Mirror/AI-on-the-edge-device-docs
1
0
Fork 0
mirror of https://github.com/jomjol/AI-on-the-edge-device-docs.git synced 2025-12-07 03:57:00 +03:00
Code Issues Packages Projects Releases Wiki Activity

Deployed 85a5689 with MkDocs version: 1.6.1

Browse Source
This commit is contained in:
github-actions[bot]
2025-04-16 18:55:22 +00:00
parent e340e569a8
commit 171031de0a
4 changed files with 20 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
Choosing-the-Model/index.html
View File

@@ -284,17 +284,6 @@
Analog pointer models
</span>
</a>
<nav aria-label="Analog pointer models" class="md-nav">
<ul class="md-nav__list">
<li class="md-nav__item">
<a class="md-nav__link" href="#ana-class100-and-ana-cont">1.2.1
<span class="md-ellipsis">
ana-class100 and ana-cont
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#different-types-of-models-normal-vs-quantized">1.3
@@ -774,17 +763,6 @@
Analog pointer models
</span>
</a>
<nav aria-label="Analog pointer models" class="md-nav">
<ul class="md-nav__list">
<li class="md-nav__item">
<a class="md-nav__link" href="#ana-class100-and-ana-cont">1.2.1
<span class="md-ellipsis">
ana-class100 and ana-cont
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#different-types-of-models-normal-vs-quantized">1.3
@@ -875,7 +853,6 @@ The <code>dig-class100</code> is a standard classification model. Each tenth ste
</div>
<p>Look <a href="https://jomjol.github.io/neural-network-digital-counter-readout">here</a> for a list of digit images used for the training.</p>
<h2 id="analog-pointer-models"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.2</span> Analog pointer models</h2>
<h3 id="ana-class100-and-ana-cont"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.2.1</span> <code>ana-class100</code> and <code>ana-cont</code></h3>
<p>For pointers on water meters use the analog models:</p>
<p><img alt="" src="../img/ana-class100.png" style="width:250px"/></p>
<p>You can choose between two models:</p>

1
Frequent-Reboots/index.html
View File

@@ -955,7 +955,6 @@ There is noting you can do about it, beside testing different hardware.</p>
</ol>
<h5 id="bad-or-insufficient-power-supply"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.0.1.1.1</span> Bad or insufficient power supply</h5>
<p>A good and stabilized power supply is essential to have error free operation. The device is quite picky in terms of proper power supply. Especially the wifi module have some load spikes which the power supply needs to cover. If the power is not stable enough, the brwonout mechanism is protecting against strange behaviour and force a reboot whenever the voltage drops below a specific level. You can see this in random reboots which indication is logfile: --&gt; Reset reason: Brownout</p>
<hr/>
<h3 id="repeating-boot-loops"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.0.2</span> Repeating boot loops</h3>
<p>Repeating boot loops at the same situation during the flow has a systematic problem either in the hardware or the configuration. It usually happens during initialization state or processing the first round as there all needed parts of the firmware have been loaded for the first time.</p>
<p>To identify the root cause the logfiles, the reduced web interface, the red board LED or the serial log of the UART interface (no remote access, USB access needed) is helpful. </p>

