[ WARN:0] global /opt/opencv/modules/videoio/src/cap_gstreamer.cpp (935)

[KDAgusin]

Hello, good day! I am building a project using poseNet for our Hand Gesture Estimation project with custom hand gesture dataset. I followed how you train your dataset on imagenet classification but applied it towards my posenet. I mounted host folder called "Code" towards the jetson-inference docker and placed all my dataset on the jetson-inference/python/training/classification folder.

I trained them exactly how an imagenet model was trained but instead of calling the imagenet model on my program, I called and organized it for my posenet. I really not quite sure on where I went wrong. My program works well with imagenet but doesn't does it job for the posenet.

Here are my setup specification:
jetson nano 2gb devkit
jetpack 4.6.4
torch (1.10.0)
torchaudio (0.10.0+d2634d8)
torchvision (0.11.0a0+fa347eb)
Python: 3.6.9
OpenCV: 4.5.5 with CUDA: Yes

Below I'll providing my code and the error output it provides:

MY CODE:
`import cv2
import numpy as np
import jetson_inference

from jetson_inference import poseNet
from jetson_utils import Log, cudaFromNumpy, cudaToNumpy

net = poseNet(argv=[
'--model=/jetson-inference/python/training/classification/models/dataset/resnet18.onnx',
'--colors=/jetson-inference/data/networks/Pose-ResNet18-Hand/colors.txt',
'--input_blob=input_0',
'--output_cmap=output_0',
'--output_paf=output_0',
'--labels=/jetson-inference/python/training/classification/models/dataset/labels.txt',
'--topology=/jetson-inference/data/networks/Pose-ResNet18-Hand/hand_pose.json',
])

cap = cv2.VideoCapture(0) # sulay -1 kon csi imo cam

#image size
width = 640
height = 480

#setting the capture image resolution
cap.set(3,width)
cap.set(4,height)

process frames until EOS or the user exits

while(cap.isOpened()):
ret, img = cap.read()
#img = cv2.rotate(img,cv2.ROTATE_180)
#change image format to cuda memory
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = cv2.cvtColor(img, cv2.COLOR_RGB2RGBA).astype(np.float32)
img = cudaFromNumpy(img)

# perform pose estimation (with overlay)
poses = net.Process(img, overlay="links,keypoints")


# print the pose results
print("detected {:d} objects in image".format(len(poses)))

for pose in poses:
    print(pose)
    print(pose.Keypoints)
    print('Links', pose.Links)

img = cudaToNumpy(img, width, height, 3) #change to 3 kon hinay ang pose est 
img = cv2.cvtColor(img, cv2.COLOR_RGBA2RGB).astype(np.uint8)
img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)

         
cv2.imshow("Pose Hand ",img)

key = cv2.waitKey(1) & 0xFF

if key != -1:  # Check if a key was pressed at all
    if key == ord('q'):
        break

cap.release()
cv2.destroyAllWindows()
`

OUTPUT FROM CMD LINE:

root@ubuntu:/Code# python3 gesture_detection.py

poseNet -- loading pose estimation model from:
-- model /jetson-inference/python/training/classification/models/dataset/resnet18.onnx
-- topology /jetson-inference/data/networks/Pose-ResNet18-Hand/hand_pose.json
-- colors /jetson-inference/data/networks/Pose-ResNet18-Hand/colors.txt
-- input_blob 'input_0'
-- output_cmap 'output_0'
-- output_paf 'output_0'
-- threshold 0.150000
-- batch_size 1

