AI REDGIO 5.0 Open Hardware Platform - Revision history

Admino739mjm7: /* External Resources */

2024-09-03T12:50:43Z

External Resources

← Older revision		Revision as of 12:50, 3 September 2024
Line 156:		Line 156:
	== External Resources ==		== External Resources ==
	<ul>		<ul>
	<li>Examples and guide for model onboarding on The Open Platform available in [https://github.com/ImasDLibelium/AI-Regio-5.0-T5-OH-AI-Deployment-Guide Github]</li>		<li>Examples and guide for model onboarding on The Open Platform available in [https://github.com/ImasDLibelium/AI-Regio-5.0-T5-OH-AI-Deployment-Guide/tree/3faa932650529876200131ba2bbae805642383d7 Github]</li>
	<li>Created by [https://www.libelium.com Libelium (HOPU)]</li>		<li>Created by [https://www.libelium.com Libelium (HOPU)]</li>
	</ul>		</ul>

Admino739mjm7: /* External Resources */

2024-02-01T10:47:20Z

External Resources

← Older revision		Revision as of 10:47, 1 February 2024
Line 156:		Line 156:
	== External Resources ==		== External Resources ==
	<ul>		<ul>
	<li>~~''Available soon'':~~ Examples and guide for model onboarding on The Open Platform available in [https://github.com/ Github]</li>		<li>Examples and guide for model onboarding on The Open Platform available in [https://github.com/ImasDLibelium/AI-Regio-5.0-T5-OH-AI-Deployment-Guide Github]</li>
	<li>Created by [https://www.libelium.com Libelium (HOPU)]</li>		<li>Created by [https://www.libelium.com Libelium (HOPU)]</li>
	</ul>		</ul>

Admino739mjm7: /* External Resources */

2023-11-22T12:25:45Z

External Resources

← Older revision		Revision as of 12:25, 22 November 2023
Line 156:		Line 156:
	== External Resources ==		== External Resources ==
	<ul>		<ul>
	<li>Available ~~Soon~~: Examples and guide for model onboarding on The Open Platform available in [https://github.com/ Github]</li>		<li>''Available soon'': Examples and guide for model onboarding on The Open Platform available in [https://github.com/ Github]</li>
	<li>Created by [https://www.libelium.com Libelium (HOPU)]</li>		<li>Created by [https://www.libelium.com Libelium (HOPU)]</li>
	</ul>		</ul>

Admino739mjm7: /* External Resources */

2023-11-22T12:25:11Z

External Resources

← Older revision		Revision as of 12:25, 22 November 2023
Line 156:		Line 156:
	== External Resources ==		== External Resources ==
	<ul>		<ul>
	<li>~~Guide~~ for ~~Python~~ model ~~compilation to C++~~ available in [https://github.com/ Github]</li>		<li>Available Soon: Examples and guide for model onboarding on The Open Platform available in [https://github.com/ Github]</li>
	<li>~~Download through~~ [https://~~github~~.com~~/ Github]</li>~~		<li>Created by [https://www.libelium.com Libelium (HOPU)]</li>
	~~<li>Created by [~~HOPU~~]</li>~~
	~~<li>Contact [email~~]</li>
	</ul>		</ul>

	== Relevant Categories==		== Relevant Categories==
	[[Category:Edge AI]][[Category:IoT]][[Category:Open Hardware Project]][[Category:Edge]][[Category:ESP32]]		[[Category:Edge AI]][[Category:IoT]][[Category:Open Hardware Project]][[Category:Edge]][[Category:ESP32]]

