在 Android 上使用以 AutoML 訓練的模型為圖片加上標籤

訓練自己的模型後 透過 AutoML Vision Edge,在應用程式中將其用於加上標籤 所以映像檔較小

事前準備

  1. 如果還沒試過 將 Firebase 新增至您的 Android 專案
  2. 將 ML Kit Android 程式庫的依附元件新增至模組 (應用程式層級) Gradle 檔案 (通常是 app/build.gradle):
    apply plugin: 'com.android.application'
    apply plugin: 'com.google.gms.google-services'
    
    dependencies {
      // ...
    
      implementation 'com.google.firebase:firebase-ml-vision:24.0.3'
      implementation 'com.google.firebase:firebase-ml-vision-automl:18.0.5'
    }
    

1. 載入模型

ML Kit 會在裝置上執行 AutoML 產生的模型。不過, 設定 ML Kit,以便從 Firebase 遠端載入模型 或兩者皆是

在 Firebase 中託管模型後,您就能在不發布的情況下更新模型 新的應用程式版本 運用遠端設定和 A/B 測試功能 為不同的使用者群組動態提供不同的模型。

如果您選擇僅透過 Firebase 託管模型,而非 就能縮減應用程式的初始下載大小。 不過請注意,如果模型未隨附於您的應用程式 您的應用程式必須下載 首次訓練模型

將模型與應用程式搭配使用,就能確保應用程式的機器學習功能 Firebase 託管的模型無法使用時仍能正常運作。

設定 Firebase 託管的模型來源

如要使用遠端託管的模型,請建立 FirebaseAutoMLRemoteModel 物件。 請指定您在發布模型時為其指派的名稱:

Java

// Specify the name you assigned in the Firebase console.
FirebaseAutoMLRemoteModel remoteModel =
    new FirebaseAutoMLRemoteModel.Builder("your_remote_model").build();

Kotlin+KTX

// Specify the name you assigned in the Firebase console.
val remoteModel = FirebaseAutoMLRemoteModel.Builder("your_remote_model").build()

接著,啟動模型下載工作,並指定在 您要允許下載的應用程式。如果裝置上沒有該型號,或者是新型號 就能以非同步方式下載該模型 建立 Vertex AI 模型

Java

FirebaseModelDownloadConditions conditions = new FirebaseModelDownloadConditions.Builder()
        .requireWifi()
        .build();
FirebaseModelManager.getInstance().download(remoteModel, conditions)
        .addOnCompleteListener(new OnCompleteListener<Void>() {
            @Override
            public void onComplete(@NonNull Task<Void> task) {
                // Success.
            }
        });

Kotlin+KTX

val conditions = FirebaseModelDownloadConditions.Builder()
    .requireWifi()
    .build()
FirebaseModelManager.getInstance().download(remoteModel, conditions)
    .addOnCompleteListener {
        // Success.
    }

許多應用程式會在初始化程式碼中啟動下載工作,���您 這個模型會在您需要使用模型前執行

設定本機模型來源

將模型與應用程式組合如下:

  1. 從下載的 ZIP 封存檔中,擷取模型及其中繼資料 建議你使用已下載的檔案 且未經修改 (包括檔案名稱)。
  2. 將模型及其中繼資料檔案納入應用程式套件:

    1. 如果專案沒有素材資源資料夾,請按照 在 app/ 資料夾上按一下滑鼠右鍵,然後點選 新增 >資料夾 >素材資源資料夾
    2. 在素材資源資料夾底下建立子資料夾,用來存放模型 檔案。
    3. 複製 model.tflitedict.txtmanifest.json 至子資料夾 (這三個檔案都必須位於 相同資料夾)。
  3. 請將以下內容新增至應用程式的 build.gradle 檔案,確保 Gradle 不會在建構應用程式時壓縮模型檔案:
    android {
        // ...
        aaptOptions {
            noCompress "tflite"
        }
    }
    
    模型檔案將包含在應用程式套件中,並可供 ML Kit 使用 做為原始素材資源
  4. 建立 FirebaseAutoMLLocalModel 物件,指定模型資訊清單的路徑 檔案:

    Java

    FirebaseAutoMLLocalModel localModel = new FirebaseAutoMLLocalModel.Builder()
            .setAssetFilePath("manifest.json")
            .build();
    

    Kotlin+KTX

    val localModel = FirebaseAutoMLLocalModel.Builder()
            .setAssetFilePath("manifest.json")
            .build()
    

從模型建立圖片標籤工具

設定模型來源後,請建立 FirebaseVisionImageLabeler 擷取的物件

如果您只有本機組合模型,只要從 FirebaseAutoMLLocalModel 物件,並設定可信度分數門檻 (請參閱評估模型):

Java

FirebaseVisionImageLabeler labeler;
try {
    FirebaseVisionOnDeviceAutoMLImageLabelerOptions options =
            new FirebaseVisionOnDeviceAutoMLImageLabelerOptions.Builder(localModel)
                    .setConfidenceThreshold(0.0f)  // Evaluate your model in the Firebase console
                                                   // to determine an appropriate value.
                    .build();
    labeler = FirebaseVision.getInstance().getOnDeviceAutoMLImageLabeler(options);
} catch (FirebaseMLException e) {
    // ...
}

Kotlin+KTX

val options = FirebaseVisionOnDeviceAutoMLImageLabelerOptions.Builder(localModel)
    .setConfidenceThreshold(0)  // Evaluate your model in the Firebase console
                                // to determine an appropriate value.
    .build()
val labeler = FirebaseVision.getInstance().getOnDeviceAutoMLImageLabeler(options)

如果您使用的是遠端託管的模型,則須檢查該模型是否已 執行前已下載完成您可以查看模型下載狀態 使用模型管理員的 isModelDownloaded() 方法完成任務

雖然您不必在執行標籤人員前確認 同時擁有遠端託管和本機封裝模型 將圖片標籤人員例���化時,要���行這項檢查:請建立 從遠端模型下載標籤人員 反之。

Java

FirebaseModelManager.getInstance().isModelDownloaded(remoteModel)
        .addOnSuccessListener(new OnSuccessListener<Boolean>() {
            @Override
            public void onSuccess(Boolean isDownloaded) {
                FirebaseVisionOnDeviceAutoMLImageLabelerOptions.Builder optionsBuilder;
                if (isDownloaded) {
                    optionsBuilder = new FirebaseVisionOnDeviceAutoMLImageLabelerOptions.Builder(remoteModel);
                } else {
                    optionsBuilder = new FirebaseVisionOnDeviceAutoMLImageLabelerOptions.Builder(localModel);
                }
                FirebaseVisionOnDeviceAutoMLImageLabelerOptions options = optionsBuilder
                        .setConfidenceThreshold(0.0f)  // Evaluate your model in the Firebase console
                                                       // to determine an appropriate threshold.
                        .build();

                FirebaseVisionImageLabeler labeler;
                try {
                    labeler = FirebaseVision.getInstance().getOnDeviceAutoMLImageLabeler(options);
                } catch (FirebaseMLException e) {
                    // Error.
                }
            }
        });

Kotlin+KTX

FirebaseModelManager.getInstance().isModelDownloaded(remoteModel)
    .addOnSuccessListener { isDownloaded -> 
    val optionsBuilder =
        if (isDownloaded) {
            FirebaseVisionOnDeviceAutoMLImageLabelerOptions.Builder(remoteModel)
        } else {
            FirebaseVisionOnDeviceAutoMLImageLabelerOptions.Builder(localModel)
        }
    // Evaluate your model in the Firebase console to determine an appropriate threshold.
    val options = optionsBuilder.setConfidenceThreshold(0.0f).build()
    val labeler = FirebaseVision.getInstance().getOnDeviceAutoMLImageLabeler(options)
}

如果只有遠端託管的模型,請停用模型相關 或隱藏部分 UI,直到 您確認模型已下載完成附加監聽器即可 變更為模型管理工具的 download() 方法:

Java

FirebaseModelManager.getInstance().download(remoteModel, conditions)
        .addOnSuccessListener(new OnSuccessListener<Void>() {
            @Override
            public void onSuccess(Void v) {
              // Download complete. Depending on your app, you could enable
              // the ML feature, or switch from the local model to the remote
              // model, etc.
            }
        });

Kotlin+KTX

FirebaseModelManager.getInstance().download(remoteModel, conditions)
    .addOnCompleteListener {
        // Download complete. Depending on your app, you could enable the ML
        // feature, or switch from the local model to the remote model, etc.
    }

2. 準備輸入圖片

接著,為要加上標籤的每張圖片建立 FirebaseVisionImage 物件。 運用本節所描述的其中一個選項,並傳遞給 FirebaseVisionImageLabeler (下節將說明)。

您可以從 media.Image 物件建立 FirebaseVisionImage 物件、 暫存器、位元組陣列或 Bitmap 物件:

  • 如何透過FirebaseVisionImage media.Image 物件,例如從 裝置的相機,請傳遞 media.Image 物件和圖片的 旋轉至 FirebaseVisionImage.fromMediaImage()

    如果您使用 CameraX 程式庫、OnImageCapturedListenerImageAnalysis.Analyzer 類別會計算旋轉值 因此只需將旋轉模型 轉換為 ML Kit 的 呼叫前 ROTATION_ 常數 FirebaseVisionImage.fromMediaImage()

    Java

    private class YourAnalyzer implements ImageAnalysis.Analyzer {
    
        private int degreesToFirebaseRotation(int degrees) {
            switch (degrees) {
                case 0:
                    return FirebaseVisionImageMetadata.ROTATION_0;
                case 90:
                    return FirebaseVisionImageMetadata.ROTATION_90;
                case 180:
                    return FirebaseVisionImageMetadata.ROTATION_180;
                case 270:
                    return FirebaseVisionImageMetadata.ROTATION_270;
                default:
                    throw new IllegalArgumentException(
                            "Rotation must be 0, 90, 180, or 270.");
            }
        }
    
        @Override
        public void analyze(ImageProxy imageProxy, int degrees) {
            if (imageProxy == null || imageProxy.getImage() == null) {
                return;
            }
            Image mediaImage = imageProxy.getImage();
            int rotation = degreesToFirebaseRotation(degrees);
            FirebaseVisionImage image =
                    FirebaseVisionImage.fromMediaImage(mediaImage, rotation);
            // Pass image to an ML Kit Vision API
            // ...
        }
    }
    

    Kotlin+KTX

    private class YourImageAnalyzer : ImageAnalysis.Analyzer {
        private fun degreesToFirebaseRotation(degrees: Int): Int = when(degrees) {
            0 -> FirebaseVisionImageMetadata.ROTATION_0
            90 -> FirebaseVisionImageMetadata.ROTATION_90
            180 -> FirebaseVisionImageMetadata.ROTATION_180
            270 -> FirebaseVisionImageMetadata.ROTATION_270
            else -> throw Exception("Rotation must be 0, 90, 180, or 270.")
        }
    
        override fun analyze(imageProxy: ImageProxy?, degrees: Int) {
            val mediaImage = imageProxy?.image
            val imageRotation = degreesToFirebaseRotation(degrees)
            if (mediaImage != null) {
                val image = FirebaseVisionImage.fromMediaImage(mediaImage, imageRotation)
                // Pass image to an ML Kit Vision API
                // ...
            }
        }
    }
    

    如果您沒有使用相機程式庫來提供圖像旋轉角度, 可根據裝置旋轉角度和相機方向計算 感應器:

    Java

    private static final SparseIntArray ORIENTATIONS = new SparseIntArray();
    static {
        ORIENTATIONS.append(Surface.ROTATION_0, 90);
        ORIENTATIONS.append(Surface.ROTATION_90, 0);
        ORIENTATIONS.append(Surface.ROTATION_180, 270);
        ORIENTATIONS.append(Surface.ROTATION_270, 180);
    }
    
    /**
     * Get the angle by which an image must be rotated given the device's current
     * orientation.
     */
    @RequiresApi(api = Build.VERSION_CODES.LOLLIPOP)
    private int getRotationCompensation(String cameraId, Activity activity, Context context)
            throws CameraAccessException {
        // Get the device's current rotation relative to its "native" orientation.
        // Then, from the ORIENTATIONS table, look up the angle the image must be
        // rotated to compensate for the device's rotation.
        int deviceRotation = activity.getWindowManager().getDefaultDisplay().getRotation();
        int rotationCompensation = ORIENTATIONS.get(deviceRotation);
    
        // On most devices, the sensor orientation is 90 degrees, but for some
        // devices it is 270 degrees. For devices with a sensor orientation of
        // 270, rotate the image an additional 180 ((270 + 270) % 360) degrees.
        CameraManager cameraManager = (CameraManager) context.getSystemService(CAMERA_SERVICE);
        int sensorOrientation = cameraManager
                .getCameraCharacteristics(cameraId)
                .get(CameraCharacteristics.SENSOR_ORIENTATION);
        rotationCompensation = (rotationCompensation + sensorOrientation + 270) % 360;
    
        // Return the corresponding FirebaseVisionImageMetadata rotation value.
        int result;
        switch (rotationCompensation) {
            case 0:
                result = FirebaseVisionImageMetadata.ROTATION_0;
                break;
            case 90:
                result = FirebaseVisionImageMetadata.ROTATION_90;
                break;
            case 180:
                result = FirebaseVisionImageMetadata.ROTATION_180;
                break;
            case 270:
                result = FirebaseVisionImageMetadata.ROTATION_270;
                break;
            default:
                result = FirebaseVisionImageMetadata.ROTATION_0;
                Log.e(TAG, "Bad rotation value: " + rotationCompensation);
        }
        return result;
    }

    Kotlin+KTX

    private val ORIENTATIONS = SparseIntArray()
    
    init {
        ORIENTATIONS.append(Surface.ROTATION_0, 90)
        ORIENTATIONS.append(Surface.ROTATION_90, 0)
        ORIENTATIONS.append(Surface.ROTATION_180, 270)
        ORIENTATIONS.append(Surface.ROTATION_270, 180)
    }
    /**
     * Get the angle by which an image must be rotated given the device's current
     * orientation.
     */
    @RequiresApi(api = Build.VERSION_CODES.LOLLIPOP)
    @Throws(CameraAccessException::class)
    private fun getRotationCompensation(cameraId: String, activity: Activity, context: Context): Int {
        // Get the device's current rotation relative to its "native" orientation.
        // Then, from the ORIENTATIONS table, look up the angle the image must be
        // rotated to compensate for the device's rotation.
        val deviceRotation = activity.windowManager.defaultDisplay.rotation
        var rotationCompensation = ORIENTATIONS.get(deviceRotation)
    
        // On most devices, the sensor orientation is 90 degrees, but for some
        // devices it is 270 degrees. For devices with a sensor orientation of
        // 270, rotate the image an additional 180 ((270 + 270) % 360) degrees.
        val cameraManager = context.getSystemService(CAMERA_SERVICE) as CameraManager
        val sensorOrientation = cameraManager
                .getCameraCharacteristics(cameraId)
                .get(CameraCharacteristics.SENSOR_ORIENTATION)!!
        rotationCompensation = (rotationCompensation + sensorOrientation + 270) % 360
    
        // Return the corresponding FirebaseVisionImageMetadata rotation value.
        val result: Int
        when (rotationCompensation) {
            0 -> result = FirebaseVisionImageMetadata.ROTATION_0
            90 -> result = FirebaseVisionImageMetadata.ROTATION_90
            180 -> result = FirebaseVisionImageMetadata.ROTATION_180
            270 -> result = FirebaseVisionImageMetadata.ROTATION_270
            else -> {
                result = FirebaseVisionImageMetadata.ROTATION_0
                Log.e(TAG, "Bad rotation value: $rotationCompensation")
            }
        }
        return result
    }

    然後,請傳遞 media.Image 物件和 將旋轉值轉換為 FirebaseVisionImage.fromMediaImage()

    Java

    FirebaseVisionImage image = FirebaseVisionImage.fromMediaImage(mediaImage, rotation);

    Kotlin+KTX

    val image = FirebaseVisionImage.fromMediaImage(mediaImage, rotation)
  • 如要從檔案 URI 建立 FirebaseVisionImage 物件,請傳遞 應用程式環境和檔案 URI FirebaseVisionImage.fromFilePath()。如果您要 使用 ACTION_GET_CONTENT 意圖提示使用者選取 取自圖片庫應用程式中的圖片。

