szaza / android-yolo-v2

Android YOLO real time object detection sample application with Tensorflow mobile.
Do What The F*ck You Want To Public License
227 stars 86 forks source link

put the PB and txt files in the assets folder. #9

Open DRACOyu opened 6 years ago

DRACOyu commented 6 years ago

I follow the instructions to put the PB and txt files in the assets folder. After the app opens, it will flash back. I am training the yolo2 to do face detection. The output is 30=5*6. What is the reason?

szaza commented 6 years ago

Could you please send me the exception what you get? You trained the model for only one class, right?

aaronhan92 commented 6 years ago

Hi Szaza,

Fyi, I am using yolov2-tiny.cfg and yolov2-tiny-voc_10000.weights to train my own dataset (winnie the pooh and tiger) . However, the Yolov2 app does not work after finished the training, I exported and replaced both yolov2-tiny.pb and label.txt file in android/asset/folder.

Please kindly advise.

Here's the error 09/29 10:30:03: Launching android-yolo-v2 $ adb install-multiple -r -t -p org.tensorflow.yolo C:\Users\hanwe\android-yolo-v2\gradleBuild\outputs\apk\debug\android-yolo-v2-debug.apk Split APKs installed $ adb shell am start -n "org.tensorflow.yolo/org.tensorflow.yolo.view.ClassifierActivity" -a android.intent.action.MAIN -c android.intent.category.LAUNCHER Client not ready yet..Waiting for process to come online Waiting for process to come online Connected to process 13342 on device oppo-cph1719-97bc8b7 Capturing and displaying logcat messages from application. This behavior can be disabled in the "Logcat output" section of the "Debugger" settings page. I/TensorFlowInferenceInterface: Model load took 2778ms, TensorFlow version: 1.6.0-rc1 I/TensorFlowInferenceInterface: Successfully loaded model from 'file:///android_asset/tiny-yolo-voc-graph.pb' I/YOLO: Sensor orientation: 90, Screen orientation: 0 I/YOLO: Initializing at size 640x480 E/CheckPermission: camera-code= 11 E/CheckPermission: camera-code= 10 E/CheckPermission: camera-code= 2 E/CheckPermission: camera-code= 11 I/CameraManager: Using legacy camera HAL. D/Camera: mHypnusCtrl is true E/CheckPermission: camera-code= 5 E/CheckPermission: camera-code= 2 E/CheckPermission: real_camera-code= 12 E/CheckPermission: camera-code= 1 E/CheckPermission: camera-code= 1 E/CheckPermission: camera-code= 2 E/CheckPermission: real_camera-code= 11 I/YOLO: Opening camera preview: 640x480 I/CameraDeviceState: Legacy camera service transitioning to state CONFIGURING I/RequestThread-0: Configure outputs: 2 surfaces configured. D/Camera: app passed NULL surface E/CheckPermission: real_camera-code= 2 E/CheckPermission: real_camera-code= 11 E/CheckPermission: real_camera-code= 10 E/ANR_LOG: >>> msg's executing time is too long E/ANR_LOG: Blocked msg = { when=-4s790ms what=0 target=android.view.Choreographer$FrameHandler callback=android.view.Choreographer$FrameDisplayEventReceiver } , cost = 4707 ms E/ANR_LOG: >>>Current msg List is: E/ANR_LOG: Current msg <1> = { when=-4s797ms what=0 target=android.os.Handler callback=android.app.Activity$1 } E/ANR_LOG: Current msg <2> = { when=-4s784ms what=5 target=android.view.ViewRootImpl$ViewRootHandler obj=com.android.internal.os.SomeArgs@9618dbb } E/ANR_LOG: Current msg <3> = { when=-4s708ms what=13 target=android.view.ViewRootImpl$ViewRootHandler } E/ANR_LOG: Current msg <4> = { when=-4s707ms what=4 target=android.view.inputmethod.InputMethodManager$H arg1=1 } E/ANR_LOG: Current msg <5> = { when=-4s704ms what=2 target=android.view.inputmethod.InputMethodManager$H obj=InputBindResult{com.android.internal.view.IInputMethodSession$Stub$Proxy@15a82d8 com.emoji.keyboard.touchpal/com.cootek.smartinput5.TouchPalIME sequence:346 userActionNotificationSequenceNumber:2} } E/ANR_LOG: Current msg <6> = { when=-4s701ms what=0 target=android.view.ViewRootImpl$ViewRootHandler callback=android.app.ActivityThread$1 } E/ANR_LOG: Current msg <7> = { when=-4s683ms what=100 target=com.android.internal.view.IInputConnectionWrapper$MyHandler } E/ANR_LOG: Current msg <8> = { when=-4s683ms what=65 target=com.android.internal.view.IInputConnectionWrapper$MyHandler } E/ANR_LOG: Current msg <9> = { when=-4s681ms barrier=2 } E/ANR_LOG: Current msg <10> = { when=-4s439ms what=149 target=android.app.ActivityThread$H obj=android.os.BinderProxy@3d76f8e } E/ANR_LOG: Current msg <11> = { when=+4s930ms what=132 target=android.app.ActivityThread$H } E/ANR_LOG: >>>CURRENT MSG DUMP OVER<<< I/Choreographer: Skipped 280 frames! The application may be doing too much work on its main thread. I/CameraDeviceState: Legacy camera service transitioning to state IDLE I/RequestQueue: Repeating capture request set. W/LegacyRequestMapper: convertRequestMetadata - control.awbRegions setting is not supported, ignoring value W/LegacyRequestMapper: Only received metering rectangles with weight 0. W/LegacyRequestMapper: Only received metering rectangles with weight 0. E/CheckPermission: real_camera-code= 10 E/CheckPermission: real_camera-code= 2 E/CheckPermission: real_camera-code= 5 E/CheckPermission: real_camera-code= 8 E/CheckPermission: real_camera-code= 12 E/CheckPermission: real_camera-code= 11 I/CameraDeviceState: Legacy camera service transitioning to state CAPTURING E/CheckPermission: real_camera-code= 12 E/CheckPermission: real_camera-code= 12 E/CheckPermission: real_camera-code= 12 E/CheckPermission: real_camera-code= 12 E/TensorFlowInferenceInterface: Failed to run TensorFlow inference with inputs:[input], outputs:[output] E/AndroidRuntime: FATAL EXCEPTION: inference Process: org.tensorflow.yolo, PID: 13342 java.lang.IllegalArgumentException: No OpKernel was registered to support Op 'ExtractImagePatches' with these attrs. Registered devices: [CPU], Registered kernels:

