dönüştürme coreml ve iOS11 <a href="https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html" rel="nofollow noreferrer">https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html</a> bulunan öğretici kullanarak

Question

entegre etmek Keras görüntü sınıflandırma modeli eğitimli, ben kedi ve köpek arasındaki farkı tanıyan bir Keras modeli eğitimli. coremltools bir kılavuz olarak documentation Kullanılması

''' 
Directory structure: 

data/ 
    train/ 
     dogs/ 
      dog001.jpg 
      dog002.jpg 
      ... 
     cats/ 
      cat001.jpg 
      cat002.jpg 
      ... 
    validation/ 
     dogs/ 
      dog001.jpg 
      dog002.jpg 
      ... 
     cats/ 
      cat001.jpg 
      cat002.jpg 
      ... 
'''  
from keras.preprocessing.image import ImageDataGenerator 
from keras.models import Sequential 
from keras.layers import Conv2D, MaxPooling2D 
from keras.layers import Activation, Dropout, Flatten, Dense 
from keras import backend as K 
from PIL import Image 
import numpy as np 

# dimensions of our images. 
img_width, img_height = 150, 150 

train_data_dir = 'data/train' 
validation_data_dir = 'data/validation' 
nb_train_samples = 2000 
nb_validation_samples = 800 
epochs = 50 
batch_size = 16 

if K.image_data_format() == 'channels_first': 
    input_shape = (3, img_width, img_height) 
else: 
    input_shape = (img_width, img_height, 3) 

model = Sequential() 
model.add(Conv2D(32, (3, 3), input_shape=input_shape)) 
model.add(Activation('relu')) 
model.add(MaxPooling2D(pool_size=(2, 2))) 

model.add(Conv2D(32, (3, 3))) 
model.add(Activation('relu')) 
model.add(MaxPooling2D(pool_size=(2, 2))) 

model.add(Conv2D(64, (3, 3))) 
model.add(Activation('relu')) 
model.add(MaxPooling2D(pool_size=(2, 2))) 

model.add(Flatten()) 
model.add(Dense(64)) 
model.add(Activation('relu')) 
model.add(Dropout(0.5)) 
model.add(Dense(1)) 
model.add(Activation('sigmoid')) 

model.compile(loss='binary_crossentropy', 
       optimizer='rmsprop', 
       metrics=['accuracy']) 

# this is the augmentation configuration we will use for training 
train_datagen = ImageDataGenerator(
    rescale=1./255, 
    shear_range=0.2, 
    zoom_range=0.2, 
    horizontal_flip=True) 

# this is the augmentation configuration we will use for testing: 
# only rescaling 
test_datagen = ImageDataGenerator(rescale=1./255) 

train_generator = train_datagen.flow_from_directory(
    train_data_dir, 
    target_size=(img_width, img_height), 
    batch_size=batch_size, 
    class_mode='binary') 

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir, 
    target_size=(img_width, img_height), 
    batch_size=batch_size, 
    class_mode='binary') 

model.fit_generator(
    train_generator, 
    steps_per_epoch=nb_train_samples // batch_size, 
    epochs=epochs, 
    validation_data=validation_generator, 
    validation_steps=nb_validation_samples // batch_size) 

model.save('first_try.h5') 

, ben coreml biçimine Modelimin dönüştürme çalıştı:

import coremltools 
import h5py 
coreml_model = coremltools.converters.keras.convert('first_try.h5',input_names='image',output_names='class',image_input_names = 'image',class_labels = ['cat', 'dog'], is_bgr=True) 
coreml_model.save('cats_dogs.mlmodel') 

ben XCode içine modeli içe ve birlikte çalışır aşağıdaki kodla (ile çalıştırdığınızda Apple'ın web sitesinde bulunan resnet50 ve inceptionv3 modelleri), kod snippet'i guard let prediction = try? model.prediction(image: pixelBuffer!) else {print("error!") return } "hata!" yazdırıyor. ve textView.text = "I think this is a \(String(describing: prediction.classLabel))." kod snippet'ine asla ulaşılamıyor.

XCode Error Implementing Custom Keras-CoreML model

ben yoğun bu sorunu çözmek için StackOverflow'daki aramış

import UIKit 
    import Vision 
    import CoreML 

    class ViewController: UIViewController, UINavigationControllerDelegate { 

     //MARK: - Properties 


     @IBOutlet weak var imageView: UIImageView! 
     @IBOutlet weak var textView: UITextView! 

     let imagePicker = UIImagePickerController() 

     //MARK: - ViewController 

     override func viewDidLoad() { 
      super .viewDidLoad() 
      self.imagePicker.delegate = self 
     } 

     @IBAction func openImagePicker(_ sender: Any) { 
      imagePicker.allowsEditing = false 
      imagePicker.sourceType = .photoLibrary 
      present(imagePicker, animated: true, completion: nil) 
     } 

     @IBAction func camera(_ sender: Any) { 

      if !UIImagePickerController.isSourceTypeAvailable(.camera) { 
       return 
      } 

      let cameraPicker = UIImagePickerController() 
      cameraPicker.delegate = self 
      cameraPicker.sourceType = .camera 
      cameraPicker.allowsEditing = false 

      present(cameraPicker, animated: true) 
     } 

    } 

    extension ViewController: UIImagePickerControllerDelegate { 
     func imagePickerControllerDidCancel(_ picker: UIImagePickerController) { 
      dismiss(animated: true, completion: nil) 
     } 

     func imagePickerController(_ picker: UIImagePickerController, didFinishPickingMediaWithInfo info: [String : Any]) { 
      picker.dismiss(animated: true) 
      textView.text = "Analyzing Image..." 
      guard let image = info["UIImagePickerControllerOriginalImage"] as? UIImage else { 
       return 
      } 

      UIGraphicsBeginImageContextWithOptions(CGSize(width: 150, height: 150), true, 2.0) 
      image.draw(in: CGRect(x: 0, y: 0, width: 150, height: 150)) 
      let newImage = UIGraphicsGetImageFromCurrentImageContext()! 
      UIGraphicsEndImageContext() 

      let attrs = [kCVPixelBufferCGImageCompatibilityKey: kCFBooleanTrue, kCVPixelBufferCGBitmapContextCompatibilityKey: kCFBooleanTrue] as CFDictionary 
      var pixelBuffer : CVPixelBuffer? 
      let status = CVPixelBufferCreate(kCFAllocatorDefault, Int(newImage.size.width), Int(newImage.size.height), kCVPixelFormatType_32ARGB, attrs, &pixelBuffer) 
      guard (status == kCVReturnSuccess) else { 
       return 
      } 

      CVPixelBufferLockBaseAddress(pixelBuffer!, CVPixelBufferLockFlags(rawValue: 0)) 
      let pixelData = CVPixelBufferGetBaseAddress(pixelBuffer!) 

      let rgbColorSpace = CGColorSpaceCreateDeviceRGB() 
      let context = CGContext(data: pixelData, width: Int(newImage.size.width), height: Int(newImage.size.height), bitsPerComponent: 8, bytesPerRow: CVPixelBufferGetBytesPerRow(pixelBuffer!), space: rgbColorSpace, bitmapInfo: CGImageAlphaInfo.noneSkipFirst.rawValue) //3 

      context?.translateBy(x: 0, y: newImage.size.height) 
      context?.scaleBy(x: 1.0, y: -1.0) 

      UIGraphicsPushContext(context!) 
      newImage.draw(in: CGRect(x: 0, y: 0, width: newImage.size.width, height: newImage.size.height)) 
      UIGraphicsPopContext() 
      CVPixelBufferUnlockBaseAddress(pixelBuffer!, CVPixelBufferLockFlags(rawValue: 0)) 
      imageView.image = newImage 

guard let prediction = try? model.prediction(image: pixelBuffer!) else { 
     print("error!") 
     return 
    } 
    textView.text = "I think this is a \(String(describing: prediction.classLabel))." 
     } 
    } 

. Bu sorunun düzeltilmesine yardımcı olmak çok takdir edilecektir!

================================= DÜZENLEME # 1:

"Yazdır (try! Model.prediction (image: pixelBuffer!) Any) "Aşağıdaki hatayı yazdırdım:

2017-07-13 15: 33: 49.034967-0400 cats_dogs [60441: 1198094] önemli hata: 'try!' Ifade beklenmedik biçimde bir hata ortaya çıkardı: Error Domain = com.apple.CoreML Code = 0 "Katmanın 'output' boyutları, sınıf etiketlerinin sayısıyla aynı değil." UserInfo = {NSLocalizedDescription = Katman 'çıktısının' boyutları, sınıf etiketlerinin sayısıyla aynı değildir.}:

"Katmanın boyutları 'çıktısının' sınıf etiketlerinin sayısıyla aynı boyutta olmadığından emin değil misiniz? " anlamına geliyor.

================================= =============================

Düzenleme # 2:

Bu benim dönüştürmek için kullandıkları koddur

0 : conv2d_1_input, <keras.engine.topology.InputLayer object at 0x1194c6c50> 
1 : conv2d_1, <keras.layers.convolutional.Conv2D object at 0x1194c6c90> 
2 : activation_1, <keras.layers.core.Activation object at 0x119515b90> 
3 : max_pooling2d_1, <keras.layers.pooling.MaxPooling2D object at 0x119501e50> 
4 : conv2d_2, <keras.layers.convolutional.Conv2D object at 0x119520cd0> 
5 : activation_2, <keras.layers.core.Activation object at 0x1194e8150> 
6 : max_pooling2d_2, <keras.layers.pooling.MaxPooling2D object at 0x11955cc50> 
7 : conv2d_3, <keras.layers.convolutional.Conv2D object at 0x11955ce50> 
8 : activation_3, <keras.layers.core.Activation object at 0x11954d9d0> 
9 : max_pooling2d_3, <keras.layers.pooling.MaxPooling2D object at 0x119594cd0> 
10 : flatten_1, <keras.layers.core.Flatten object at 0x1195a08d0> 
11 : dense_1, <keras.layers.core.Dense object at 0x119579f10> 
12 : activation_4, <keras.layers.core.Activation object at 0x1195c94d0> 
13 : dense_2, <keras.layers.core.Dense object at 0x1195ea450> 
14 : activation_5, <keras.layers.core.Activation object at 0x119614b10> 

input { 
    name: "image" 
    shortDescription: "Image of a cat or dog" 
    type { 
    imageType { 
     width: 150 
     height: 150 
     colorSpace: RGB 
    } 
    } 
} 
output { 
    name: "output1" 
    type { 
    dictionaryType { 
     stringKeyType { 
     } 
    } 
    } 
} 
output { 
    name: "classLabel" 
    type { 
    stringType { 
    } 
    } 
} 
predictedFeatureName: "classLabel" 
predictedProbabilitiesName: "output1" 
metadata { 
    shortDescription: "Model to classify images as either cats or dogs" 
    author: "" 
} 

Answer 1

Not sure what "Dimensions of layer 'output' is not the same size as the number of class labels" means.

: .mlmodel biçiminde

import coremltools 
import h5py 
output_labels = ['cat','dog'] 
coreml_model = coremltools.converters.keras.convert('first_try.h5',input_names='image',image_input_names = 'image',class_labels = output_labels, is_bgr=False) 
coreml_model.author = '' 
coreml_model.short_description = 'Model to classify images as either cats or dogs' 
coreml_model.input_description['image'] = 'Image of a cat or dog' 
print coreml_model 
coreml_model.save('cats_dogs.mlmodel') 

Bu terminal çıkış model

Bu modelin son katman (I boyutun 2'nin olduğunu varsayıyorum) sınıf etiketleri farklı bir boyut olduğu anlamına gelir. Bu parametreyi kaldırma öneriyoruz: Model dönüşüm

class_labels = output_labels

ve sorunu giderir görmek