Closed AdarshJais closed 3 years ago
You can refer tensorflow js face landmark detection from the tensorflow website itself it might help you ,for capturing the images u can use openCV
This question is better asked on StackOverflow since it is not a bug or feature request. There is also a larger community that reads questions there.
When I use Tensor Camera
1. It is very much laggy 2. I guess it keeps capturing each frame and thus we just get one item in prediction using the mobilenet model 3. In case we use cocossd for multiple image detection it throw error ""tf.nonMaxSuppression() in webgl locks the UI thread. Call tf.nonMaxSuppressionAsync() instead""
So How is it possible to make a real-time multiple image detection, I can see an example in flutter so is that the same possible in React Native anyway?
Flutter example that I need in React Native : - https://heartbeat.fritz.ai/turning-the-mobile-camera-into-a-real-time-object-detector-with-flutter-and-tensorflow-lite-f412962b1805
Did you find a solution?
Hi. I'm facing the same issue. It's very laggy on Android. Any helps please? Thanks a lot
When I use Tensor Camera
1. It is very much laggy 2. I guess it keeps capturing each frame and thus we just get one item in prediction using the mobilenet model 3. In case we use cocossd for multiple image detection it throw error ""tf.nonMaxSuppression() in webgl locks the UI thread. Call tf.nonMaxSuppressionAsync() instead""
So How is it possible to make a real-time multiple image detection, I can see an example in flutter so is that the same possible in React Native anyway? Flutter example that I need in React Native : - https://heartbeat.fritz.ai/turning-the-mobile-camera-into-a-real-time-object-detector-with-flutter-and-tensorflow-lite-f412962b1805
Did you find a solution?
No bro, no solution yet.
Hi. I'm facing the same issue. It's very laggy on Android. Any helps please? Thanks a lot
Brother did you find any solution to this im also facing same problem im using a model that I created using teachable machine and its very laggy ?
When I use Tensor Camera
1. It is very much laggy 2. I guess it keeps capturing each frame and thus we just get one item in prediction using the mobilenet model 3. In case we use cocossd for multiple image detection it throw error ""tf.nonMaxSuppression() in webgl locks the UI thread. Call tf.nonMaxSuppressionAsync() instead""
So How is it possible to make a real-time multiple image detection, I can see an example in flutter so is that the same possible in React Native anyway? Flutter example that I need in React Native : - https://heartbeat.fritz.ai/turning-the-mobile-camera-into-a-real-time-object-detector-with-flutter-and-tensorflow-lite-f412962b1805
Did you find a solution?
Brother did you find any solution to this im also facing same problem im using a model that I created using teachable machine and its very laggy ?
Hi. I'm facing the same issue. It's very laggy on Android. Any helps please? Thanks a lot
any solution brother pls help ?
Hi. My solution is still a little bit laggy on android, but you can find an article I wrote about two years ago (https://www.bam.tech/article/how-to-recognize-real-time-object-in-reactnative-for-dummies) it has not been updated since so it may be an outdated solution. Hope it can help
When I use Tensor Camera
So How is it possible to make a real-time multiple image detection, I can see an example in flutter so is that the same possible in React Native anyway?
Flutter example that I need in React Native : - https://heartbeat.fritz.ai/turning-the-mobile-camera-into-a-real-time-object-detector-with-flutter-and-tensorflow-lite-f412962b1805