Anurag 4nuragk

How to install CUDA / cuDNN / TensorRT on Ubuntu

Install NVIDIA drivers

Update & upgrade

sudo apt update && sudo apt upgrade

Remove previous NVIDIA installation

Steps to install Deepstream-6.1 on Ubuntu_20.04-LTS, Run YOLO and YOLO.py

***Needed Ubuntu-20 and nvidia driver 510

Step 1: Install Cuda 11.6

wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-ubuntu2004.pin
sudo mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-60

First do pip install flask Pillow in your venv :)

Quick Clean Cache

Open android studio Tools->Flutter->Clean
Go to File -> Invalidate Caches / Restart
Or open terminal run "flutter clean"
Remove pubspec.lock
Double check the Flutter SDK Path config correcty - https://tppr.me/qn6dP

Or open the terminal and try this script:

flutter clean

Kinetics Numeric/String labels

These are mapping files that go between class IDs to class names. These are generated from the training CSV files from each dataset by collecting the unique classes, sorting them, and then numbering them from 0 upwards.

	import requests as r
	import json
	from pprint import pprint

	# Images
	dir = 'https://github.com/ultralytics/yolov5/raw/master/data/images/'
	imgs = [dir + f for f in ('zidane.jpg', 'bus.jpg')] # batched list of images

	# Send images to endpoint
	res = r.post("http://localhost:9999/inference", data=json.dumps({'img_list': imgs}))

	# WARNING : This gist in the current form is a collection of command examples. Please exercise caution where mentioned.

	# Docker
	sudo apt-get update
	sudo apt-get remove docker docker-engine docker.io
	sudo apt install docker.io
	sudo systemctl start docker
	sudo systemctl enable docker
	docker --version

	#!/usr/bin/env python3
	import sys
	import os
	import cv2
	import gi
	import signal
	import threading

	gi.require_version('Gst', '1.0')
	from gi.repository import Gst, GObject

	#!/bin/bash

	# Sometimes you want to sleep until a specific time in a bash script. This is useful, for instance
	# in a docker container that does a single thing at a specific time on a regular interval, but does not want to be bothered
	# with cron or at. The -d option to date is VERY flexible for relative times.
	# See
	# https://www.gnu.org/software/coreutils/manual/html_node/Relative-items-in-date-strings.html#Relative-items-in-date-strings
	# For details
	# ALPINE USERS: You will need to install coreutils, as the built-in busybox date does not handle -d correctly.

	#!/bin/bash

	### steps ####
	# Verify the system has a cuda-capable gpu
	# Download and install the nvidia cuda toolkit and cudnn
	# Setup environmental variables
	# Verify the installation
	###

	### to verify your gpu is cuda enable check