11 Commits

Author	SHA1	Message	Date
Nate Meyer	1f8a8ffd3d	Add configuration for model inputs ... Support transforming detection regions to RGB or BGR. Support specifying the input tensor shape. The tensor shape has a standard format ["BHWC"] when handed to the detector, but can be transformed in the detector to match the model shape using the model input_tensor config.	2022-10-25 22:39:47 -04:00
Nate Meyer	c359c7c9bd	Refactor EdgeTPU and CPU model handling to detector submodules.	2022-10-25 22:39:47 -04:00
Nicolas Mowen	0a4d658c7f	Ability to enable / disable motion detection via MQTT (#3117) ... * Starting working on adding motion toggle * Add all info to mqtt command * Send motion to correct funs * Update mqtt docs * Fixes for contingencies * format * mypy * Tweak behavior * Fix motion breaking frames * Fix bad logic in detect set * Always set value for motion boxes	2022-04-26 07:29:28 -05:00
Blake Blackshear	93f418ac0b	fix process_clip	2022-02-18 21:18:26 -06:00
Blake Blackshear	0e43f452d2	use resolution of clip	2022-02-18 21:18:26 -06:00
Blake Blackshear	0695bb097d	revamp process clip	2022-02-18 21:18:26 -06:00
Blake Blackshear	a4b88ac4a7	fix process clip	2021-01-26 21:40:33 -06:00
Blake Blackshear	ec4d048905	upgrade to python3.8 and switch from plasma store to shared_memory	2020-10-18 13:47:13 -05:00
Blake Blackshear	69406343ee	allow setting the camera fps if needed	2020-09-17 07:37:27 -05:00
Blake Blackshear	e26308a05b	print score info	2020-09-17 07:37:27 -05:00
Blake Blackshear	acb75fa02d	refactor and reduce false positives	2020-09-17 07:37:27 -05:00