38
Neural-Network-Types/index.html
View File

@@ -400,7 +400,7 @@
<li class="md-nav__item">
<a class="md-nav__link" href="#types-of-counters-trained">1.3.1.1
<span class="md-ellipsis">
Types of counters trained:
Types of counters trained
</span>
</a>
</li>
@@ -450,7 +450,7 @@
<li class="md-nav__item">
<a class="md-nav__link" href="#types-of-counters-trained_1">1.3.2.1
<span class="md-ellipsis">
Types of counters trained:
Types of counters trained
</span>
</a>
</li>
@@ -464,10 +464,10 @@
<li class="md-nav__item">
<a class="md-nav__link" href="#cnn-technical-details_1">1.3.2.3
<span class="md-ellipsis">
CNN Technical details:
CNN Technical details
</span>
</a>
<nav aria-label="CNN Technical details:" class="md-nav">
<nav aria-label="CNN Technical details" class="md-nav">
<ul class="md-nav__list">
<li class="md-nav__item">
<a class="md-nav__link" href="#input_1">1.3.2.3.1
@@ -500,7 +500,7 @@
<li class="md-nav__item">
<a class="md-nav__link" href="#types-of-counters-trained_2">1.3.3.1
<span class="md-ellipsis">
Types of counters trained:
Types of counters trained
</span>
</a>
</li>
@@ -514,10 +514,10 @@
<li class="md-nav__item">
<a class="md-nav__link" href="#cnn-technical-details_2">1.3.3.3
<span class="md-ellipsis">
CNN Technical details:
CNN Technical details
</span>
</a>
<nav aria-label="CNN Technical details:" class="md-nav">
<nav aria-label="CNN Technical details" class="md-nav">
<ul class="md-nav__list">
<li class="md-nav__item">
<a class="md-nav__link" href="#input_2">1.3.3.3.1
@@ -869,7 +869,7 @@
<li class="md-nav__item">
<a class="md-nav__link" href="#types-of-counters-trained">1.3.1.1
<span class="md-ellipsis">
Types of counters trained:
Types of counters trained
</span>
</a>
</li>
@@ -919,7 +919,7 @@
<li class="md-nav__item">
<a class="md-nav__link" href="#types-of-counters-trained_1">1.3.2.1
<span class="md-ellipsis">
Types of counters trained:
Types of counters trained
</span>
</a>
</li>
@@ -933,10 +933,10 @@
<li class="md-nav__item">
<a class="md-nav__link" href="#cnn-technical-details_1">1.3.2.3
<span class="md-ellipsis">
CNN Technical details:
CNN Technical details
</span>
</a>
<nav aria-label="CNN Technical details:" class="md-nav">
<nav aria-label="CNN Technical details" class="md-nav">
<ul class="md-nav__list">
<li class="md-nav__item">
<a class="md-nav__link" href="#input_1">1.3.2.3.1
@@ -969,7 +969,7 @@
<li class="md-nav__item">
<a class="md-nav__link" href="#types-of-counters-trained_2">1.3.3.1
<span class="md-ellipsis">
Types of counters trained:
Types of counters trained
</span>
</a>
</li>
@@ -983,10 +983,10 @@
<li class="md-nav__item">
<a class="md-nav__link" href="#cnn-technical-details_2">1.3.3.3
<span class="md-ellipsis">
CNN Technical details:
CNN Technical details
</span>
</a>
<nav aria-label="CNN Technical details:" class="md-nav">
<nav aria-label="CNN Technical details" class="md-nav">
<ul class="md-nav__list">
<li class="md-nav__item">
<a class="md-nav__link" href="#input_2">1.3.3.3.1
@@ -1100,7 +1100,7 @@
<h3 id="analog-pointer-ana-cont_xxxtflite-ana-class100_xxxtflite"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.1</span> Analog Pointer ("ana-cont_XXX.tflite" &amp; "ana-class100_XXX.tflite")</h3>
<p>This is to transfer the direction of a pointer into a continuous number between 0 and 1, whereas 0 (=1) is the upwards position (12 o'clock), 0.25 corresponds to the 3 o'clock positions and so on. This network is a envelop for all different types of pointers. Currently there are no dedicated network trainings for specific types of pointers.</p>
<p>There are two types of network structure, currently both are supported. The "class100" is a pure classification network, that might need a bit more accuracy in the labeling. "cont" is a no classic approach with a continuous output off only 2 neurons (details see below).</p>
<h4 id="types-of-counters-trained"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.1.1</span> Types of counters trained:</h4>
<h4 id="types-of-counters-trained"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.1.1</span> Types of counters trained</h4>
<table>
<thead>
<tr>
@@ -1150,7 +1150,7 @@
</ul>
<h3 id="digits-with-11-classes-dig-class11_xxxtflite"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.2</span> Digits with 11 classes ("dig-class11_XXX.tflite")</h3>
<p>The digit type is a classical classification network, with 11 classes representing the numbers 0, 1, ... 9 and the special class "N". It is trained for the rolling ring of gas and electric meters. As there is sometime a status between two images, the special class "N" is representing Not-A-Number for the case, that the image cannot be unique classified to one number e.g. because it is between two digits. For this type the lowest amount of training data per type is needed, resulting in a large variety of type being already part of the training set.</p>
<h4 id="types-of-counters-trained_1"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.2.1</span> Types of counters trained:</h4>
<h4 id="types-of-counters-trained_1"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.2.1</span> Types of counters trained</h4>
<table>
<thead>
<tr>
@@ -1194,7 +1194,7 @@
<p>Naming: x_ARBITRARY.jpg, where x = value 0 ... 9 + N</p>
</li>
</ul>
<h4 id="cnn-technical-details_1"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.2.3</span> CNN Technical details:</h4>
<h4 id="cnn-technical-details_1"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.2.3</span> CNN Technical details</h4>
<h5 id="input_1"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.2.3.1</span> Input</h5>
<ul>
<li>20 x 32 RGB images</li>
@@ -1207,7 +1207,7 @@
</ul>
<h3 id="digits-with-rolling-results-dig-class100_xxxtflite-dig-cont_xxxtflite"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.3</span> Digits with rolling results ("dig-class100_XXX.tflite" &amp; "dig-cont_XXX.tflite")</h3>
<p>This type of network tries to overcome the problem, that there are intermediate values, when a rolling digit is between two numbers. Previous this was the "N" class. In this network type, there are also sub-digit values trained, so that the intermediate state can be used as additional information for the algorithms. </p>
<h4 id="types-of-counters-trained_2"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.3.1</span> Types of counters trained:</h4>
<h4 id="types-of-counters-trained_2"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.3.1</span> Types of counters trained</h4>
<table>
<thead>
<tr>
@@ -1236,7 +1236,7 @@
<p>Naming: x.y_ARBITRARY.jpg, where x.y = 0.0, 0.1, ... 9.9 representing the intermediate state</p>
</li>
</ul>
<h4 id="cnn-technical-details_2"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.3.3</span> CNN Technical details:</h4>
<h4 id="cnn-technical-details_2"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.3.3</span> CNN Technical details</h4>
<h5 id="input_2"><span class="enumerate-headings-plugin enumerate-heading-plugin">1.3.3.3.1</span> Input</h5>
<ul>
<li>20 x 32 RGB images</li>

2
search/search_index.json
View File

File diff suppressed because one or more lines are too long