學習筆記TF066:TensorFlow移動端應用，iOS、Android系統實踐

TensorFlow對Android、iOS、樹莓派都提供移動端支持。

移動端應用原理。移動端、嵌入式設備應用深度學習方式，一模型運行在雲端服務器，向服務器發送請求，接收服務器響應；二在本地運行模型，PC訓練模型，放到移動端預測。向服務端請求數據可行性差，移動端資源稀缺。本地運行實時性更好。加速計算，內存空間和速度優化。精簡模型，節省內存空間，加快計算速度。加快框架執行速度，優化模型複雜度和每步計算速度。
精簡模型，用更低權得精度，量化(quantization)、權重剪枝(weight pruning，剪小權重鏈接，把全部權值鏈接低於閾值的從網絡移除)。加速框架執行，優化矩陣通用乘法(GEMM)運算，影響卷積層(先數據im2col運行，再GEMM運算)和全鏈接層。im2col，索引圖像塊重排列爲矩陣列。先將大矩陣重疊劃分多個子矩陣，每一個子矩陣序列化成向量，獲得另外一個矩陣。

量化(quantitative)。《How to Quantize Neural Networks with TensorFlow》https://www.tensorflow.org/pe... 。離散化。用比32位浮點數更少空間存儲、運行模型，TensorFlow量化實現屏蔽存儲、運行細節。神經網絡預測，浮點影響速度，量化加快速度，保持較高精度。減少模型文件大小。存儲模型用8位整數，加載模型運算轉換回32位浮點數。下降預測過程計算資源。神經網絡噪聲健壯笥強，量化精度損失不會危害總體準確度。訓練，反向傳播須要計算梯度，不能用低精度格式直接訓練。PC訓練浮點數模型，轉8位，移動端用8位模型預測。
量化示例。GoogleNet模型轉8位模型例子。下載訓練好GoogleNet模型，http://download.tensorflow.or... 。

bazel build tensorflow/tools/quantization:quantization_graph
bazel-bin/tensorflow/tools/quantization/quantization_graph \
--input=/tmp/classify_image_graph_def.pb \
--output_node_names="softmax" --output=/tmp/quantized_graph.pb \
--mode=eightbit

生成量化後模型大小隻有原來的1/4。執行：

bazel build tensorflow/examples/label_image:label_image
bazel-bin/tensorflow/examples/label_image/label_image \
--image=/tmp/cropped_panda.jpg \
--graph=/tmp/quantized_graph.pb \
--labels=/tmp/imagenet_synset_to_human_label_map.txt \
--input_width=299 \
--input_height=299 \
--input_mean=128 \
--input_std=128 \
--input_layer="Mul:0" \
--output_layer="softmax:0"

量化過程實現。預測操做轉換成等價8位版本操做實現。原始Relu操做，輸入、輸出浮點數。量化Relu操做，根據輸入浮點數計算最大值、最小值，進入量化(Quantize)操做輸入數據轉換8位。保證輸出層輸入數據準確性，須要反量化(Dequantize)操做，權重轉回32位精度，保證預測準確性。整個模型前向傳播用8位整數支行，最後一層加反量化層，8位轉回32位輸出層輸入。每一個量化操做後執行反量化操做。

量化數據表示。浮點數轉8位表示，是壓縮問題。權重、通過激活函數處理上層輸出，是分佈在一個範圍內的值。量化過程，找出最大值、最小值，將浮點數線性分佈，作線性擴展。

優化矩陣乘法運算。谷歌開源小型獨立低精度通用矩陣乘法(General Matrix to Matrix Multiplication,GEMM)庫 gemmlowp。https://github.com/google/gem... 。

iOS系統實踐。

環境準備。操做系統Mac OS X，集成開發工具Xcode 7.3以上版本。編譯TensorFlow核心靜態庫。tensorflow/contrib/makefiles/download_depencies.sh 。依賴庫下載到tensorflow/contrib/makefile/downloads目錄。eigen #C++開源矩陣計算工具。gemmlowp #小型獨立低精度通用矩陣乘法(GEMM)庫。googletest #谷歌開源C++測試框架。protobuf #谷歌開源數據交換格式協議。re2 #谷歌開源正則表達式庫。

編譯演示程度，運行。tensorflow/contrib/makefile/build_all_iso.sh。編譯生成靜態庫，tensorflow/contrib/makefile/gen/lib：ios_ARM6四、ios_ARMV七、ios_ARMV7S、ios_I38六、ios_X86_6四、libtensorflow-core.a。Xcode模擬器或iOS設備運行APP預測示例。TensorFlow iOS示例。https://github.com/tensorflow... 。3個目錄。benchmark目錄是預測基準示例。simple目錄是圖片預測示例。camera目錄是視頻流實時預測示例。下載Inception V1模型，能識別1000類圖片，https://storage.googleapis.co... 。解壓模型，複製到benchmark、simple、camera的data目錄。運行目錄下xcodeproj文件。選擇iPhone 7 Plus模擬器，點擊運行標誌，編譯完成點擊Run Model按鈕。預測結果見Xcode 控制檯。

自定義模型編譯、運行。https://github.com/tensorflow... 。下載花卉數據 http://download.tensorflow.or... 。鬱金香(tulips)、玫瑰(roses)、浦公英(dandelion)、向日葵(sunflowers)、雛菊(daisy)5種花卉文件目錄，各800張圖片。
訓練原始模型。下載預訓練Inception V3模型 http://download.tensorflow.or... 。

python tensorflow/examples/image_retraining/retrain.py \
--bottlenectk_dir=/tmp/bottlenecks/ \
--how_many_training_steps 10 \
--model_dir=/tmp/inception \
--output_graph=/tmp/retrained_graph.pb \
--output_labels=/tmp/retrained_labels.txt \
--image_dir /tmp/flower_photos

訓練完成，/tmp目錄有模型文件retrained_graph.pb、標籤文件上retrained_labels.txt。「瓶頸」(bottlenecks)文件，描述實際分類最終輸出層前一層(倒數第二層)。倒數第二層訓練很好，瓶頸值是有意義緊湊圖像摘要，包含足夠信息使分類選擇。第一次訓練，retrain.py文件代碼先分析全部圖片，計算每張圖片瓶頸值存儲下來。每張圖片被使用屢次，沒必要重複計算。

編譯iOS支持模型。https://petewarden.com/2016/0... 。原始模型到iOS模型，先去掉iOS系統不支持操做，優化模型，再將模型量化，權重變8位常數，縮小模型，最後模型內存映射。
去掉iOS系統不支持操做，優化模型。iOS版本TensorFlow僅支持預測階段常見沒有大外部依賴關係操做。支持操做列表：https://github.com/tensorflow... 。DecodeJpeg不支持，JPEG格式圖片解碼，依賴libjpeg。從攝像頭實時識別花卉種類，直接處理相機圖像緩衝區，不存JPEG文件再解碼。預訓練模型Inception V3 從圖片數據集訓練，包含DecodeJpeg操做。輸入數據直接提供(feed)Decode後Mul操做，繞過Decode操做。優化加速預測，顯式批處理規範化(explicit batch normalization)操做合併到卷積權重，減小計算次數。

bazel build tensorflow/python/tools:optimize_for_inference
bazel-bin/tensorflow/python/tools/optimize_for_inference \
--input=/tmp/retrained_graph.pb \
--output=/tmp/optimized_graph.pb \
--input_names=Mul \
--output_names=final_result \

label_image命令預測：

bazel-bin/tensorflow/examples/label_image/label_image \
--output_layer=final_result \
--labels=/tmp/output_labels.txt \
--image=/tmp/flower_photos/daisy/5547758_eea9edfd54_n.jpg
--graph=/tmp/output_graph.pb \
--input_layer=Mul \
--input_mean=128 \
--input_std=128 \

量化模型。蘋果系統在.ipa包分發應用程度，全部應用程度資源都用zip壓縮。模型權重從浮點數轉整數(範圍0~255)，損失準確度，小於1%。

bazel build tensorflow/tools/quantization:quantization_graph
bazel-bin/tensorflow/tools/quantization/quantization_graph \
--input=/tmp/optimized_graph.pb \
--output=/tmp/rounded_graph.pb \
--output_node_names=final_result \
--mode=weights_rounded

內存映射 memory mapping。物理內存映射到進程地址空間內，應用程序直接用輸入/輸出地址空間，提升讀寫效率。模型所有一次性加載到內存緩衝區，會對iOS RAM施加過大壓力，操做系統會殺死內存佔用過多程序。模型權值緩衝區只讀，可映射到內存。從新排列模型，權重分部分逐塊從主GraphDef加載到內存。

bazel build tensorflow/contrib/util:convert_graphdef_memmapped_format
bazel-bin/tensorflow/contrib/util/convert_graphdef_memmapped_format \
--in_graph=/tmp/rounded_graph.pb \
--out_graph=/tmp/mmapped_graph.pb

生成iOS工程文件運行。視頻流實進預測演示程序例子。https://github.com/tensorflow... 。模型文件、標記文件複製到data目錄。修改CameraExampleViewController.mm，更改加載模型文件名稱、輸入圖片尺寸、操做節點名字、縮放像素大小。