Admino739mjm7: /* Phase I: Model generation and translation */

2023-11-21T07:54:22Z

Phase I: Model generation and translation

← Older revision		Revision as of 07:54, 21 November 2023
Line 69:		Line 69:
	#First, the code of the artificial intelligence model is generated in Python using the TensorFlow library, training the model and performing the necessary tests to obtain a satisfactory result		#First, the code of the artificial intelligence model is generated in Python using the TensorFlow library, training the model and performing the necessary tests to obtain a satisfactory result
	#The next step is to convert the model to TensorFlow Lite. To do this, it is only necessary to make a call to a function.		#The next step is to convert the model to TensorFlow Lite. To do this, it is only necessary to make a call to a function.
	#The last step of this phase is to convert the model; for this, the Unix command is used:		#The last step of this phase is to convert the model to C; for this, the Unix command is used:


Line 94:		Line 94:
	[[File:Open hardware phase 1.png\|center\|x300px\|Image Caption]]		[[File:Open hardware phase 1.png\|center\|x300px\|Image Caption]]
	<div align="center" style="font-size:88%;line-height: 2em">''Image 3: AI REDGIO 5.0 Open Hardware - Model conversion steps''</div>		<div align="center" style="font-size:88%;line-height: 2em">''Image 3: AI REDGIO 5.0 Open Hardware - Model conversion steps''</div>


	=== Phase II: Implementation of the code in the Open Hardware ===		=== Phase II: Implementation of the code in the Open Hardware ===

Admino739mjm7: /* AI on Open Hardware Deployment Steps */

2023-11-20T15:21:50Z

AI on Open Hardware Deployment Steps

← Older revision		Revision as of 15:21, 20 November 2023
Line 96:		Line 96:


	=== Phase II: Implementation of the code in the Open Hardware		=== Phase II: Implementation of the code in the Open Hardware ===
	<p style="line-height: 1.5em">		<p style="line-height: 1.5em">
	The following connectivity, model loading and execution steps are required by the Open Hardware Platform users in order to deploy their AI models on the platform.		The following connectivity, model loading and execution steps are required by the Open Hardware Platform users in order to deploy their AI models on the platform.
Line 102:		Line 102:

	[[File:Open hardware deployment steps.png\|center\|x300px\|Image Caption]]		[[File:Open hardware deployment steps.png\|center\|x300px\|Image Caption]]
	<div align="center" style="font-size:88%;line-height: 2em">''Image 3: AI REDGIO 5.0 Open Hardware - AI Deployment Steps''</div>		<div align="center" style="font-size:88%;line-height: 2em">''Image 4: AI REDGIO 5.0 Open Hardware - AI Deployment Steps''</div>

	=== 1. Network Connection and Data Reception===		=== 1. Network Connection and Data Reception===
Line 132:		Line 132:

	[[File:Arduino ide serial monitor.png\|center\|x300px\|Image Caption]]		[[File:Arduino ide serial monitor.png\|center\|x300px\|Image Caption]]
	<div align="center" style="font-size:88%;line-height: 2em">''Image 4: Arduino Ide serial monitor''</div>		<div align="center" style="font-size:88%;line-height: 2em">''Image 5: Arduino Ide serial monitor''</div>

	<p style="line-height: 1.5em">		<p style="line-height: 1.5em">
Line 140:		Line 140:

	[[File:Mqtt message.png\|center\|x300px\|Image Caption]]		[[File:Mqtt message.png\|center\|x300px\|Image Caption]]
	<div align="center" style="font-size:88%;line-height: 2em">''Image 5: MQTT Message''</div>		<div align="center" style="font-size:88%;line-height: 2em">''Image 6: MQTT Message''</div>

	<p style="line-height: 1.5em">		<p style="line-height: 1.5em">
Line 148:		Line 148:

	[[File:Ai model prediction output.png\|center\|x300px\|Image Caption]]		[[File:Ai model prediction output.png\|center\|x300px\|Image Caption]]
	<div align="center" style="font-size:88%;line-height: 2em">''Image 6: AI Model Prediction Output''</div>		<div align="center" style="font-size:88%;line-height: 2em">''Image 7: AI Model Prediction Output''</div>

	'''*Note: Importance of Version Consistency'''		'''*Note: Importance of Version Consistency'''

