public static async Task <IActionResult> Run([HttpTrigger(AuthorizationLevel.Anonymous, "get", "post", Route = null)] HttpRequest req, ILogger log, ExecutionContext context)
{
#region Preparation
var imageUrl = req.Query["imageUrl"];
var config = new ConfigurationBuilder()
.SetBasePath(context.FunctionAppDirectory)
.AddJsonFile("local.settings.json", optional: true, reloadOnChange: true)
.AddEnvironmentVariables()
.Build();
var predictionSubscriptionKey = config["predictionSubscriptionKey"];
var predictionProjectId = config["predictionProjectId"];
#endregion
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = predictionSubscriptionKey
};
var result = endpoint.PredictImageUrl(Guid.Parse(predictionProjectId), new ImageUrl(imageUrl));
#region Output
return(new OkObjectResult(result));
#endregion
}
public async Task <IList <PredictionViewModel> > Predict(byte[] image)
{
var trainingCredentials = new TrainingApiCredentials(APIKeys.TrainingAPIKey);
var trainingApi = new TrainingApi(trainingCredentials);
var predictionEndpointCredentials = new PredictionEndpointCredentials(APIKeys.PredictionAPIKey);
var predictionEndpoint = new PredictionEndpoint(predictionEndpointCredentials);
var projects = await trainingApi.GetProjectsAsync();
var stream = new System.IO.MemoryStream(image);
var results = await predictionEndpoint.PredictImageAsync(projects[0].Id, stream);
var predictions = new List <PredictionViewModel>();
foreach (var result in results.Predictions)
{
predictions.Add(new PredictionViewModel()
{
Tag = result.Tag, Prediction = result.Probability
});
}
return(predictions);
}
static void Main(string[] args)
{
var predictionKey = "insert your prediction key here";
PredictionEndpointCredentials predictionEndpointCredentials = new PredictionEndpointCredentials(predictionKey);
PredictionEndpoint endpoint = new PredictionEndpoint(predictionEndpointCredentials);
// Make a prediction against the new project
Console.WriteLine("Making a prediction:");
var testImage = new MemoryStream(File.ReadAllBytes(@"insert the picture you want to compare here"));
var projectId = new Guid("insert the project guid here");
var result = endpoint.PredictImage(projectId, testImage, null, null);
// Loop over each prediction and write out the results
foreach (var c in result.Predictions)
{
Console.WriteLine($"\t{c.Tag}: {c.Probability:P1}");
}
Console.ReadKey();
}
private async void EvaluateImages()
{
// Add your prediction key from the settings page of the portal
// The prediction key is used in place of the training key when making predictions
string predictionKey = "ab7cbbf3606a41308e3c66d73c4af3fa";
// Create a prediction endpoint, passing in obtained prediction key
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = predictionKey
};
// Get image to test
var imagePath = System.IO.Path.Combine(root, "../../Evaluated/evaluated.jpg");
testImage = new MemoryStream(File.ReadAllBytes(imagePath));
// Make a prediction against the new project
Log("Making a prediction:");
//Hardcoding projectID.
//Guid projectID = new Guid("d8622071-5654-435d-a776-83944fc43129");
var result = await endpoint.PredictImageAsync(project.Id, testImage);
// Loop over each prediction and write out the results
foreach (var c in result.Predictions)
{
Log($"\t{c.Tag}: {c.Probability:P1}");
}
}
static void Main(string[] args)
{
var options = Options.InitializeOptions <PredictionOptions>(args);
if (options == null)
{
return;
}
var images = ImagesLoaderGenerator.GenerateImagesLoader(options, options.AllowedTagNames).LoadImages();
var predictionEndpoint = new PredictionEndpoint(new PredictionEndpointCredentials(options.PredictionKey));
if (options.BaseUri != null)
{
Console.WriteLine($"The default base uri is {predictionEndpoint.BaseUri}. Changed it to {options.BaseUri}.");
predictionEndpoint.BaseUri = options.BaseUri;
}
PrecisionAndRecall precisionAndRecall;
using (var predictor = ConstructPredictor(predictionEndpoint, options.WorkDir + options.PredictionFileName, options.MilliSecondsBetweenPredictions))
{
var batchPredictor = new BatchPredictorWithRateLimit(predictor, options.MilliSecondsBetweenPredictions);
precisionAndRecall = PrecisionAndRecall.ComputeAsync(
images,
options.Threshold,
async imgs => await batchPredictor.PredictWithImagesAsync(imgs, options.ProjectId, options.IterationId),
options.AllowedTagNames).Result;
}
Console.WriteLine($"Precision: {precisionAndRecall.Precision}");
Console.WriteLine($"Recall: {precisionAndRecall.Recall}");
Console.WriteLine("Press any key to exit.");
Console.ReadKey();
}
private static ImagePredictionResultModel ProcessImagePredictions(string imageUrl, Guid projectId)
{
string predictionKey = "6c9f96aa9a574ab8b3aa18f5e0ec4c1c";
var shouldAlert = false;
// Create a prediction endpoint, passing in a prediction credentials object that contains the obtained prediction key
PredictionEndpointCredentials predictionEndpointCredentials = new PredictionEndpointCredentials(predictionKey);