#import <AssertMacros.h>
#import <AssetsLibrary/AssetsLibrary.h>
#import <CoreImage/CoreImage.h>
#import <ImageIO/ImageIO.h>
#import "CameraExampleViewController.h"
#include <sys/time.h>
#include "tensorflow_utils.h"
// If you have your own model, modify this to the file name, and make sure
// you've added the file to your app resources too.
static NSString* model_file_name = @"tensorflow_inception_graph";
static NSString* model_file_type = @"pb";
// This controls whether we'll be loading a plain GraphDef proto, or a
// file created by the convert_graphdef_memmapped_format utility that wraps a
// GraphDef and parameter file that can be mapped into memory from file to
// reduce overall memory usage.
const bool model_uses_memory_mapping = false;
// If you have your own model, point this to the labels file.
static NSString* labels_file_name = @"imagenet_comp_graph_label_strings";
static NSString* labels_file_type = @"txt";
// These dimensions need to match those the model was trained with.
// 如下尺寸須要和模型訓練時相匹配
const int wanted_input_width =299;// 224;
const int wanted_input_height = 299;//224;
const int wanted_input_channels = 3;
const float input_mean = 128.0f;//117.0f;
const float input_std = 128.0f;//1.0f;
const std::string input_layer_name = "Mul";//"input";
const std::string output_layer_name = "final_result";//"softmax1";
static void *AVCaptureStillImageIsCapturingStillImageContext =
    &AVCaptureStillImageIsCapturingStillImageContext;
@interface CameraExampleViewController (InternalMethods)
- (void)setupAVCapture;
- (void)teardownAVCapture;
@end
@implementation CameraExampleViewController
- (void)setupAVCapture {
  NSError *error = nil;
  session = [AVCaptureSession new];
  if ([[UIDevice currentDevice] userInterfaceIdiom] ==
      UIUserInterfaceIdiomPhone)
    [session setSessionPreset:AVCaptureSessionPreset640x480];
  else
    [session setSessionPreset:AVCaptureSessionPresetPhoto];
  AVCaptureDevice *device =
      [AVCaptureDevice defaultDeviceWithMediaType:AVMediaTypeVideo];
  AVCaptureDeviceInput *deviceInput =
      [AVCaptureDeviceInput deviceInputWithDevice:device error:&error];
  assert(error == nil);
  isUsingFrontFacingCamera = NO;
  if ([session canAddInput:deviceInput]) [session addInput:deviceInput];
  stillImageOutput = [AVCaptureStillImageOutput new];
  [stillImageOutput
      addObserver:self
       forKeyPath:@"capturingStillImage"
          options:NSKeyValueObservingOptionNew
          context:(void *)(AVCaptureStillImageIsCapturingStillImageContext)];
  if ([session canAddOutput:stillImageOutput])
    [session addOutput:stillImageOutput];
  videoDataOutput = [AVCaptureVideoDataOutput new];
  NSDictionary *rgbOutputSettings = [NSDictionary
      dictionaryWithObject:[NSNumber numberWithInt:kCMPixelFormat_32BGRA]
                    forKey:(id)kCVPixelBufferPixelFormatTypeKey];
  [videoDataOutput setVideoSettings:rgbOutputSettings];
  [videoDataOutput setAlwaysDiscardsLateVideoFrames:YES];
  videoDataOutputQueue =
      dispatch_queue_create("VideoDataOutputQueue", DISPATCH_QUEUE_SERIAL);
  [videoDataOutput setSampleBufferDelegate:self queue:videoDataOutputQueue];
  if ([session canAddOutput:videoDataOutput])
    [session addOutput:videoDataOutput];
  [[videoDataOutput connectionWithMediaType:AVMediaTypeVideo] setEnabled:YES];
  previewLayer = [[AVCaptureVideoPreviewLayer alloc] initWithSession:session];
  [previewLayer setBackgroundColor:[[UIColor blackColor] CGColor]];
  [previewLayer setVideoGravity:AVLayerVideoGravityResizeAspect];
  CALayer *rootLayer = [previewView layer];
  [rootLayer setMasksToBounds:YES];
  [previewLayer setFrame:[rootLayer bounds]];
  [rootLayer addSublayer:previewLayer];
  [session startRunning];
  if (error) {
    NSString *title = [NSString stringWithFormat:@"Failed with error %d", (int)[error code]];
    UIAlertController *alertController =
        [UIAlertController alertControllerWithTitle:title
                                            message:[error localizedDescription]
                                     preferredStyle:UIAlertControllerStyleAlert];
    UIAlertAction *dismiss =
        [UIAlertAction actionWithTitle:@"Dismiss" style:UIAlertActionStyleDefault handler:nil];
    [alertController addAction:dismiss];
    [self presentViewController:alertController animated:YES completion:nil];
    [self teardownAVCapture];
  }
}
- (void)teardownAVCapture {
  [stillImageOutput removeObserver:self forKeyPath:@"isCapturingStillImage"];
  [previewLayer removeFromSuperlayer];
}
- (void)observeValueForKeyPath:(NSString *)keyPath
                      ofObject:(id)object
                        change:(NSDictionary *)change
                       context:(void *)context {
  if (context == AVCaptureStillImageIsCapturingStillImageContext) {
    BOOL isCapturingStillImage =
        [[change objectForKey:NSKeyValueChangeNewKey] boolValue];
    if (isCapturingStillImage) {
      // do flash bulb like animation
      flashView = [[UIView alloc] initWithFrame:[previewView frame]];
      [flashView setBackgroundColor:[UIColor whiteColor]];
      [flashView setAlpha:0.f];
      [[[self view] window] addSubview:flashView];
      [UIView animateWithDuration:.4f
                       animations:^{
                         [flashView setAlpha:1.f];
                       }];
    } else {
      [UIView animateWithDuration:.4f
          animations:^{
            [flashView setAlpha:0.f];
          }
          completion:^(BOOL finished) {
           [flashView removeFromSuperview];
            flashView = nil;
          }];
    }
  }
}
- (AVCaptureVideoOrientation)avOrientationForDeviceOrientation:
    (UIDeviceOrientation)deviceOrientation {
  AVCaptureVideoOrientation result =
      (AVCaptureVideoOrientation)(deviceOrientation);
  if (deviceOrientation == UIDeviceOrientationLandscapeLeft)
    result = AVCaptureVideoOrientationLandscapeRight;
  else if (deviceOrientation == UIDeviceOrientationLandscapeRight)
    result = AVCaptureVideoOrientationLandscapeLeft;
  return result;
}
- (IBAction)takePicture:(id)sender {
  if ([session isRunning]) {
    [session stopRunning];
    [sender setTitle:@"Continue" forState:UIControlStateNormal];
    flashView = [[UIView alloc] initWithFrame:[previewView frame]];
    [flashView setBackgroundColor:[UIColor whiteColor]];
    [flashView setAlpha:0.f];
    [[[self view] window] addSubview:flashView];
    [UIView animateWithDuration:.2f
        animations:^{
          [flashView setAlpha:1.f];
        }
        completion:^(BOOL finished) {
          [UIView animateWithDuration:.2f
              animations:^{
                [flashView setAlpha:0.f];
              }
              completion:^(BOOL finished) {
                [flashView removeFromSuperview];
                flashView = nil;
              }];
        }];
  } else {
    [session startRunning];
    [sender setTitle:@"Freeze Frame" forState:UIControlStateNormal];
  }
}
+ (CGRect)videoPreviewBoxForGravity:(NSString *)gravity
                          frameSize:(CGSize)frameSize
                       apertureSize:(CGSize)apertureSize {
  CGFloat apertureRatio = apertureSize.height / apertureSize.width;
  CGFloat viewRatio = frameSize.width / frameSize.height;
  CGSize size = CGSizeZero;
  if ([gravity isEqualToString:AVLayerVideoGravityResizeAspectFill]) {
    if (viewRatio > apertureRatio) {
      size.width = frameSize.width;
      size.height =
          apertureSize.width * (frameSize.width / apertureSize.height);
    } else {
      size.width =
          apertureSize.height * (frameSize.height / apertureSize.width);
      size.height = frameSize.height;
   }
  } else if ([gravity isEqualToString:AVLayerVideoGravityResizeAspect]) {
    if (viewRatio > apertureRatio) {
      size.width =
          apertureSize.height * (frameSize.height / apertureSize.width);
      size.height = frameSize.height;
    } else {
      size.width = frameSize.width;
      size.height =
          apertureSize.width * (frameSize.width / apertureSize.height);
    }
  } else if ([gravity isEqualToString:AVLayerVideoGravityResize]) {
    size.width = frameSize.width;
    size.height = frameSize.height;
  }
  CGRect videoBox;
  videoBox.size = size;
  if (size.width < frameSize.width)
    videoBox.origin.x = (frameSize.width - size.width) / 2;
  else
    videoBox.origin.x = (size.width - frameSize.width) / 2;
  if (size.height < frameSize.height)
    videoBox.origin.y = (frameSize.height - size.height) / 2;
  else
    videoBox.origin.y = (size.height - frameSize.height) / 2;
  return videoBox;
}
- (void)captureOutput:(AVCaptureOutput *)captureOutput
didOutputSampleBuffer:(CMSampleBufferRef)sampleBuffer
       fromConnection:(AVCaptureConnection *)connection {
  CVPixelBufferRef pixelBuffer = CMSampleBufferGetImageBuffer(sampleBuffer);
  CFRetain(pixelBuffer);
  [self runCNNOnFrame:pixelBuffer];
  CFRelease(pixelBuffer);
}
- (void)runCNNOnFrame:(CVPixelBufferRef)pixelBuffer {
  assert(pixelBuffer != NULL);
  OSType sourcePixelFormat = CVPixelBufferGetPixelFormatType(pixelBuffer);
  int doReverseChannels;
  if (kCVPixelFormatType_32ARGB == sourcePixelFormat) {
    doReverseChannels = 1;
  } else if (kCVPixelFormatType_32BGRA == sourcePixelFormat) {
    doReverseChannels = 0;
  } else {
    assert(false);  // Unknown source format
  }
  const int sourceRowBytes = (int)CVPixelBufferGetBytesPerRow(pixelBuffer);
  const int image_width = (int)CVPixelBufferGetWidth(pixelBuffer);
  const int fullHeight = (int)CVPixelBufferGetHeight(pixelBuffer);
  CVPixelBufferLockFlags unlockFlags = kNilOptions;
  CVPixelBufferLockBaseAddress(pixelBuffer, unlockFlags);
  unsigned char *sourceBaseAddr =
      (unsigned char *)(CVPixelBufferGetBaseAddress(pixelBuffer));
  int image_height;
  unsigned char *sourceStartAddr;
  if (fullHeight <= image_width) {
    image_height = fullHeight;
    sourceStartAddr = sourceBaseAddr;
  } else {
    image_height = image_width;
    const int marginY = ((fullHeight - image_width) / 2);
    sourceStartAddr = (sourceBaseAddr + (marginY * sourceRowBytes));
  }
  const int image_channels = 4;
  assert(image_channels >= wanted_input_channels);
  tensorflow::Tensor image_tensor(
      tensorflow::DT_FLOAT,
      tensorflow::TensorShape(
          {1, wanted_input_height, wanted_input_width, wanted_input_channels}));
  auto image_tensor_mapped = image_tensor.tensor<float, 4>();
  tensorflow::uint8 *in = sourceStartAddr;
  float *out = image_tensor_mapped.data();
  for (int y = 0; y < wanted_input_height; ++y) {
    float *out_row = out + (y * wanted_input_width * wanted_input_channels);
    for (int x = 0; x < wanted_input_width; ++x) {
      const int in_x = (y * image_width) / wanted_input_width;
      const int in_y = (x * image_height) / wanted_input_height;
      tensorflow::uint8 *in_pixel =
          in + (in_y * image_width * image_channels) + (in_x * image_channels);
      float *out_pixel = out_row + (x * wanted_input_channels);
      for (int c = 0; c < wanted_input_channels; ++c) {
        out_pixel[c] = (in_pixel[c] - input_mean) / input_std;
      }
    }
  }
  CVPixelBufferUnlockBaseAddress(pixelBuffer, unlockFlags);
  if (tf_session.get()) {
    std::vector<tensorflow::Tensor> outputs;
    tensorflow::Status run_status = tf_session->Run(
        {{input_layer_name, image_tensor}}, {output_layer_name}, {}, &outputs);
    if (!run_status.ok()) {
      LOG(ERROR) << "Running model failed:" << run_status;
    } else {
      tensorflow::Tensor *output = &outputs[0];
      auto predictions = output->flat<float>();
      NSMutableDictionary *newValues = [NSMutableDictionary dictionary];
      for (int index = 0; index < predictions.size(); index += 1) {
        const float predictionValue = predictions(index);
        if (predictionValue > 0.05f) {
          std::string label = labels[index % predictions.size()];
          NSString *labelObject = [NSString stringWithUTF8String:label.c_str()];
          NSNumber *valueObject = [NSNumber numberWithFloat:predictionValue];
          [newValues setObject:valueObject forKey:labelObject];
        }
      }
      dispatch_async(dispatch_get_main_queue(), ^(void) {
        [self setPredictionValues:newValues];
      });
    }
  }
  CVPixelBufferUnlockBaseAddress(pixelBuffer, 0);
}
- (void)dealloc {
  [self teardownAVCapture];
}
// use front/back camera
- (IBAction)switchCameras:(id)sender {
  AVCaptureDevicePosition desiredPosition;
  if (isUsingFrontFacingCamera)
    desiredPosition = AVCaptureDevicePositionBack;
  else
    desiredPosition = AVCaptureDevicePositionFront;
  for (AVCaptureDevice *d in
       [AVCaptureDevice devicesWithMediaType:AVMediaTypeVideo]) {
    if ([d position] == desiredPosition) {
      [[previewLayer session] beginConfiguration];
      AVCaptureDeviceInput *input =
          [AVCaptureDeviceInput deviceInputWithDevice:d error:nil];
      for (AVCaptureInput *oldInput in [[previewLayer session] inputs]) {
        [[previewLayer session] removeInput:oldInput];
      }
      [[previewLayer session] addInput:input];
      [[previewLayer session] commitConfiguration];
      break;
    }
  }
  isUsingFrontFacingCamera = !isUsingFrontFacingCamera;
}
- (void)didReceiveMemoryWarning {
  [super didReceiveMemoryWarning];
}
- (void)viewDidLoad {
  [super viewDidLoad];
  square = [UIImage imageNamed:@"squarePNG"];
  synth = [[AVSpeechSynthesizer alloc] init];
  labelLayers = [[NSMutableArray alloc] init];
  oldPredictionValues = [[NSMutableDictionary alloc] init];
  tensorflow::Status load_status;
  if (model_uses_memory_mapping) {
    load_status = LoadMemoryMappedModel(
        model_file_name, model_file_type, &tf_session, &tf_memmapped_env);
  } else {
    load_status = LoadModel(model_file_name, model_file_type, &tf_session);
  }
  if (!load_status.ok()) {
    LOG(FATAL) << "Couldn't load model: " << load_status;
  }
  tensorflow::Status labels_status =
      LoadLabels(labels_file_name, labels_file_type, &labels);
  if (!labels_status.ok()) {
    LOG(FATAL) << "Couldn't load labels: " << labels_status;
  }
  [self setupAVCapture];
}
- (void)viewDidUnload {
  [super viewDidUnload];
}
- (void)viewWillAppear:(BOOL)animated {
  [super viewWillAppear:animated];
}
- (void)viewDidAppear:(BOOL)animated {
  [super viewDidAppear:animated];
}
- (void)viewWillDisappear:(BOOL)animated {
  [super viewWillDisappear:animated];
}
- (void)viewDidDisappear:(BOOL)animated {
  [super viewDidDisappear:animated];
}
- (BOOL)shouldAutorotateToInterfaceOrientation:
    (UIInterfaceOrientation)interfaceOrientation {
  return (interfaceOrientation == UIInterfaceOrientationPortrait);
}
- (BOOL)prefersStatusBarHidden {
  return YES;
}
- (void)setPredictionValues:(NSDictionary *)newValues {
  const float decayValue = 0.75f;
  const float updateValue = 0.25f;
  const float minimumThreshold = 0.01f;
  NSMutableDictionary *decayedPredictionValues =
      [[NSMutableDictionary alloc] init];
  for (NSString *label in oldPredictionValues) {
    NSNumber *oldPredictionValueObject =
        [oldPredictionValues objectForKey:label];
    const float oldPredictionValue = [oldPredictionValueObject floatValue];
    const float decayedPredictionValue = (oldPredictionValue * decayValue);
    if (decayedPredictionValue > minimumThreshold) {
      NSNumber *decayedPredictionValueObject =
          [NSNumber numberWithFloat:decayedPredictionValue];
      [decayedPredictionValues setObject:decayedPredictionValueObject
                                  forKey:label];
    }
  }
  oldPredictionValues = decayedPredictionValues;
  for (NSString *label in newValues) {
    NSNumber *newPredictionValueObject = [newValues objectForKey:label];
    NSNumber *oldPredictionValueObject =
        [oldPredictionValues objectForKey:label];
    if (!oldPredictionValueObject) {
      oldPredictionValueObject = [NSNumber numberWithFloat:0.0f];
    }
    const float newPredictionValue = [newPredictionValueObject floatValue];
    const float oldPredictionValue = [oldPredictionValueObject floatValue];
    const float updatedPredictionValue =
        (oldPredictionValue + (newPredictionValue * updateValue));
    NSNumber *updatedPredictionValueObject =
        [NSNumber numberWithFloat:updatedPredictionValue];
    [oldPredictionValues setObject:updatedPredictionValueObject forKey:label];
  }
  NSArray *candidateLabels = [NSMutableArray array];
  for (NSString *label in oldPredictionValues) {
    NSNumber *oldPredictionValueObject =
        [oldPredictionValues objectForKey:label];
    const float oldPredictionValue = [oldPredictionValueObject floatValue];
    if (oldPredictionValue > 0.05f) {
      NSDictionary *entry = @{
        @"label" : label,
        @"value" : oldPredictionValueObject
      };
      candidateLabels = [candidateLabels arrayByAddingObject:entry];
    }
  }
  NSSortDescriptor *sort =
      [NSSortDescriptor sortDescriptorWithKey:@"value" ascending:NO];
  NSArray *sortedLabels = [candidateLabels
      sortedArrayUsingDescriptors:[NSArray arrayWithObject:sort]];
  const float leftMargin = 10.0f;
  const float topMargin = 10.0f;
  const float valueWidth = 48.0f;
  const float valueHeight = 26.0f;
  const float labelWidth = 246.0f;
  const float labelHeight = 26.0f;
  const float labelMarginX = 5.0f;
  const float labelMarginY = 5.0f;
  [self removeAllLabelLayers];
  int labelCount = 0;
  for (NSDictionary *entry in sortedLabels) {
    NSString *label = [entry objectForKey:@"label"];
    NSNumber *valueObject = [entry objectForKey:@"value"];
    const float value = [valueObject floatValue];
    const float originY =
        (topMargin + ((labelHeight + labelMarginY) * labelCount));
    const int valuePercentage = (int)roundf(value * 100.0f);
    const float valueOriginX = leftMargin;
    NSString *valueText = [NSString stringWithFormat:@"%d%%", valuePercentage];
    [self addLabelLayerWithText:valueText
                        originX:valueOriginX
                        originY:originY
                          width:valueWidth
                         height:valueHeight
                      alignment:kCAAlignmentRight];
    const float labelOriginX = (leftMargin + valueWidth + labelMarginX);
    [self addLabelLayerWithText:[label capitalizedString]
                        originX:labelOriginX
                        originY:originY
                          width:labelWidth
                         height:labelHeight
                      alignment:kCAAlignmentLeft];
    if ((labelCount == 0) && (value > 0.5f)) {
      [self speak:[label capitalizedString]];
    }
    labelCount += 1;
    if (labelCount > 4) {
      break;
    }
  }
}
- (void)removeAllLabelLayers {
  for (CATextLayer *layer in labelLayers) {
    [layer removeFromSuperlayer];
  }
  [labelLayers removeAllObjects];
}
- (void)addLabelLayerWithText:(NSString *)text
                      originX:(float)originX
                      originY:(float)originY
                        width:(float)width
                       height:(float)height
                    alignment:(NSString *)alignment {
  CFTypeRef font = (CFTypeRef) @"Menlo-Regular";
  const float fontSize = 20.0f;
  const float marginSizeX = 5.0f;
  const float marginSizeY = 2.0f;
  const CGRect backgroundBounds = CGRectMake(originX, originY, width, height);
  const CGRect textBounds =
      CGRectMake((originX + marginSizeX), (originY + marginSizeY),
                 (width - (marginSizeX * 2)), (height - (marginSizeY * 2)));
  CATextLayer *background = [CATextLayer layer];
  [background setBackgroundColor:[UIColor blackColor].CGColor];
  [background setOpacity:0.5f];
  [background setFrame:backgroundBounds];
  background.cornerRadius = 5.0f;
  [[self.view layer] addSublayer:background];
  [labelLayers addObject:background];
  CATextLayer *layer = [CATextLayer layer];
  [layer setForegroundColor:[UIColor whiteColor].CGColor];
  [layer setFrame:textBounds];
  [layer setAlignmentMode:alignment];
  [layer setWrapped:YES];
  [layer setFont:font];
  [layer setFontSize:fontSize];
  layer.contentsScale = [[UIScreen mainScreen] scale];
  [layer setString:text];
  [[self.view layer] addSublayer:layer];
  [labelLayers addObject:layer];
}
- (void)setPredictionText:(NSString *)text withDuration:(float)duration {
  if (duration > 0.0) {
    CABasicAnimation *colorAnimation =
        [CABasicAnimation animationWithKeyPath:@"foregroundColor"];
    colorAnimation.duration = duration;
    colorAnimation.fillMode = kCAFillModeForwards;
    colorAnimation.removedOnCompletion = NO;
    colorAnimation.fromValue = (id)[UIColor darkGrayColor].CGColor;
    colorAnimation.toValue = (id)[UIColor whiteColor].CGColor;
    colorAnimation.timingFunction =
        [CAMediaTimingFunction functionWithName:kCAMediaTimingFunctionLinear];
    [self.predictionTextLayer addAnimation:colorAnimation
                                    forKey:@"colorAnimation"];
  } else {
    self.predictionTextLayer.foregroundColor = [UIColor whiteColor].CGColor;
  }
  [self.predictionTextLayer removeFromSuperlayer];
  [[self.view layer] addSublayer:self.predictionTextLayer];
  [self.predictionTextLayer setString:text];
}
- (void)speak:(NSString *)words {
  if ([synth isSpeaking]) {
    return;
  }
  AVSpeechUtterance *utterance =
      [AVSpeechUtterance speechUtteranceWithString:words];
  utterance.voice = [AVSpeechSynthesisVoice voiceWithLanguage:@"en-US"];
  utterance.rate = 0.75 * AVSpeechUtteranceDefaultSpeechRate;
  [synth speakUtterance:utterance];
}
@end

連上iPhone手機，雙擊tensorflow/contrib/ios_examples/camera/camera_example.xcodeproj編譯運行。手機安裝好APP，打開APP，找到玫瑰花識別。訓練迭代次數10000次後，識別率99%以上。模擬器打包，生成打包工程文件位於/Users/libinggen/Library/Developer/Xcode/DeriveData/camera_example-dhfdsdfesfmrwtfb1fpfkfjsdfhdskf/Build/Products/Debug-iphoneos。打開CameraExample.app，有可執行文件CameraExample、資源文件模型文件mmapped_graph.pb、標記文件retrained_labels.txt。

Android系統實踐。

環境準備。MacBook Pro。Oracle官網下載JDK1.8版本。http://www.oracle.com/technet... 。jdk-8u111-macosx-x64.dmg。雙擊安裝。設置Java環境變量：

JAVA_HOME='/usr/libexec/java_home'
export JAVA_HOME

搭建Android SDK環境。Android官網下載Android SDK，https://developer.android.com 。25.0.2版本。android-sdk_r25.0.2-macosx.zip。解壓到~/Library/Android/sdk目錄。build-tools、extras、patcher、platform-tools #各版本SDK 根據API Level劃分SDK版本、platforms、sources、system-images、temp #臨時文件夾 在SDK更新安裝時用到、tools #各版本通用SDK工具 有adb、aapt、aidl、dx文件。
搭建Android NDK環境。Android官網下載Android NDK Mac OS X版本，https://developer.android.com... 。android-ndk-r13b-darwin-x86_64.zip文件。解壓，CHANGELOG.md、build、ndk-build、ndk-depends、ndk-gdb、ndk-stack、ndk-which、platforms、prebuilt、python-packages、shader-tools、simpleperf、source.properties、sources、toolchains。搭建Bazel。brew安裝bazel:

brew install bazel

更新bazel:

brew upgrade bazel

編譯演示程序運行。修改tensorflow-1.1.0根目錄WORKSPACE文件。android_sdk_repository、android_ndk_repository配置改成用戶本身安裝目錄、版本。

android_sdk_repository(
    name = "androidsdk",
    api_level = 25,
    build_tools_version = "25.0.2",
    # Replace with path to Android SDK on your system
    path = "~/Library/Android/sdk"
)
android_ndk_repository(
    name = "androidndk",
    api_level = 23,
    path = "~/Downloads/android-ndk-r13b"
)

在根目錄用bazel構建：

bazel build // tensorflow/examples/android:tensorflow_demo

編譯成功，默認在tensorflow-1.1.0/bazel-bin/tensorflow/examples/android目錄生成TensorFlow演示程序。
運行。生成apk文件傳輸到手機，手機攝像頭看效果。Android 6.0.1。開啓「開發者模式」。手機用數據線與計算機相連，進入SDK所在目錄，進入platform-tools文件夾，找到adb命令，執行：

./adb install tensorflow-0.12/bazel-bin/tensorflow/examples/android/tensorflow_demo.apk

tensorflow_demo.apk自動安裝到手機。打開TF Detec App。App 調起手機攝像頭，攝像頭返回數據流實時監測。

自定義模型編譯運行。訓練原始模型、編譯Android系統支持模型、生成Android apk文件運行。
訓練原始模型、編譯Android系統支持模型。用項目根目錄tensorflow/python/tools/optimize_for_inference.py、tensorflow/tools/quantization/quantize_graph.py、tensorflow/contrib/util/convert_graphdef_memmapped_format.cc對模型優化。將第一步生成原始模型文件retrained_graph.pb、標記文件retrained_labels.txt放在tensorflow/examples/android/assets目錄。修改tensorflow/examples/android/src/org/tensorflow/demo/TensorFlowImageClassifier.java要加載模型文件名稱，輸入圖片尺寸、操做節點名字、縮放像素大小。

package org.tensorflow.demo;
import android.content.res.AssetManager;
import android.graphics.Bitmap;
import android.os.Trace;
import android.util.Log;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.Comparator;
import java.util.List;
import java.util.PriorityQueue;
import java.util.Vector;
import org.tensorflow.Operation;
import org.tensorflow.contrib.android.TensorFlowInferenceInterface;
/** A classifier specialized to label images using TensorFlow. */
public class TensorFlowImageClassifier implements Classifier {
  private static final String TAG = "TensorFlowImageClassifier";
  // Only return this many results with at least this confidence.
  private static final int MAX_RESULTS = 3;
  private static final float THRESHOLD = 0.1f;
  // Config values.
  private String inputName;
  private String outputName;
  private int inputSize;
  private int imageMean;
  private float imageStd;
  // Pre-allocated buffers.
  private Vector<String> labels = new Vector<String>();
  private int[] intValues;
  private float[] floatValues;
  private float[] outputs;
  private String[] outputNames;
  private boolean logStats = false;
  private TensorFlowInferenceInterface inferenceInterface;
  private TensorFlowImageClassifier() {}
  /**
   * Initializes a native TensorFlow session for classifying images.
   *
   * @param assetManager The asset manager to be used to load assets.
   * @param modelFilename The filepath of the model GraphDef protocol buffer.
   * @param labelFilename The filepath of label file for classes.
   * @param inputSize The input size. A square image of inputSize x inputSize is assumed.
   * @param imageMean The assumed mean of the image values.
   * @param imageStd The assumed std of the image values.
   * @param inputName The label of the image input node.
   * @param outputName The label of the output node.
   * @throws IOException
   */
  public static Classifier create(
      AssetManager assetManager,
      String modelFilename,
      String labelFilename,
      int inputSize,
      int imageMean,
      float imageStd,
      String inputName,
      String outputName) {
    TensorFlowImageClassifier c = new TensorFlowImageClassifier();
    c.inputName = inputName;
    c.outputName = outputName;
    // Read the label names into memory.
    // TODO(andrewharp): make this handle non-assets.
    String actualFilename = labelFilename.split("file:///android_asset/")[1];
    Log.i(TAG, "Reading labels from: " + actualFilename);
    BufferedReader br = null;
    try {
      br = new BufferedReader(new InputStreamReader(assetManager.open(actualFilename)));
      String line;
      while ((line = br.readLine()) != null) {
        c.labels.add(line);
      }
      br.close();
    } catch (IOException e) {
      throw new RuntimeException("Problem reading label file!" , e);
    }
    c.inferenceInterface = new TensorFlowInferenceInterface(assetManager, modelFilename);
    // The shape of the output is [N, NUM_CLASSES], where N is the batch size.
    final Operation operation = c.inferenceInterface.graphOperation(outputName);
    final int numClasses = (int) operation.output(0).shape().size(1);
    Log.i(TAG, "Read " + c.labels.size() + " labels, output layer size is " + numClasses);
    // Ideally, inputSize could have been retrieved from the shape of the input operation.  Alas,
    // the placeholder node for input in the graphdef typically used does not specify a shape, so it
    // must be passed in as a parameter.
    c.inputSize = inputSize;
    c.imageMean = imageMean;
    c.imageStd = imageStd;
    // Pre-allocate buffers.
    c.outputNames = new String[] {outputName};
    c.intValues = new int[inputSize * inputSize];
    c.floatValues = new float[inputSize * inputSize * 3];
    c.outputs = new float[numClasses];
    return c;
  }
  @Override
  public List<Recognition> recognizeImage(final Bitmap bitmap) {
    // Log this method so that it can be analyzed with systrace.
    Trace.beginSection("recognizeImage");
    Trace.beginSection("preprocessBitmap");
    // Preprocess the image data from 0-255 int to normalized float based
    // on the provided parameters.
    bitmap.getPixels(intValues, 0, bitmap.getWidth(), 0, 0, bitmap.getWidth(), bitmap.getHeight());
    for (int i = 0; i < intValues.length; ++i) {
      final int val = intValues[i];
      floatValues[i * 3 + 0] = (((val >> 16) & 0xFF) - imageMean) / imageStd;
      floatValues[i * 3 + 1] = (((val >> 8) & 0xFF) - imageMean) / imageStd;
      floatValues[i * 3 + 2] = ((val & 0xFF) - imageMean) / imageStd;
    }
    Trace.endSection();
    // Copy the input data into TensorFlow.
    Trace.beginSection("feed");
    inferenceInterface.feed(inputName, floatValues, 1, inputSize, inputSize, 3);
    Trace.endSection();
    // Run the inference call.
    Trace.beginSection("run");
    inferenceInterface.run(outputNames, logStats);
    Trace.endSection();
    // Copy the output Tensor back into the output array.
    Trace.beginSection("fetch");
    inferenceInterface.fetch(outputName, outputs);
    Trace.endSection();
    // Find the best classifications.
    PriorityQueue<Recognition> pq =
        new PriorityQueue<Recognition>(
            3,
            new Comparator<Recognition>() {
              @Override
              public int compare(Recognition lhs, Recognition rhs) {
                // Intentionally reversed to put high confidence at the head of the queue.
                return Float.compare(rhs.getConfidence(), lhs.getConfidence());
              }
            });
    for (int i = 0; i < outputs.length; ++i) {
      if (outputs[i] > THRESHOLD) {
        pq.add(
            new Recognition(
                "" + i, labels.size() > i ? labels.get(i) : "unknown", outputs[i], null));
      }
    }
    final ArrayList<Recognition> recognitions = new ArrayList<Recognition>();
    int recognitionsSize = Math.min(pq.size(), MAX_RESULTS);
    for (int i = 0; i < recognitionsSize; ++i) {
      recognitions.add(pq.poll());
    }
    Trace.endSection(); // "recognizeImage"
    return recognitions;
  }
  @Override
  public void enableStatLogging(boolean logStats) {
    this.logStats = logStats;
  }
  @Override
  public String getStatString() {
    return inferenceInterface.getStatString();
  }
  @Override
  public void close() {
    inferenceInterface.close();
  }
}

從新編譯apk，鏈接Android手機，安裝apk：

bazel buld //tensorflow/examples/android:tensorflow_demo
adb install -r -g bazel-bin/tensorflow/examples/android/tensorflow_demo.apk

樹莓派實踐。

Tensorflow能夠在樹莓派(Raspberry Pi)運行。樹莓派，只有信用卡大小微型電腦，系統基於Linux，有音頻、視頻功能。應用，輸入1萬張本身的面部圖片，在樹莓派訓練人臉識別模型，教會它認識你，你進入家門後，幫你開燈、播放音樂各類功能。樹莓派編譯方法和直接在Linux環境上用類似。

參考資料：
《TensorFlow技術解析與實戰》

歡迎推薦上海機器學習工做機會，個人微信：qingxingfengzi