Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Peoplenet model is erroring #1876

Open
muemajk opened this issue Jul 13, 2024 · 0 comments
Open

Peoplenet model is erroring #1876

muemajk opened this issue Jul 13, 2024 · 0 comments

Comments

@muemajk
Copy link

muemajk commented Jul 13, 2024

previous my custom mydetections.py script worked, infact other devices currently running a cloned jetson-inference(cloned months ago) also work but now as i try to clone and run the jetson-inference on a new machine, i get the error indicated below
CODE:
import os
import sys
import argparse
import time
import datetime
import threading
import pygame
import signal
import logging
import subprocess

from dotenv import load_dotenv
from websocket_server import websocket_server
from audio_manager import AudioManager

from jetson_inference import detectNet
from jetson_utils import videoSource, videoOutput, Log

load_dotenv()

Initialize Pygame Mixer for audio playback

pygame.mixer.init()

logging.basicConfig(filename='timestamped_my_detections_log.log', level=logging.INFO,
format='%(asctime)s:%(levelname)s:%(message)s')

parse the command line

parser = argparse.ArgumentParser(description="Locate objects in a live camera stream using an object detection DNN.",
formatter_class=argparse.RawTextHelpFormatter,
epilog=detectNet.Usage() + videoSource.Usage() + videoOutput.Usage() + Log.Usage())

parser.add_argument("input", type=str, default="/dev/video0", nargs='?', help="URI of the input stream")
parser.add_argument("output", type=str, default="webrtc://@:8554/output", nargs='?', help="URI of the output stream")
parser.add_argument("--network", type=str, default="peoplenet", help="pre-trained model to load (see below for options)")
parser.add_argument("--overlay", type=str, default="box,labels,conf", help="detection overlay flags (e.g. --overlay=box,labels,conf)\nvalid combinations are: 'box', 'labels', 'conf', 'none'")
parser.add_argument("--threshold", type=float, default=0.25, help="minimum detection threshold to use")

try:
args = parser.parse_known_args()[0]
except:
print("")
parser.print_help()
sys.exit(0)

create video sources and outputs

input = videoSource(args.input, argv=sys.argv)
output = videoOutput(args.output, argv=sys.argv)

ERROR:

2024-07-13 01:59:41 : Traceback (most recent call last):
2024-07-13 01:59:41 : File "/home/checkout/POS/jetson-inference/mydetections.py", line 229, in
2024-07-13 01:59:41 : net = detectNet(args.network, sys.argv, args.threshold)
2024-07-13 01:59:41 : Exception: jetson.inference -- detectNet failed to load network
2024-07-13 02:11:08 : �[0;31m[TRT] Could not register plugin creator - ::FlattenConcat_TRT version 1
2024-07-13 02:11:08 : �[0m�[0;31m[TRT] 1: [runtime.cpp::parsePlan::314] Error Code 1: Serialization (Serialization assertion plan->header.magicTag == rt::kPLAN_MAGIC_TAG failed.)
2024-07-13 02:11:08 : �[0m�[0;31m[TRT] device GPU, failed to create CUDA engine
2024-07-13 02:11:08 : �[0m�[0;31m[TRT] failed to load /usr/local/bin/networks/peoplenet_deployable_quantized_v2.6.1/resnet34_peoplenet_int8.etlt.engine
2024-07-13 02:11:08 : �[0m�[0;31m[TRT] detectNet -- failed to initialize.
2024-07-13 02:11:08 : �[0mpygame 2.6.0 (SDL 2.28.4, Python 3.10.12)
2024-07-13 02:11:08 : Hello from the pygame community. https://www.pygame.org/contribute.html
2024-07-13 02:11:08 : STORE ID IS 110
2024-07-13 02:11:08 : Starting RabbitMQ message consumption
2024-07-13 02:11:08 : Traceback (most recent call last):
2024-07-13 02:11:08 : File "/home/checkout/POS/jetson-inference/mydetections.py", line 229, in
2024-07-13 02:11:08 : net = detectNet(args.network, sys.argv, args.threshold)
2024-07-13 02:11:08 : Exception: jetson.inference -- detectNet failed to load network

Can anyone help me get over this error

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant