francoismarceau29

func predict(image: UIImage) -> Species? {
    do {
        if let resizedImage = resize(image: image, newSize: trainedImageSize), let pixelBuffer = resizedImage.toCVPixelBuffer() {
            let model = DogAndCatCNN()
            let prediction = try model.prediction(data: pixelBuffer)
            if prediction.species[0].intValue == 1 {
                return .Dog
             } else {
                return .Cat
             }

francoismarceau29

func resize(image: UIImage, newSize: CGSize) -> UIImage? {
    UIGraphicsBeginImageContextWithOptions(newSize, false, 0.0)
    image.draw(in: CGRect(x: 0, y: 0, width: newSize.width, height: newSize.height))
    let newImage = UIGraphicsGetImageFromCurrentImageContext()
    UIGraphicsEndImageContext()
    return newImage
}

francoismarceau29

func takePhotoTouched() {
    let imagePicker = UIImagePickerController()
    imagePicker.sourceType = .camera
    imagePicker.delegate = self
    imagePicker.allowsEditing = true
    present(imagePicker, animated: true, completion: nil)
}

func imagePickerControllerDidCancel(_ picker: UIImagePickerController) {
    dismiss(animated: true, completion: nil)

francoismarceau29

import UIKit

extension UIImage {
    func toCVPixelBuffer() -> CVPixelBuffer? {
        let attrs = [kCVPixelBufferCGImageCompatibilityKey: kCFBooleanTrue, kCVPixelBufferCGBitmapContextCompatibilityKey: kCFBooleanTrue] as CFDictionary
        var pixelBuffer : CVPixelBuffer?
        let status = CVPixelBufferCreate(kCFAllocatorDefault, Int(self.size.width), Int(self.size.height), kCVPixelFormatType_32ARGB, attrs, &pixelBuffer)
        guard status == kCVReturnSuccess else {
            return nil
        }

francoismarceau29

import coremltools
coreml_model = coremltools.converters.keras.convert('model.h5', input_names='data', image_input_names='data', is_bgr=True, output_names='species')
coreml_model.save('model.mlmodel')

francoismarceau29

def predict(data):
  # Process your data, create a dataframe/vector and make your predictions
  final_formatted_data = []
  return load_model().predict(final_formatted_data)

francoismarceau29

from sklearn.externals import joblib
from boto.s3.key import Key
from boto.s3.connection import S3Connection
from flask import Flask
from flask import request
from flask import json

BUCKET_NAME = 'your-s3-bucket-name'
MODEL_FILE_NAME = 'your-model-name.pkl'
MODEL_LOCAL_PATH = '/tmp/' + MODEL_FILE_NAME

francoismarceau29

def load_model():
  conn = S3Connection()
  bucket = conn.create_bucket(BUCKET_NAME)
  key_obj = Key(bucket)
  key_obj.key = MODEL_FILE_NAME

  contents = key_obj.get_contents_to_filename(MODEL_LOCAL_PATH)
  return joblib.load(MODEL_LOCAL_PATH)

francoismarceau29

from sklearn.externals import joblib
from boto.s3.key import Key
from boto.s3.connection import S3Connection
from flask import Flask
from flask import request
from flask import json

BUCKET_NAME = 'your-s3-bucket-name'
MODEL_FILE_NAME = 'your-model-name.pkl'
MODEL_LOCAL_PATH = '/tmp/' + MODEL_FILE_NAME

francoismarceau29

// Use Gists to store code you would like to remember later on
console.log(window); // log the "window" object to the console