Failed to run impulse Cannot find any webcams

[wudiAg]

I am using Raspberry Pi 4b and the camera is a CSI camera module. When running OpenCV, the camera image can be viewed normally, proving that the camera is not damaged. But how to solve the following problem when connecting to edge pulse?
api@raspberrypi :~$edge implose Linux runner
Edge Impulse Linux runner v1.4.8
[RUN] Already have model/home/api/ei-linux-runner/models/318877/v4/model.eim not downloading
[RUN] Starting the image classifier for cqut/zhonghe (v4)
[RUN] Parameters image size 96x96 px (3 channels) classes ['face ‘,’ mask ‘,’ nose ']
[GST] Checking for/etc/os release
[RUN] Failed to run impulse Cannot find any webcams

[shawn_edgeimpulse]

Hi @wudiAg,

This is likely an issue with the Raspberry Pi drivers and/or new camera support. Please see the following threads for more information:

Raspberry Pi 3 Cannot find any webcams while classification

I am running this code: #!/usr/bin/env python import cv2 import os import sys, getopt import signal import time from edge_impulse_linux.image import ImageImpulseRunner import RPi.GPIO as GPIO from hx711 import HX711 import requests import json from requests.structures import CaseInsensitiveDict runner = None show_camera = True c_value = 0 flag = 0 ratio = 218.0548780487805 id_product = 1 list_label = [] list_weight = [] count = 0 final_weight = 0 taken = 0 a = ‘Apple’ b…

Cannot find any webcams when running classify.py

Question/Issue: I wanna run my model locally on my Raspberry Pi 3B and a Raspberry Pi Camera Module V2. When I run edge-impulse-linux or edge-impulse-linux-runner the camera is detected and it works perfectly fine. However, when I try to run the classify.py example it returns this: MODEL: /home/pi/linux-sdk-python/examples/image/models/FOMO-int8.eim Loaded runner for "Benjamin / Real-Time Object Tracking for Autonomous UAVs" Looking for a camera in port 0: Looking for a camera in port 1: [ WAR…

Exception: Cannot find any webcams on Raspberry Camera module V3

I am attempting to execute the local model on a Raspberry Pi 4 and a Raspberry Pi Camera Module V3. The camera is functioning correctly when used with edge-impulse-linux and edge-impulse-runner. However, upon running classify.py from the Linux Python SDK, I encountered this exception.(Tried by both enabling and disabling the legacy camera with proper reboot) MODEL: /home/pi/modelfile.eim Loaded runner for "Nik / Bill_New" Looking for a camera in port 0: Looking for a camera in port 1: [ WARN:0@…

[nicosandller]

@wudiAg I had the same error and same setup I believe and I solved it by changing the permissions for video:

sudo usermod -a -G video $USER

and rebooting.