[TRT] topology -- keypoint 0 palm
[TRT] topology -- keypoint 1 thumb_1
[TRT] topology -- keypoint 2 thumb_2
[TRT] topology -- keypoint 3 thumb_3
[TRT] topology -- keypoint 4 thumb_4
[TRT] topology -- keypoint 5 index_finger_1
[TRT] topology -- keypoint 6 index_finger_2
[TRT] topology -- keypoint 7 index_finger_3
[TRT] topology -- keypoint 8 index_finger_4
[TRT] topology -- keypoint 9 middle_finger_1
[TRT] topology -- keypoint 10 middle_finger_2
[TRT] topology -- keypoint 11 middle_finger_3
[TRT] topology -- keypoint 12 middle_finger_4
[TRT] topology -- keypoint 13 ring_finger_1
[TRT] topology -- keypoint 14 ring_finger_2
[TRT] topology -- keypoint 15 ring_finger_3
[TRT] topology -- keypoint 16 ring_finger_4
[TRT] topology -- keypoint 17 baby_finger_1
[TRT] topology -- keypoint 18 baby_finger_2
[TRT] topology -- keypoint 19 baby_finger_3
[TRT] topology -- keypoint 20 baby_finger_4
[TRT] topology -- skeleton link 0 1 5
[TRT] topology -- skeleton link 1 1 9
[TRT] topology -- skeleton link 2 1 13
[TRT] topology -- skeleton link 3 1 17
[TRT] topology -- skeleton link 4 1 21
[TRT] topology -- skeleton link 5 2 3
[TRT] topology -- skeleton link 6 3 4
[TRT] topology -- skeleton link 7 4 5
[TRT] topology -- skeleton link 8 6 7
[TRT] topology -- skeleton link 9 7 8
[TRT] topology -- skeleton link 10 8 9
[TRT] topology -- skeleton link 11 10 11
[TRT] topology -- skeleton link 12 11 12
[TRT] topology -- skeleton link 13 12 13
[TRT] topology -- skeleton link 14 14 15
[TRT] topology -- skeleton link 15 15 16
[TRT] topology -- skeleton link 16 16 17
[TRT] topology -- skeleton link 17 18 19
[TRT] topology -- skeleton link 18 19 20
[TRT] topology -- skeleton link 19 20 21
[TRT] poseNet -- keypoint 00 'palm' color 200 200 200 255
[TRT] poseNet -- keypoint 01 'thumb_1' color 215 0 0 255
[TRT] poseNet -- keypoint 02 'thumb_2' color 194 0 0 255
[TRT] poseNet -- keypoint 03 'thumb_3' color 172 0 0 255
[TRT] poseNet -- keypoint 04 'thumb_4' color 150 0 0 255
[TRT] poseNet -- keypoint 05 'index_finger_1' color 221 255 48 255
[TRT] poseNet -- keypoint 06 'index_finger_2' color 200 230 43 255
[TRT] poseNet -- keypoint 07 'index_finger_3' color 175 200 35 255
[TRT] poseNet -- keypoint 08 'index_finger_4' color 155 180 31 255
[TRT] poseNet -- keypoint 09 'middle_finger_1' color 152 254 111 255
[TRT] poseNet -- keypoint 10 'middle_finger_2' color 135 228 101 255
[TRT] poseNet -- keypoint 11 'middle_finger_3' color 120 203 89 255
[TRT] poseNet -- keypoint 12 'middle_finger_4' color 105 180 78 255
[TRT] poseNet -- keypoint 13 'ring_finger_1' color 64 103 252 255
[TRT] poseNet -- keypoint 14 'ring_finger_2' color 57 93 227 255
[TRT] poseNet -- keypoint 15 'ring_finger_3' color 51 83 202 255
[TRT] poseNet -- keypoint 16 'ring_finger_4' color 43 72 177 255
[TRT] poseNet -- keypoint 17 'baby_finger_1' color 173 18 252 255
[TRT] poseNet -- keypoint 18 'baby_finger_2' color 156 15 227 255
[TRT] poseNet -- keypoint 19 'baby_finger_3' color 138 12 201 255
[TRT] poseNet -- keypoint 20 'baby_finger_4' color 121 9 177 255
[TRT] poseNet -- loaded 21 class colors
[TRT] TensorRT version 8.2.1
[TRT] loading NVIDIA plugins...
[TRT] Registered plugin creator - ::GridAnchor_TRT version 1
[TRT] Registered plugin creator - ::GridAnchorRect_TRT version 1
[TRT] Registered plugin creator - ::NMS_TRT version 1
[TRT] Registered plugin creator - ::Reorg_TRT version 1
[TRT] Registered plugin creator - ::Region_TRT version 1
[TRT] Registered plugin creator - ::Clip_TRT version 1
[TRT] Registered plugin creator - ::LReLU_TRT version 1
[TRT] Registered plugin creator - ::PriorBox_TRT version 1
[TRT] Registered plugin creator - ::Normalize_TRT version 1
[TRT] Registered plugin creator - ::ScatterND version 1
[TRT] Registered plugin creator - ::RPROI_TRT version 1
[TRT] Registered plugin creator - ::BatchedNMS_TRT version 1
[TRT] Registered plugin creator - ::BatchedNMSDynamic_TRT version 1
[TRT] Could not register plugin creator - ::FlattenConcat_TRT version 1
