ZackAkil’s gists

ZackAkil / automl_IOD_label_extraction.py

Created August 27, 2024 16:03

This Python script automates the process of converting assisted labeled images stored in Google Cloud Storage into a labeled dataset suitable for training an AutoML object detection model. It extracts bounding box annotations from image metadata, structures them into the AutoML format,

	# Import necessary libraries
	import argparse # Command-line argument parsing
	import json # JSON handling

	# Google Cloud Storage library for interacting with buckets and objects
	from google.cloud import storage


	# Function to extract bucket name and folder from a Google Storage location
	def get_bucket_folder(location):

ZackAkil / app.py

Created June 14, 2023 07:30

Server

	from flask import Flask, send_from_directory

	app = Flask(__name__)

	@app.route('/')
	def index():
	return 'Hello, World!'

	@app.route('/<path:path>')
	def serve_files(path):

ZackAkil / appscript.gs

Last active December 2, 2022 11:54

Build a desicion tree from a spreadsheet.ipynb



	function onOpen() {
	var ui = SpreadsheetApp.getUi();

	ui.createMenu("🔮 Predictions for cell")
	.addItem('🌸 Iris', 'predict_on_row')
	.addToUi();
	}

ZackAkil / automl-edge-tflite-metadata.ipynb

Created November 7, 2022 12:22

automl-edge-tflite-metadata.ipynb

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

Sorry, this file is invalid so it cannot be displayed.

ZackAkil / pi-rgb-test.py

Created February 19, 2022 21:06

	#!/usr/bin/env python3
	# rpi_ws281x library strandtest example
	# Author: Tony DiCola ([email protected])
	#
	# Direct port of the Arduino NeoPixel library strandtest example. Showcases
	# various animations on a strip of NeoPixels.

	import time
	from rpi_ws281x import *
	import argparse

ZackAkil / cv_thumbnails.py

Created July 12, 2021 18:58

Using CV2 generate folders of thumbnails given a folder of videos.

	# given a folder of videos, generate thumbnails for each video and store them in a new folder structure

	# !pip install opencv-python
	# !sudo apt-get install ffmpeg libsm6 libxext6 -y

	import cv2
	import os
	from PIL import Image

ZackAkil / gs_folders_to_labels_file.py

Created July 12, 2021 11:43

Script to generate the labels csv file for AutoML Image Classification (Vertex AI) based on folder structure within google cloud storage

	from google.cloud import storage

	folder_location = 'YOUR GCS FOLDER LOCATION' # e.g automl-ui-dataset/x-ray-dataset

	parts = folder_location.split('/')
	bucket_name = parts[0]
	prefix = '/'.join(parts[1:]) if len(parts) > 1 else ''

	storage_client = storage.Client()
	blobs = storage_client.list_blobs(bucket_name, prefix=prefix)

ZackAkil / main.py

Last active May 20, 2021 17:29

Google Cloud Function code for Video Object Detection on Storage trigger.


	from google.cloud import videointelligence
	import time

	video_client = videointelligence.VideoIntelligenceServiceClient()

	OUTPUT_BUCKET = 'gs://YOUR OUTPUT BUCKET NAME/'

	features = [
	videointelligence.Feature.OBJECT_TRACKING

ZackAkil / script.py

Last active May 12, 2021 15:41

Given a Google Cloud Storage folder location, generate a automl image classification training data label file using the folders as labels. (https://cloud.google.com/ai-platform-unified/docs/datasets/prepare-image)

	from google.cloud import storage

	folder_location = 'automl-ui-dataset/x-ray-dataset'

	parts = folder_location.split('/')
	prefix = '/'.join(parts[1:]) if len(parts) > 1 else ''

	storage_client = storage.Client()
	blobs = storage_client.list_blobs(parts[0], prefix=prefix)

ZackAkil / main.py

Created November 11, 2020 13:50

Google Cloud Function to Generate a tracking gif of a body part using Video Intelligence API and Storage Triggers.

	import io
	import numpy as np

	import imageio
	import cv2

	from google.cloud import storage
	from google.cloud import videointelligence_v1p3beta1 as videointelligence

	storage_client = storage.Client()

Zack Akil ZackAkil