toz

you may try "SubCenter-ArcFace-r100-gpu" [docker from compreface](https://github.com/exadel-inc/CompreFace/blob/master/custom-builds/README.md). they say thats the heaviest modell and most accurate. on the same computer with the normal compreface model (facenet) my whole system stood...

The have 1) facenet (facenet-lib), 2) mobilenet(insightface-lib), 3) arcface (insightface-lib). facenet seems the default and does its job. i had high hopes for more precision with mobilenet, but it detected...

i will check with 1.0. But i have to pull it first...hold on. i come back

maybe related? i have images with training-timeout. but cannot move& train this single image. a Gui-button would be helpful. if i use the dropdown to select a target-person other than...

for clarification: i am on the the train-pages. i did like you suggested: i clicked the trash-button and the image was trashed. expectable. no more re-train. image was deleted. not...

is ist possible to retrain all folder at once? ( i switched compreface to custom-image with mobilenet and i think i have to relearn all faces) now i search for...

thanks. i changed the compreface modell and wanted to compare the detection precision between the default model (facenet - i guess) and the heaviest modell ([insightface](https://github.com/deepinsight/insightface), looks promising. github says...

i was wondering if doubl-take could use the normal compreface API for face-rec, but with different compreface-models? do you tested this? does compreface aggregate face-recognitions form different models== "embedding" servers":3000...

first start? (my topic starts with a slash "/", please note this)  ``` [{"id":"ad8ddf2b.79d33","type":"mqtt in","z":"2d5205a0.26601a","name":"","topic":"/double-take/#","qos":"2","datatype":"auto","broker":"9b50c12.74a3a4","x":170,"y":1560,"wires":[["87f6d4aa.1261e8"]]},{"id":"87f6d4aa.1261e8","type":"json","z":"2d5205a0.26601a","name":"","property":"payload","action":"","pretty":false,"x":370,"y":1560,"wires":[["f7ab8316.5c808","3fe2df70.4cf46","e542771b.6c7558","c450cc38.c8b8d"]]},{"id":"3fe2df70.4cf46","type":"image","z":"2d5205a0.26601a","name":"dt: FACE-REC","width":"320","data":"payload.match.base64","dataType":"msg","thumbnail":false,"active":true,"pass":false,"outputs":0,"x":580,"y":1560,"wires":[]},{"id":"9b50c12.74a3a4","type":"mqtt-broker","name":"192.168.14.204-hik","broker":"192.168.14.204","port":"1883","clientid":"","usetls":false,"compatmode":true,"keepalive":"60","cleansession":true,"birthTopic":"","birthQos":"0","birthPayload":"","closeTopic":"","closePayload":"","willTopic":"","willQos":"0","willPayload":""}] ```

@nmsoares . i dont understand the question for the last function. may you could ask with more context. what do you want to achieve?