Shubham Panchal
Shubham Panchal
@Sheimy I will look into the issue and get back here.
@omikesharwani22 I am looking into the issue and will get back to you within a few days.
You can obtain a pretrained Keras model for FaceNet, from [DeepFace](https://github.com/serengil/deepface). Then load this model using `tf.keras.models.load_model()` and you're ready to train the model on your dataset.
This is because of different device configurations. Probably switching off the `GpuDelegate` and `XNNPack` might help. In the `FaceNetModel.kt` class, you'll see these lines, ``` init { // Initialize TFLiteInterpreter...
@emreakcan Could you resolve the error by removing `GpuDelegate`?
@DineshIT can you send me some more details of the Samsung A21 device on which you're testing the app? I need these details specifically: 1. Android OS Version 2. GPU...
@DineshIT Can you open a PR in this repo, so that I can review the changes?
I have converted the model checkpoints to the TFLite format and used it in an Android app. Check the repo -> [shubham0204/Hand_Detection_TFLite_Android](https://github.com/shubham0204/Hand_Detection_TFLite_Android). To convert the checkpoints yourself, follow this step-by-step...
For future viewers of this issue, the warning seems to be a bug from the IDE, and the library works perfectly fine. I'm using version catalogs with Gradle, here's my...
@omikesharwani22 The issue seems to arise from the flipping from input camera frames that is performed when the front camera is used. The app has a hardcoded camera selection `CameraSelector.LENS_FACING_FRONT`...