symisc’s gists

symisc / cnn_full.c

Last active May 8, 2018 00:13

SOD CNN multi-class object detection intro using the MS COCO (80 classes) full model - https://sod.pixlab.io

	/*
	* Programming introduction with the SOD Embedded Convolutional/Recurrent Neural Networks (CNN/RNN) API.
	* Copyright (C) PixLab \| Symisc Systems, https://sod.pixlab.io
	*/
	/*
	* Compile this file together with the SOD embedded source code to generate
	* the executable. For example:
	*
	* gcc sod.c cnn_full.c -lm -Ofast -march=native -Wall -std=c99 -o sod_cnn_intro
	*

symisc / train.txt

Created June 5, 2018 06:29

Template (skeleton) for training SOD RealNets models - https://sod.pixlab.io

	# Single class pedestrian detector for SOD RealNets.
	#
	# This file can serve as template for your future RealNets models to be generated by the SOD training
	# interfaces which are documented at https://sod.pixlab.io/api.html#realnet_train.
	#
	# Copyright (C) PixLab\| Symisc Systems - All right reserved. [email protected] - https://sod.pixlab.io

	# The first thing to specify is where the training samples are located.
	# You must group your dataset on the same directory so can SOD load each entry
	# on a single run and pass the collected image set to the RealNet trainer.

symisc / realtime_face_detection_with_sod.c

Created June 12, 2018 08:51

Real-time frontal face detection with the SOD library - https://sod.pixlab.io

	/*
	* This simple program is a quick introduction on how to embed and start
	* experimenting with SOD without having to do a lot of tedious
	* reading and configuration.
	*
	* Given an input image, detect and draw a bounding box on each detected
	* faces at Real-time.
	*
	* Make sure you have the latest release of SOD from:
	* https://pixlab.io/downloads

symisc / client.js

Created December 9, 2018 03:43 — forked from hagino3000/client.js

WebSocket with binary data

	var socket = null;

	function bootstrap() {

	// 適当な図形を描画
	var c = document.getElementById('mycanvas');
	var ctx = c.getContext('2d');
	ctx.globalalpha = 0.3;
	for(var i=0; i<1000; i++) {
	ctx.beginPath();

symisc / usage.html

Last active November 29, 2020 04:37

Usage example of the WebAssembly Real-Time face detector model - https://pixlab.io/downloads

	<!DOCTYPE html>
	<head>
	<meta charset="utf-8">
	<meta http-equiv="X-UA-Compatible" content="IE=edge">
	<title>WebAssembly Real-Time Face Detection</title>
	<meta name="viewport" content="width=device-width, initial-scale=1">
	</head>
	<style>
	body {
	font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Roboto", "Oxygen", "Ubuntu", "Cantarell", "Fira Sans", "Droid Sans", "Helvetica Neue", sans-serif;

symisc / minutiae.c

Created January 12, 2019 02:29

This program extracts ridges and bifurcations from a fingerprint image.

	/*
	* Programming introduction with the SOD Embedded Image Processing API.
	* Copyright (C) PixLab \| Symisc Systems, https://sod.pixlab.io
	*/
	/*
	* Compile this file together with the SOD embedded source code to generate
	* the executable. For example:
	*
	* gcc sod.c minutiae.c -lm -Ofast -march=native -Wall -std=c99 -o sod_img_proc
	*

symisc / passport_id_scan_ocr.py

Last active June 27, 2024 23:30

Scan over 11K ID Documents from over 197 countries using the PixLab DOCSCAN API Endpoint documented at: https://ekyc.pixlab.io/docscan

	import requests
	import json

	# Scan over 11K ID Documents from over 197 countries using the PixLab DOCSCAN API Endpoint
	# documented at: https://ekyc.pixlab.io/docscan
	#
	# In this example, given a Passport document, extract the passport holder face and convert/parse all Machine Readable Zone
	# to textual content ready to be consumed by your application.
	#
	# PixLab recommend that you connect your AWS S3 bucket via the dashboard at https://console.pixlab.io

symisc / passport_img_scan.php

Last active June 19, 2024 23:21

Scan over 11K ID Documents from over 197 countries using the PixLab DOCSCAN API Endpoint documented at: https://ekyc.pixlab.io/docscan

	<?php
	/*
	* PixLab PHP Client which is just a single class PHP file without any dependency that you can get from Github
	* https://github.com/symisc/pixlab-php
	*/
	require_once "pixlab.php";

	# Scan over 11K ID Documents from over 197 countries using the PixLab DOCSCAN API Endpoint
	# documented at: https://ekyc.pixlab.io/docscan
	#

symisc / realnet_face_detection_embedded.c

Last active April 16, 2019 01:51

Embedded real-time face detection (mobile device, Desktop) via SOD CV Realnets - https://sod.pixlab.io

	/*
	* Programming introduction with the SOD Embedded RealNets API (Frontal Facial detection).
	* Copyright (C) PixLab \| Symisc Systems, https://sod.pixlab.io
	*/
	/*
	* Compile this file together with the SOD embedded source code to generate
	* the executable. For example:
	*
	* gcc sod.c realnet_face_detection_embedded.c -lm -Ofast -march=native -Wall -std=c99 -o sod_realnet_face_detect
	*

symisc / hnsw_exception.py

Created May 13, 2019 17:11

	import numpy as np
	import threading
	import hnswlib

	def func1():
	global index, count, lock
	while True:
	if count > 5000:
	print(f"Max elem reached {count}")
	return

PixLab | Symisc Systems symisc