectNet model Jetson Nano jetson-inference , jetson-nano	2	1124	October 6, 2022
How to build the objection detection framework SSD with tensorRT on tx2? Jetson TX2	96	21863	February 21, 2018

segmentation not working on TX2

Input filename: networks/FCN-ResNet18-DeepScene-864x480/fcn_resnet18.onnx ONNX IR version: 0.0.4 Opset version: 9 Producer name: pytorch Producer version: 1.1 Domain: Model version: 0 Doc string:

Input filename: networks/FCN-ResNet18-MHP-640x360/fcn_resnet18.onnx ONNX IR version: 0.0.4 Opset version: 9 Producer name: pytorch Producer version: 1.1 Domain: Model version: 0 Doc string:

Related topics

Input filename: networks/FCN-ResNet18-DeepScene-864x480/fcn_resnet18.onnx
ONNX IR version: 0.0.4
Opset version: 9
Producer name: pytorch
Producer version: 1.1
Domain:
Model version: 0
Doc string:

Input filename: networks/FCN-ResNet18-MHP-640x360/fcn_resnet18.onnx
ONNX IR version: 0.0.4
Opset version: 9
Producer name: pytorch
Producer version: 1.1
Domain:
Model version: 0
Doc string: