It`s bugged! In a few minutes when using crushed

[GochaGT]

Error!

Bug! Bug! Bug!

Sos!

👎
I use the face method in this library in the app. 50-55 seconds after launch the app crashes. It obviously has some bug...
This is the error code after checking
I/DynamiteModule: Considering local module com.google.android.gms.vision.dynamite.face:180000 and remote module com.google.android.gms.vision.dynamite.face:0
I/DynamiteModule: Selected local version of com.google.android.gms.vision.dynamite.face
D/TransportRuntime.JobInfoScheduler: Upload for context TransportContext(cct, VERY_LOW, MSRodHRwczovL2ZpcmViYXNlbG9nZ2luZy5nb29nbGVhcGlzLmNvbS92MGNjL2xvZy9iYXRjaD9mb3JtYXQ9anNvbl9wcm90bzNc) is already scheduled. Returning...
I/native: face_detector_v2_jni.cc:33 Loading models/fssd_25_8bit_v1.tflite
I/native: face_detector_v2_jni.cc:33 Loading models/fssd_25_8bit_gray_v1.tflite
I/native: face_detector_v2_jni.cc:33 Loading models/LMprec_600.emd
I/native: face_detector_v2_jni.cc:33 Loading models/BCLlefteyeclosed_200.emd
I/native: face_detector_v2_jni.cc:33 Loading models/BCLrighteyeclosed_200.emd
I/native: face_detector_v2_jni.cc:33 Loading models/BCLjoy_200.emd
I/native: face_detector_v2_jni.cc:33 Loading models/MFT_fssd_fastgray.pb
I/native: face_detector_v2_jni.cc:33 Loading models/contours.tfl
I/native: face_detector_v2_jni.cc:33 Loading models/blazeface.tfl
W/StreamingFormatChecker: ML Kit has detected that you seem to pass camera frames to the detector as a Bitmap object. This is inefficient. Please use YUV_420_888 format for camera2 API or NV21 format for (legacy) camera API and directly pass down the byte array to ML Kit.
Disconnected from the target VM, address: 'localhost:49625', transport: 'socket'