[[Node: ExtractImagePatches = ExtractImagePatches[T=DT_FLOAT, ksizes=[1, 2, 2, 1], padding="VALID", rates=[1, 1, 1, 1], strides=[1, 2, 2, 1]](47-leaky)]] at org.tensorflow.Session.run(Native Method) at org.tensorflow.Session.access$100(Session.java:48) at org.tensorflow.Session$Runner.runHelper(Session.java:298) at org.tensorflow.Session$Runner.run(Session.java:248) at org.tensorflow.contrib.android.TensorFlowInferenceInterface.run(TensorFlowInferenceInterface.java:230) at org.tensorflow.contrib.android.TensorFlowInferenceInterface.run(TensorFlowInferenceInterface.java:197) at org.tensorflow.contrib.android.TensorFlowInferenceInterface.run(TensorFlowInferenceInterface.java:187) at org.tensorflow.yolo.TensorFlowImageRecognizer.runTensorFlow(TensorFlowImageRecognizer.java:67) at org.tensorflow.yolo.TensorFlowImageRecognizer.recognizeImage(TensorFlowImageRecognizer.java:50) at org.tensorflow.yolo.view.ClassifierActivity.lambda$onImageAvailable$1$ClassifierActivity(ClassifierActivity.java:107) at org.tensorflow.yolo.view.ClassifierActivity$$Lambda$1.run(Unknown Source) at android.os.Handler.handleCallback(Handler.java:751) at android.os.Handler.dispatchMessage(Handler.java:95) at android.os.Looper.loop(Looper.java:185) at android.os.HandlerThread.run(HandlerThread.java:61)
balaji199823 commented 4 years ago

hello szaza i have changed the .pb as well as the label.txt file then the app is build but wen i open the app it stop directly i didnt get any error but the yolo_tiny-obj_last.weight file detect by objects and i converted as per ur instructions to .pb file then also it is not working in ur android gradle. plz i want ur help plz reply me as soon as possible my email id: hp31jul@gmail.com