[TRT] Registered plugin creator - ::CropAndResize version 1
[TRT] Registered plugin creator - ::DetectionLayer_TRT version 1
[TRT] Registered plugin creator - ::EfficientNMS_TRT version 1
[TRT] Registered plugin creator - ::EfficientNMS_ONNX_TRT version 1
[TRT] Registered plugin creator - ::EfficientNMS_TFTRT_TRT version 1
[TRT] Registered plugin creator - ::Proposal version 1
[TRT] Registered plugin creator - ::ProposalLayer_TRT version 1
[TRT] Registered plugin creator - ::PyramidROIAlign_TRT version 1
[TRT] Registered plugin creator - ::ResizeNearest_TRT version 1
[TRT] Registered plugin creator - ::Split version 1
[TRT] Registered plugin creator - ::SpecialSlice_TRT version 1
[TRT] Registered plugin creator - ::InstanceNormalization_TRT version 1
[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] [MemUsageChange] Init CUDA: CPU +224, GPU +0, now: CPU 260, GPU 3494 (MiB)
[TRT] [MemUsageSnapshot] Begin constructing builder kernel library: CPU 260 MiB, GPU 3494 MiB
[TRT] [MemUsageSnapshot] End constructing builder kernel library: CPU 290 MiB, GPU 3523 MiB
[TRT] native precisions detected for GPU: FP32, FP16
[TRT] selecting fastest native precision for GPU: FP16
[TRT] found engine cache file /jetson-inference/python/training/classification/models/dataset/resnet18.onnx.1.1.8201.GPU.FP16.engine
[TRT] found model checksum /jetson-inference/python/training/classification/models/dataset/resnet18.onnx.sha256sum
[TRT] echo "$(cat /jetson-inference/python/training/classification/models/dataset/resnet18.onnx.sha256sum) /jetson-inference/python/training/classification/models/dataset/resnet18.onnx" | sha256sum --check --status
[TRT] model matched checksum /jetson-inference/python/training/classification/models/dataset/resnet18.onnx.sha256sum
[TRT] loading network plan from engine cache... /jetson-inference/python/training/classification/models/dataset/resnet18.onnx.1.1.8201.GPU.FP16.engine
[TRT] device GPU, loaded /jetson-inference/python/training/classification/models/dataset/resnet18.onnx
[TRT] [MemUsageChange] Init CUDA: CPU +0, GPU +0, now: CPU 307, GPU 3569 (MiB)
[TRT] Loaded engine size: 45 MiB
[TRT] Using cublas as a tactic source
[TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +158, GPU -7, now: CPU 465, GPU 3562 (MiB)
[TRT] Using cuDNN as a tactic source
[TRT] [MemUsageChange] Init cuDNN: CPU +240, GPU +17, now: CPU 705, GPU 3579 (MiB)
[TRT] Deserialization required 3770659 microseconds.
[TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +45, now: CPU 0, GPU 45 (MiB)
[TRT] Using cublas as a tactic source
[TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +0, now: CPU 705, GPU 3579 (MiB)
[TRT] Using cuDNN as a tactic source
[TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 705, GPU 3579 (MiB)
[TRT] Total per-runner device persistent memory is 42887680
[TRT] Total per-runner host persistent memory is 24224
[TRT] Allocated activation device memory of size 2408448
[TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +43, now: CPU 0, GPU 88 (MiB)
[TRT]
[TRT] CUDA engine context initialized on device GPU:
[TRT] -- layers 27
[TRT] -- maxBatchSize 1
[TRT] -- deviceMemory 2408448
[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 #2 224
-- dim #3 224
[TRT] binding 1
-- index 1
-- name 'output_0'
-- type FP32
-- in/out OUTPUT
-- # dims 2
-- dim #0 1
-- dim #1 3
[TRT]
[TRT] binding to input 0 input_0 binding index: 0
[TRT] binding to input 0 input_0 dims (b=1 c=3 h=224 w=224) size=602112
[TRT] binding to output 0 output_0 binding index: 1
[TRT] binding to output 0 output_0 dims (b=1 c=3 h=1 w=1) size=12
[TRT] binding to output 1 output_0 binding index: 1
[TRT] binding to output 1 output_0 dims (b=1 c=3 h=1 w=1) size=12
[TRT]
[TRT] device GPU, /jetson-inference/python/training/classification/models/dataset/resnet18.onnx initialized.
[ WARN:0] global /opt/opencv/modules/videoio/src/cap_gstreamer.cpp (935) open OpenCV | GStreamer warning: Cannot query video position: status=0, value=-1, duration=-1
Segmentation fault (core dumped)