使用 AutoML Vision Edge 訓練專屬模型後,即可在應用程式中使用該模型偵測圖片中的物件。
整合透過 AutoML Vision Edge 訓練的模型有兩種方式。您可以將模型檔案複製到 Xcode 專案中,藉此將模型套裝組合,也可以從 Firebase 動態下載模型。
| 模型搭售方案選項 | |
|---|---|
| 與應用程式一併提供 | 
 | 
| 託管於 Firebase | 
 | 
事前準備
- 如要下載模型,請務必將 Firebase 新增至 Apple 專案 (如果尚未新增)。如果您是將模型套裝組合,則不需要這麼做。 
- 在 Podfile 中加入 TensorFlow 和 Firebase 程式庫: - 如要將模型與應用程式組合: - Swift- pod 'TensorFlowLiteSwift'- Objective-C- pod 'TensorFlowLiteObjC'- 如要從 Firebase 動態下載模型,請新增 - Firebase/MLModelInterpreter依附元件:- Swift- pod 'TensorFlowLiteSwift' pod 'Firebase/MLModelInterpreter'- Objective-C- pod 'TensorFlowLiteObjC' pod 'Firebase/MLModelInterpreter'
- 安裝或更新專案的 Pod 後,請使用 - .xcworkspace開啟 Xcode 專案。
1. 載入模型
設定本機模型來源
如要將模型與應用程式組合在一起,請將模型和標籤檔案複製到 Xcode 專案,並務必選取「Create folder references」(建立資料夾參照)。模型檔案和標籤會納入應用程式套件。
此外,請查看與模型一併建立的 tflite_metadata.json 檔案。您需要兩個值:
- 模型的輸入維度。預設為 320x320。
- 模型可偵測到的最大數量。預設為 40。
設定 Firebase 託管的模型來源
如要使用遠端代管模型,請建立 CustomRemoteModel 物件,並指定您發布模型時指派的名稱:
Swift
let remoteModel = CustomRemoteModel(
    name: "your_remote_model"  // The name you assigned in the Google Cloud console.
)
Objective-C
FIRCustomRemoteModel *remoteModel = [[FIRCustomRemoteModel alloc]
                                     initWithName:@"your_remote_model"];
接著啟動模型下載工作,並指定允許下載的條件。如果裝置上沒有模型,或是模型有較新版本,工作會從 Firebase 非同步下載模型:
Swift
let downloadProgress = ModelManager.modelManager().download(
    remoteModel,
    conditions: ModelDownloadConditions(
        allowsCellularAccess: true,
        allowsBackgroundDownloading: true
    )
)
Objective-C
FIRModelDownloadConditions *conditions =
        [[FIRModelDownloadConditions alloc] initWithAllowsCellularAccess:YES
                                             allowsBackgroundDownloading:YES];
NSProgress *progress = [[FIRModelManager modelManager] downloadModel:remoteModel
                                                          conditions:conditions];
許多應用程式會在初始化程式碼中啟動下載工作,但您可以在需要使用模型前的任何時間點執行這項操作。
從模型建立物件偵測工具
設定模型來源後,請從其中一個來源建立 TensorFlow Lite Interpreter 物件。
如果您只有在本機封裝的模型,只要從模型檔案建立解譯器即可:
Swift
guard let modelPath = Bundle.main.path(
    forResource: "model",
    ofType: "tflite"
) else {
  print("Failed to load the model file.")
  return true
}
let interpreter = try Interpreter(modelPath: modelPath)
try interpreter.allocateTensors()
Objective-C
NSString *modelPath = [[NSBundle mainBundle] pathForResource:@"model"
                                                      ofType:@"tflite"];
NSError *error;
TFLInterpreter *interpreter = [[TFLInterpreter alloc] initWithModelPath:modelPath
                                                                  error:&error];
if (error != NULL) { return; }
[interpreter allocateTensorsWithError:&error];
if (error != NULL) { return; }
如果您有遠端代管模型,必須先確認模型已下載,才能執行。您可以使用模型管理工具的 isModelDownloaded(remoteModel:) 方法,檢查模型下載工作的狀態。
雖然您只需要在執行解譯器前確認這項資訊,但如果您同時有遠端代管模型和本機綁定模型,在例項化 Interpreter 時執行這項檢查可能很有意義:如果已下載遠端模型,請從該模型建立解譯器,否則請從本機模型建立解譯器。
Swift
var modelPath: String?
if ModelManager.modelManager().isModelDownloaded(remoteModel) {
    ModelManager.modelManager().getLatestModelFilePath(remoteModel) { path, error in
        guard error == nil else { return }
        guard let path = path else { return }
        modelPath = path
    }
} else {
    modelPath = Bundle.main.path(
        forResource: "model",
        ofType: "tflite"
    )
}
guard modelPath != nil else { return }
let interpreter = try Interpreter(modelPath: modelPath)
try interpreter.allocateTensors()
Objective-C
__block NSString *modelPath;
if ([[FIRModelManager modelManager] isModelDownloaded:remoteModel]) {
    [[FIRModelManager modelManager] getLatestModelFilePath:remoteModel
                                                completion:^(NSString * _Nullable filePath,
                                                             NSError * _Nullable error) {
        if (error != NULL) { return; }
        if (filePath == NULL) { return; }
        modelPath = filePath;
    }];
} else {
    modelPath = [[NSBundle mainBundle] pathForResource:@"model"
                                                ofType:@"tflite"];
}
NSError *error;
TFLInterpreter *interpreter = [[TFLInterpreter alloc] initWithModelPath:modelPath
                                                                  error:&error];
if (error != NULL) { return; }
[interpreter allocateTensorsWithError:&error];
if (error != NULL) { return; }
如果只有遠端託管模型,您應停用模型相關功能 (例如將部分 UI 設為灰色或隱藏),直到確認模型已下載為止。
您可以將觀察器附加至預設的通知中心,取得模型下載狀態。請務必在觀察器區塊中使用對 self 的弱參照,因為下載作業可能需要一些時間,而原始物件可能會在下載完成前釋出。例如:
Swift
NotificationCenter.default.addObserver(
    forName: .firebaseMLModelDownloadDidSucceed,
    object: nil,
    queue: nil
) { [weak self] notification in
    guard let strongSelf = self,
        let userInfo = notification.userInfo,
        let model = userInfo[ModelDownloadUserInfoKey.remoteModel.rawValue]
            as? RemoteModel,
        model.name == "your_remote_model"
        else { return }
    // The model was downloaded and is available on the device
}
NotificationCenter.default.addObserver(
    forName: .firebaseMLModelDownloadDidFail,
    object: nil,
    queue: nil
) { [weak self] notification in
    guard let strongSelf = self,
        let userInfo = notification.userInfo,
        let model = userInfo[ModelDownloadUserInfoKey.remoteModel.rawValue]
            as? RemoteModel
        else { return }
    let error = userInfo[ModelDownloadUserInfoKey.error.rawValue]
    // ...
}
Objective-C
__weak typeof(self) weakSelf = self;
[NSNotificationCenter.defaultCenter
    addObserverForName:FIRModelDownloadDidSucceedNotification
                object:nil
                 queue:nil
            usingBlock:^(NSNotification *_Nonnull note) {
              if (weakSelf == nil | note.userInfo == nil) {
                return;
              }
              __strong typeof(self) strongSelf = weakSelf;
              FIRRemoteModel *model = note.userInfo[FIRModelDownloadUserInfoKeyRemoteModel];
              if ([model.name isEqualToString:@"your_remote_model"]) {
                // The model was downloaded and is available on the device
              }
            }];
[NSNotificationCenter.defaultCenter
    addObserverForName:FIRModelDownloadDidFailNotification
                object:nil
                 queue:nil
            usingBlock:^(NSNotification *_Nonnull note) {
              if (weakSelf == nil | note.userInfo == nil) {
                return;
              }
              __strong typeof(self) strongSelf = weakSelf;
              NSError *error = note.userInfo[FIRModelDownloadUserInfoKeyError];
            }];
2. 準備輸入圖片
接著,您需要準備圖片,供 TensorFlow Lite 解譯器使用。
- 根據 - tflite_metadata.json檔案中指定的模型輸入尺寸 (預設為 320x320 像素),裁剪及縮放圖片。你可以使用 Core Image 或第三方程式庫執行這項操作
- 將圖片資料複製到 - Data(- NSData物件):- Swift- guard let image: CGImage = // Your input image guard let context = CGContext( data: nil, width: image.width, height: image.height, bitsPerComponent: 8, bytesPerRow: image.width * 4, space: CGColorSpaceCreateDeviceRGB(), bitmapInfo: CGImageAlphaInfo.noneSkipFirst.rawValue ) else { return nil } context.draw(image, in: CGRect(x: 0, y: 0, width: image.width, height: image.height)) guard let imageData = context.data else { return nil } var inputData = Data() for row in 0 ..< 320 { // Model takes 320x320 pixel images as input for col in 0 ..< 320 { let offset = 4 * (col * context.width + row) // (Ignore offset 0, the unused alpha channel) var red = imageData.load(fromByteOffset: offset+1, as: UInt8.self) var green = imageData.load(fromByteOffset: offset+2, as: UInt8.self) var blue = imageData.load(fromByteOffset: offset+3, as: UInt8.self) inputData.append(&red, count: 1) inputData.append(&green, count: 1) inputData.append(&blue, count: 1) } }- Objective-C- CGImageRef image = // Your input image long imageWidth = CGImageGetWidth(image); long imageHeight = CGImageGetHeight(image); CGContextRef context = CGBitmapContextCreate(nil, imageWidth, imageHeight, 8, imageWidth * 4, CGColorSpaceCreateDeviceRGB(), kCGImageAlphaNoneSkipFirst); CGContextDrawImage(context, CGRectMake(0, 0, imageWidth, imageHeight), image); UInt8 *imageData = CGBitmapContextGetData(context); NSMutableData *inputData = [[NSMutableData alloc] initWithCapacity:0]; for (int row = 0; row < 300; row++) { for (int col = 0; col < 300; col++) { long offset = 4 * (row * imageWidth + col); // (Ignore offset 0, the unused alpha channel) UInt8 red = imageData[offset+1]; UInt8 green = imageData[offset+2]; UInt8 blue = imageData[offset+3]; [inputData appendBytes:&red length:1]; [inputData appendBytes:&green length:1]; [inputData appendBytes:&blue length:1]; } }
3. 執行物件偵測工具
接著,將準備好的輸入內容傳遞給解譯器:
Swift
try interpreter.copy(inputData, toInputAt: 0)
try interpreter.invoke()
Objective-C
TFLTensor *input = [interpreter inputTensorAtIndex:0 error:&error];
if (error != nil) { return; }
[input copyData:inputData error:&error];
if (error != nil) { return; }
[interpreter invokeWithError:&error];
if (error != nil) { return; }
4. 取得偵測到的物件資訊
如果物件偵測成功,模型會輸出三個陣列,每個陣列有 40 個元素 (或 tflite_metadata.json 檔案中指定的元素數量)。每個元素都對應一個潛在物件。第一個陣列是定界框陣列,第二個是標籤陣列,第三個則是信賴值陣列。如要取得模型輸出內容,請按照下列步驟操作:
Swift
var output = try interpreter.output(at: 0)
let boundingBoxes =
    UnsafeMutableBufferPointer<Float32>.allocate(capacity: 4 * 40)
output.data.copyBytes(to: boundingBoxes)
output = try interpreter.output(at: 1)
let labels =
    UnsafeMutableBufferPointer<Float32>.allocate(capacity: 40)
output.data.copyBytes(to: labels)
output = try interpreter.output(at: 2)
let probabilities =
    UnsafeMutableBufferPointer<Float32>.allocate(capacity: 40)
output.data.copyBytes(to: probabilities)
Objective-C
TFLTensor *output = [interpreter outputTensorAtIndex:0 error:&error];
if (error != nil) { return; }
NSData *boundingBoxes = [output dataWithError:&error];
if (error != nil) { return; }
output = [interpreter outputTensorAtIndex:1 error:&error];
if (error != nil) { return; }
NSData *labels = [output dataWithError:&error];
if (error != nil) { return; }
output = [interpreter outputTensorAtIndex:2 error:&error];
if (error != nil) { return; }
NSData *probabilities = [output dataWithError:&error];
if (error != nil) { return; }
接著,您可以將標籤輸出內容與標籤字典合併:
Swift
guard let labelPath = Bundle.main.path(
    forResource: "dict",
    ofType: "txt"
) else { return true }
let fileContents = try? String(contentsOfFile: labelPath)
guard let labelText = fileContents?.components(separatedBy: "\n") else { return true }
for i in 0 ..< 40 {
    let top = boundingBoxes[0 * i]
    let left = boundingBoxes[1 * i]
    let bottom = boundingBoxes[2 * i]
    let right = boundingBoxes[3 * i]
    let labelIdx = Int(labels[i])
    let label = labelText[labelIdx]
    let confidence = probabilities[i]
    if confidence > 0.66 {
        print("Object found: \(label) (confidence: \(confidence))")
        print("  Top-left: (\(left),\(top))")
        print("  Bottom-right: (\(right),\(bottom))")
    }
}
Objective-C
NSString *labelPath = [NSBundle.mainBundle pathForResource:@"dict"
                                                    ofType:@"txt"];
NSString *fileContents = [NSString stringWithContentsOfFile:labelPath
                                                   encoding:NSUTF8StringEncoding
                                                      error:&error];
if (error != nil || fileContents == NULL) { return; }
NSArray<NSString*> *labelText = [fileContents componentsSeparatedByString:@"\n"];
for (int i = 0; i < 40; i++) {
    Float32 top, right, bottom, left;
    Float32 labelIdx;
    Float32 confidence;
    [boundingBoxes getBytes:&top range:NSMakeRange(16 * i + 0, 4)];
    [boundingBoxes getBytes:&left range:NSMakeRange(16 * i + 4, 4)];
    [boundingBoxes getBytes:&bottom range:NSMakeRange(16 * i + 8, 4)];
    [boundingBoxes getBytes:&right range:NSMakeRange(16 * i + 12, 4)];
    [labels getBytes:&labelIdx range:NSMakeRange(4 * i, 4)];
    [probabilities getBytes:&confidence range:NSMakeRange(4 * i, 4)];
    if (confidence > 0.5f) {
        NSString *label = labelText[(int)labelIdx];
        NSLog(@"Object detected: %@", label);
        NSLog(@"  Confidence: %f", confidence);
        NSLog(@"  Top-left: (%f,%f)", left, top);
        NSLog(@"  Bottom-right: (%f,%f)", right, bottom);
    }
}
提升即時成效的訣竅
如要在即時應用程式中標記圖片,請遵循下列指南,盡可能提高影格速率:
- 節流對偵測器的呼叫。如果偵測器執行期間有新的影片影格可用,請捨棄該影格。
- 如果您要使用偵測器的輸出內容,在輸入圖片上疊加圖像,請先取得結果,然後在單一步驟中算繪圖片並疊加圖像。這樣做的話,每個輸入影格只會轉譯到顯示表面一次。如需範例,請參閱展示範例應用程式中的 previewOverlayView 和 FIRDetectionOverlayView 類別。