iaverypadberg

ffmpeg -i bg_3.mp4 -vb 30M -filter:v "crop=320:320:200:600, fps=3" frames/office_2_%04d.jpg

iaverypadberg

from sqlite3 import adapt
import numpy as np



from PIL import Image
import glob
import cv2
import numpy as np
import tflite_runtime.interpreter as tflite 

iaverypadberg

Building a background dataset from scratch

For object detection models with very few classes (<5) and no background images, most models will struggle with false positives. The model is only learning what the thing is that it needs to detect. This is only half the problem.

The other half is that the model needs to learn what not to detect. Heres where background images come in.

Aquire background images

The easiest way to get some background images is to take a video with a smart phone and chop it into individual frames.

iaverypadberg

import org.jetbrains.kotlinx.multik.api.toNDArray
import org.jetbrains.kotlinx.multik.ndarray.data.get
import org.jetbrains.kotlinx.multik.ndarray.data.slice
import org.jetbrains.kotlinx.multik.ndarray.operations.last
import org.jetbrains.kotlinx.multik.ndarray.operations.minus
import org.jetbrains.kotlinx.multik.ndarray.operations.plus
import org.jetbrains.kotlinx.multik.ndarray.operations.toList

// Filter out all items
val startList = listOf(Pair(1,.2),Pair(2,.4),Pair(3,.6),Pair(4,.3))

iaverypadberg

private fun argsort(needsSorting : Array<Int>){
    val theRange = IntRange(0,needsSorting.size-1)
    val idxs = theRange.toList().sortedBy { needsSorting[it] }
}

iaverypadberg

#from importlib.metadata import files
import xml.etree.ElementTree as ET
import glob


# Sort through a dataset's xml files and print out file names that contain labels which are invalid
valid_labels = ["frodo","baggins"]

# Loop through all xml files
files = glob.glob('/home/isaac/Desktop/work_area/working_on/*.xml')

iaverypadberg

import random
from re import S
import xml.etree.ElementTree as ET
from glob import glob
import cv2

input_dir ='/home/isaac/Desktop/work_area/working_on/'

files = glob(input_dir+'*.png')
# For each file with a .png extension

iaverypadberg

Configuring a tensorflow environment to work with gpu's is really annoying. Thankfully, conda & pipmake it a lot less annoying.

Here are the core dependencies for getting this to work.

• cudatoolkit=11.6.0
• cudnn=8.2.1.32
• tensorflow=2.7.0
• tensorflow-gpu=2.7.0
• tensorflow-io=0.25.0
• python=3.9

iaverypadberg

import xml.etree.ElementTree as ET
from glob import glob
labels = [
"labels",
"to",
"be",
"removed"]
files = glob('directory/with/xml/files/*.xml')

for file in files:

iaverypadberg

from re import T
import os
import subprocess

from glob import glob

import xml.etree.ElementTree as ET
labels = [
"some",
"labels",