    Java

    FirebaseVisionImage image;
    try {
        image = FirebaseVisionImage.fromFilePath(context, uri);
    } catch (IOException e) {
        e.printStackTrace();
    }

    Kotlin+KTX

    val image: FirebaseVisionImage
    try {
        image = FirebaseVisionImage.fromFilePath(context, uri)
    } catch (e: IOException) {
        e.printStackTrace()
    }
  • 如何透過FirebaseVisionImage ByteBuffer 或位元組陣列,請先計算圖片 旋轉 (方法如上所述) media.Image 輸入欄位。

    接著建立 FirebaseVisionImageMetadata 物件 包含圖片的高度、寬度、色彩編碼格式 和輪替金鑰

    Java

    FirebaseVisionImageMetadata metadata = new FirebaseVisionImageMetadata.Builder()
            .setWidth(480)   // 480x360 is typically sufficient for
            .setHeight(360)  // image recognition
            .setFormat(FirebaseVisionImageMetadata.IMAGE_FORMAT_NV21)
            .setRotation(rotation)
            .build();

    Kotlin+KTX

    val metadata = FirebaseVisionImageMetadata.Builder()
            .setWidth(480) // 480x360 is typically sufficient for
            .setHeight(360) // image recognition
            .setFormat(FirebaseVisionImageMetadata.IMAGE_FORMAT_NV21)
            .setRotation(rotation)
            .build()

    使用緩衝區或陣列和中繼資料物件 FirebaseVisionImage 物件:

    Java

    FirebaseVisionImage image = FirebaseVisionImage.fromByteBuffer(buffer, metadata);
    // Or: FirebaseVisionImage image = FirebaseVisionImage.fromByteArray(byteArray, metadata);

    Kotlin+KTX

    val image = FirebaseVisionImage.fromByteBuffer(buffer, metadata)
    // Or: val image = FirebaseVisionImage.fromByteArray(byteArray, metadata)
  • 如何透過FirebaseVisionImage Bitmap 物件:

    Java

    FirebaseVisionImage image = FirebaseVisionImage.fromBitmap(bitmap);

    Kotlin+KTX

    val image = FirebaseVisionImage.fromBitmap(bitmap)
    Bitmap 物件代表的圖片必須 保持直立,不用另外旋轉。

3. 執行映像檔標籤工具

如要為圖片中的物件加上標籤,請將 FirebaseVisionImage 物件傳遞至 FirebaseVisionImageLabelerprocessImage() 方法。

Java

labeler.processImage(image)
        .addOnSuccessListener(new OnSuccessListener<List<FirebaseVisionImageLabel>>() {
            @Override
            public void onSuccess(List<FirebaseVisionImageLabel> labels) {
                // Task completed successfully
                // ...
            }
        })
        .addOnFailureListener(new OnFailureListener() {
            @Override
            public void onFailure(@NonNull Exception e) {
                // Task failed with an exception
                // ...
            }
        });

Kotlin+KTX

labeler.processImage(image)
        .addOnSuccessListener { labels ->
            // Task completed successfully
            // ...
        }
        .addOnFailureListener { e ->
            // Task failed with an exception
            // ...
        }

如果圖片標籤成功,系統會傳回 FirebaseVisionImageLabel 物件陣列 就會傳遞到成功事件監聽器。在每個物件中,您可以 圖片中辨識功能的相關資訊。

例如:

Java

for (FirebaseVisionImageLabel label: labels) {
    String text = label.getText();
    float confidence = label.getConfidence();
}

Kotlin+KTX

for (label in labels) {
    val text = label.text
    val confidence = label.confidence
}

即時效能改善訣竅

  • 限制對偵測工具的呼叫。如果新的影片影格 因此請在偵測器執行時捨棄影格。
  • 使用偵測工具的輸出內容將圖像重疊 先從 ML Kit 取得結果,然後算繪圖片 並疊加單一步驟這麼一來,您的應用程式就會算繪到顯示途徑 每個輸入影格只能建立一次
  • 如果你使用 Camera2 API, ImageFormat.YUV_420_888 格式。

    如果使用舊版 Camera API,請以 ImageFormat.NV21 格式。