Closed SdeGeata closed 4 years ago
I don't notice that behavior on my machine...
Really? I can’t be the only one. I keep having to dig into the folder and delete the ones that are added... hmmm, i should just set up a cron job to dump ‘em i guess.
Are your sure it's "extendDataset: false," not "extendDataset: 'false'," something like that? Maybe posting your config will help. I copy-pasted mine straight from the README. Try that and work from there. Also be aware of ending differences between Linux / Windows so use a proper editor.
Hello again Horst;
Definitely certain that its not a typo, as you can see - mine too is copied straight from the readme. Also not a windows issue, I'm driving a mac. Here's that config...
{ module: 'MMM-Face-Reco-DNN', config: { // Logout 10 seconds after user is not detected anymore, if they are detected between this 15 Seconds, they delay will start again logoutDelay: 15000, // How many time the recognition starts, with a RasPi 3+ it would be good every 2 seconds checkInterval: 2000, // Module set used for strangers and if no user is detected defaultClass: 'default', // Set of modules which should be shown for every user everyoneClass: 'everyone', // XML to recognize with haarcascae cascade: 'modules/MMM-Face-Reco-DNN/tools/haarcascade_frontalface_default.xml', // Pre encoded pickle with the faces encodings: 'modules/MMM-Face-Reco-DNN/tools/encodings.pickle', // You wanna use pi camera or usb / builtin (1 = raspi camera, 0 = other camera) usePiCamera: 1, // Method of face detection (dnn = deep neural network, haar = haarcascade) method: 'haar', // Which face detection model to use. "hog" is less accurate but faster on CPUs. "cnn" is a more accurate deep-learning model which is GPU/CUDA accelerated (if available). detectionMethod: 'hog', // How fast in ms should the modules hide and show (face effect) animationSpeed: 1000, // Path to Python to run the face recognition (null / '' means default path) pythonPath: null, // Should shown welcome message over alert module from MagicMirror welcomeMessage: true, // Save some pictures from recognized people, if unknown we save it in folder "unknown" // So you can extend your dataset and retrain it afterwards for better recognitions extendDataset: false, // if extenDataset is set, you need to set the full path of the dataset dataset: 'modules/MMM-Face-Reco-DNN/dataset/' } },
Woah, it doesn't look all crappy like that normally. Lemme try again...
{ module: 'MMM-Face-Reco-DNN', config: { // Logout 10 seconds after user is not detected anymore, if they are detected between this 15 Seconds, they delay will start again logoutDelay: 15000, // How many time the recognition starts, with a RasPi 3+ it would be good every 2 seconds checkInterval: 2000, // Module set used for strangers and if no user is detected defaultClass: 'default', // Set of modules which should be shown for every user everyoneClass: 'everyone', // XML to recognize with haarcascae cascade: 'modules/MMM-Face-Reco-DNN/tools/haarcascade_frontalface_default.xml', // Pre encoded pickle with the faces encodings: 'modules/MMM-Face-Reco-DNN/tools/encodings.pickle', // You wanna use pi camera or usb / builtin (1 = raspi camera, 0 = other camera) usePiCamera: 1, // Method of face detection (dnn = deep neural network, haar = haarcascade) method: 'haar', // Which face detection model to use. "hog" is less accurate but faster on CPUs. "cnn" is a more accurate deep-learning model which is GPU/CUDA accelerated (if available). detectionMethod: 'hog', // How fast in ms should the modules hide and show (face effect) animationSpeed: 1000, // Path to Python to run the face recognition (null / '' means default path) pythonPath: null, // Should shown welcome message over alert module from MagicMirror welcomeMessage: true, // Save some pictures from recognized people, if unknown we save it in folder "unknown" // So you can extend your dataset and retrain it afterwards for better recognitions extendDataset: false, // if extenDataset is set, you need to set the full path of the dataset dataset: 'modules/MMM-Face-Reco-DNN/dataset/' } },
Well thats more legible!
Here's a screen grab of the datasets from the last couple days (since last I emptied them)... for any sceptics. ;-p
You were right. It happens for me too. Try my fix.
Pardon my newbie question... how do I implement that? git pull... and to where?
it is on my master now, you can use git pull
Ah, thanks Thierry! ...and thanks Horst for solving that lingering problem for me! You guys are awesome!
I have “extendDataset” set to false in my config, but new pictures continue to be added anyway. I now have close to a hundred in my own folder.