Admino739mjm7: /* Phase I: Model generation and translation */

2023-11-20T15:20:53Z

Phase I: Model generation and translation

← Older revision		Revision as of 15:20, 20 November 2023
Line 85:		Line 85:
	The output of the command will be a C array similar to this one:		The output of the command will be a C array similar to this one:

	''unsigned char converted_model_tflite[] = ''		''unsigned char converted_model_tflite[] = ''<br>
	''{''		''{''<br>
	''0x18, 0x00, 0x00, 0x00, 0x00, 0x54, 0x46, 0x4c, 0x33, 0x00, 0x00, 0x00, 0x0e, 0x00.''		''0x18, 0x00, 0x00, 0x00, 0x00, 0x54, 0x46, 0x4c, 0x33, 0x00, 0x00, 0x00, 0x0e, 0x00.''<br>
	''<Lines omitted>''		''<Lines omitted>''<br>
	''};''		''};''<br>
	''unsigned int converted_model_tflite_len = 18200''		''unsigned int converted_model_tflite_len = 18200''<br>

	[[File:Open hardware phase 1.png\|center\|x300px\|Image Caption]]		[[File:Open hardware phase 1.png\|center\|x300px\|Image Caption]]

Admino739mjm7: /* AI on Open Hardware Deployment Steps */

2023-11-20T15:20:25Z

AI on Open Hardware Deployment Steps

← Older revision		Revision as of 15:20, 20 November 2023
Line 85:		Line 85:
	The output of the command will be a C array similar to this one:		The output of the command will be a C array similar to this one:

	''unsigned char converted_model_tflite[] =		''unsigned char converted_model_tflite[] = ''
	{0x18, 0x00, 0x00, 0x00, 0x00, 0x54, 0x46, 0x4c, 0x33, 0x00, 0x00, 0x00, 0x0e, 0x00.		''{''
	<Lines omitted>		''0x18, 0x00, 0x00, 0x00, 0x00, 0x54, 0x46, 0x4c, 0x33, 0x00, 0x00, 0x00, 0x0e, 0x00.''
	};		''<Lines omitted>''
	unsigned int converted_model_tflite_len = 18200''		''};''
			''unsigned int converted_model_tflite_len = 18200''

	[[File:Open hardware phase 1.png\|center\|x300px\|Image Caption]]		[[File:Open hardware phase 1.png\|center\|x300px\|Image Caption]]

Admino739mjm7: /* Phase I: Model generation and translation */

2023-11-20T15:18:47Z

Phase I: Model generation and translation

← Older revision		Revision as of 15:18, 20 November 2023
Line 75:		Line 75:
	<div align="center" >		<div align="center" >

	{\| class="wikitable" style="margin:auto; width:~~100%~~; line-height: 1.5em"		{\| class="wikitable" style="margin:auto; width:300px; line-height: 1.5em"
	\|-		\|-
	\| '''xxd -i input_file.tflite > output_file.cc'''		\| '''xxd -i input_file.tflite > output_file.cc'''

Admino739mjm7: /* Phase I: Model generation and translation */

2023-11-20T15:18:05Z

Phase I: Model generation and translation

← Older revision		Revision as of 15:18, 20 November 2023
Line 70:		Line 70:
	#The next step is to convert the model to TensorFlow Lite. To do this, it is only necessary to make a call to a function.		#The next step is to convert the model to TensorFlow Lite. To do this, it is only necessary to make a call to a function.
	#The last step of this phase is to convert the model; for this, the Unix command is used:		#The last step of this phase is to convert the model; for this, the Unix command is used:
	<div align="center" >'''xxd -i input_file.tflite > output_file.cc'''</div>


			<div align="center" >

			{\| class="wikitable" style="margin:auto; width:100%; line-height: 1.5em"
			\|-
			\| '''xxd -i input_file.tflite > output_file.cc'''
			\|-
			\|}

			</div>

	The output of the command will be a C array similar to this one:		The output of the command will be a C array similar to this one: