TinyML - Revision history

Tim: /* tinyML */

2021-03-16T15:59:38Z

tinyML

← Older revision		Revision as of 11:59, 16 March 2021
Line 1:		Line 1:
	= tinyML =		= tinyML =

			while it is easy to benchmark tensorlite models via colab, what standards or can be used to benchmark device performance? ex:KWS on nano33: would the benchmark be an audio file that you play to its microphone? Will there be extensions to the code to create a confusion matrix or some measure?

	==troubleshooting==		==troubleshooting==
	@bagwas thereafter the accuracy was really good		@bagwas thereafter the accuracy was really good

Tim: /* datasets */

2021-03-16T15:45:23Z

datasets

← Older revision		Revision as of 11:45, 16 March 2021
Line 80:		Line 80:

	===datasets===		===datasets===
			https://github.com/mlcommons/tiny.

	https://archive.ics.uci.edu/ml/datasets.php		https://archive.ics.uci.edu/ml/datasets.php

	https://arxiv.org/abs/1908.03299 anomaly detection		https://arxiv.org/abs/1908.03299 anomaly detection

Tim at 15:41, 16 March 2021

2021-03-16T15:41:16Z

← Older revision		Revision as of 11:41, 16 March 2021
Line 81:		Line 81:
	===datasets===		===datasets===
	https://archive.ics.uci.edu/ml/datasets.php		https://archive.ics.uci.edu/ml/datasets.php
			https://arxiv.org/abs/1908.03299 anomaly detection

	## references & discussion:		## references & discussion:

Tim at 15:38, 16 March 2021

2021-03-16T15:38:12Z

← Older revision		Revision as of 11:38, 16 March 2021
Line 79:		Line 79:
	> If that works, how could I make it work on an uncommon word that will open my door? Maybe take all the audio data and reverse it in time, like playing a the Beatles White Album backwards to hear 'Paul is dead'. Instead of 'hello', 'olleh' opens my door. Train on that and build another model.		> If that works, how could I make it work on an uncommon word that will open my door? Maybe take all the audio data and reverse it in time, like playing a the Beatles White Album backwards to hear 'Paul is dead'. Instead of 'hello', 'olleh' opens my door. Train on that and build another model.

			===datasets===
			https://archive.ics.uci.edu/ml/datasets.php
	## references & discussion:		## references & discussion:

Tim: /* troubleshooting */

2021-03-12T21:42:28Z

troubleshooting

← Older revision		Revision as of 17:42, 12 March 2021
Line 8:		Line 8:
	@stephenbaileymagic I believe that I will need to do a lot of tweaks to the whole pipeline to improve real world performance.		@stephenbaileymagic I believe that I will need to do a lot of tweaks to the whole pipeline to improve real world performance.
	@stephenbaileymagicit doesn’t test the micro model after converting		@stephenbaileymagicit doesn’t test the micro model after converting

			on poor KWS performance: tweak the whole pipeline?

			I decided `ProcessLatestResults` was sending stuff to `RespondToCommand` that was driving me crazy and hiding data that I wanted to see. I put

	==voice recognition project==		==voice recognition project==

Tim: /* tinyML */

2021-03-12T21:35:48Z

tinyML

← Older revision		Revision as of 17:35, 12 March 2021
Line 1:		Line 1:
	= tinyML =		= tinyML =
			==troubleshooting==
			@bagwas thereafter the accuracy was really good
			@H_Scholten The idea is to trigger the recording with the switch on the board and record a word.
			@dizgotti, it seems that you have dug into the code a bit to find "failed to detect".
			@brian_plancher In terms of adding volume requirements to the website -- I will definitely look into it
			@vjreddi it shouldn't be really bad for yes/no. It should definitely work.
			@stephenbaileymagic I believe that I will need to do a lot of tweaks to the whole pipeline to improve real world performance.
			@stephenbaileymagicit doesn’t test the micro model after converting

	==voice recognition project==		==voice recognition project==

Tim: /* tinyML */

2021-03-10T21:02:25Z

tinyML

← Older revision		Revision as of 17:02, 10 March 2021
Line 2:		Line 2:

	==voice recognition project==		==voice recognition project==
			https://www.mathworks.com/help/audio/ug/speaker-identification-using-pitch-and-mfcc.html

			https://github.com/pannous/tensorflow-speech-recognition

	[https://storage.googleapis.com/download.tensorflow.org/data/speech_commands_v0.02.tar.gz pete's audio dataset]		[https://storage.googleapis.com/download.tensorflow.org/data/speech_commands_v0.02.tar.gz pete's audio dataset]

Tim: /* tinyML */

2021-03-10T20:09:08Z

tinyML

@@ Line 7: / Line 7: @@
 https://discuss.tinymlx.org/c/projects/5
 https://www.globalsecurity.org/security/systems/biometrics-voice.htm
 ===post to [https://discuss.tinymlx.org/c/projects/5 projects]===

Tim: /* 3-1.6 */

2021-03-10T19:45:53Z

3-1.6

← Older revision		Revision as of 15:45, 10 March 2021
Line 1:		Line 1:
	= tinyML =		= tinyML =
	==~~3-1.6~~==
			==voice recognition project==
	[https://storage.googleapis.com/download.tensorflow.org/data/speech_commands_v0.02.tar.gz pete's audio dataset]		[https://storage.googleapis.com/download.tensorflow.org/data/speech_commands_v0.02.tar.gz pete's audio dataset]

Line 6:		Line 7:

	https://discuss.tinymlx.org/c/projects/5		https://discuss.tinymlx.org/c/projects/5

			https://www.globalsecurity.org/security/systems/biometrics-voice.htm

	===post to [https://discuss.tinymlx.org/c/projects/5 projects]===		===post to [https://discuss.tinymlx.org/c/projects/5 projects]===
Line 119:		Line 122:

	"the difficulty associated with procuring large quantities of data. This procedure is aptly named dataset engineering" or 'sexy AI machine learning job' or being a mechanical turk (soon to be replaced by meta-AI. "data provenance. We must be cognizant of the origin of our data" and consult experts on how they have managed to take our data. "radiologists may be necessary" for a little while longer.		"the difficulty associated with procuring large quantities of data. This procedure is aptly named dataset engineering" or 'sexy AI machine learning job' or being a mechanical turk (soon to be replaced by meta-AI. "data provenance. We must be cognizant of the origin of our data" and consult experts on how they have managed to take our data. "radiologists may be necessary" for a little while longer.

			==3-1.6==

	==3-1.5 Forum: Pretrained KWS Model==		==3-1.5 Forum: Pretrained KWS Model==

Tim: /* tinyML */

2021-03-10T19:25:45Z

tinyML

← Older revision		Revision as of 15:25, 10 March 2021
Line 1:		Line 1:
	= tinyML =		= tinyML =
	==3-1.6==		==3-1.6==
			[https://storage.googleapis.com/download.tensorflow.org/data/speech_commands_v0.02.tar.gz pete's audio dataset]

	https://github.com/gigwegbe/tinyml-papers-and-projects		https://github.com/gigwegbe/tinyml-papers-and-projects