PredictionEndpoint endpoint = new PredictionEndpoint(predictionEndpointCredentials);
// Make a prediction against the new project
var result = endpoint.PredictImageUrl(projectId, new Microsoft.Cognitive.CustomVision.Models.ImageUrl(imageUrl));
// Need to throttle the requests as to not upset it into throwing the dreaded 429 too many requests in a given period of time
Thread.Sleep(200);
//check for any probabilities greater than 90%
shouldAlert = result.Predictions.Any(x => x.Probability > .9);
if (shouldAlert)
{
return(result);
}
else
{
return(null);
}
}
private void MediaService_Saving(IMediaService sender, SaveEventArgs <IMedia> e)
{
var umbracoHelper = new Umbraco.Web.UmbracoHelper(Umbraco.Web.UmbracoContext.Current);
_customVisionPredictionKey = umbracoHelper.TypedContent(1127).GetPropertyValue <string>("customVisionPredictionKey");
_customVisionApiProjectId = umbracoHelper.TypedContent(1127).GetPropertyValue <string>("customVisionProjectId");
if (!string.IsNullOrWhiteSpace(_customVisionPredictionKey) && !string.IsNullOrWhiteSpace(_customVisionApiProjectId))
{
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = _customVisionPredictionKey
};
foreach (IMedia media in e.SavedEntities.Where(a => a.ContentType.Name.Equals(Constants.Conventions.MediaTypes.Image)))
{
string relativeImagePath = ImagePathHelper.GetImageFilePath(media);
using (Stream imageFileStream = _fs.OpenFile(relativeImagePath))
{
var result = endpoint.PredictImage(Guid.Parse(_customVisionApiProjectId), imageFileStream);
IEnumerable <string> tags = result.Predictions.Where(a => a.Probability > 0.75).Select(a => a.Tag);
media.SetTags("customVisionTags", tags, true);
}
}
}
}
public async Task <IEnumerable <LabelConfidence> > Tags(byte[] image, CustomVisionSettings settings)
{
// Create a prediction endpoint, passing in obtained prediction key
var endpoint = new PredictionEndpoint()
{
ApiKey = settings.CustomVisionPredictionKey
};
Cognitive.CustomVision.Prediction.Models.ImagePredictionResultModel result;
using (var testImage = new MemoryStream(image))
{
// Make a prediction against the prediction project
// IMPORTANT: the prediction project should have an iteration marked as default.
// Otherwise, you need to specify an iteration ID
result = await endpoint.PredictImageWithNoStoreAsync(settings.CustomVisionProjectId, testImage);
}
return(result.Predictions.Select(t => new LabelConfidence()
{
Label = t.Tag, Probability = (float)t.Probability
})
.Where(c => c.Probability >= settings.Threshold)
.OrderByDescending(c => c.Probability));
}
public async Task <ImageInsights> PredictImage(string imageLocalPath)
{
var fileName = Path.GetFileName(imageLocalPath);
var customVisionProjectId = ConfigurationManager.AppSettings["CustomVisionProjectId"];
var customVisionPredictionKey = ConfigurationManager.AppSettings["CustomVisionPredictionKey"];
PredictionEndpointCredentials predictionEndpointCredentials = new PredictionEndpointCredentials(customVisionPredictionKey);
PredictionEndpoint endpoint = new PredictionEndpoint(predictionEndpointCredentials);
try
{
// Make a prediction against the project
var testImage = new MemoryStream(System.IO.File.ReadAllBytes(imageLocalPath));
var result = await endpoint.PredictImageAsync(Guid.Parse(customVisionProjectId), testImage);
ImageInsights insights = new ImageInsights
{
ImageId = fileName,
Tags = result.Predictions.Where(s => s.Probability >= 0.60).Select(s => s.Tag).ToArray()
};
return(insights);
}
catch (Exception ex)
{
return(null);
}
}
static void EfetuarTesteImagem(string caminho, bool eURL)
{
string chaveAPI = "0c91a890892d40a0ba9f9e22a5e358de";
string chaveProjeto = "4a1a0670-7689-4d01-ac59-fc56227cc3ed";
// Crio o client do Custom View Service.
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = chaveAPI
};
ImagePrediction resultado = null;
// Verifico se o projeto é uma URL ou um arquivo local para usar o método correto.
if (eURL)
{
resultado = endpoint.PredictImageUrl(new Guid(chaveProjeto), new ImageUrl(caminho));
}
else
{
resultado = endpoint.PredictImage(new Guid(chaveProjeto), File.OpenRead(caminho));
}
// Percorro as analises.
foreach (var possibilidade in resultado.Predictions)
{
Console.WriteLine($"Tag: {possibilidade.TagName}");
Console.WriteLine($"Possibilidade: {possibilidade.Probability:P1}");
}
}
public CustomVisionService(string predictionKey, string projectId)
{
_endpoint = new PredictionEndpoint {
ApiKey = predictionKey
};
_projectId = projectId;
}
public Form1()
{
InitializeComponent();
trainingApi = new TrainingApi()
{
ApiKey = trainingKey
};
currentPredictionMode = PredictionMode.Detection;
project = trainingApi.GetProject(new Guid("e1ec7b7e-ac74-4959-9c8b-4d48d25a7668"));
// Create a prediction endpoint, passing in obtained prediction key
endpoint = new PredictionEndpoint()
{
ApiKey = predictionKey
};
labelInfo.Text = textBoxUrl.Text = "";
percentLevel = trackBar1.Value;
selectedItemIndex = -1;
isPredicting = true;
textBoxTag.Enabled = buttonAddTag.Enabled = buttonSend.Enabled = buttonClear.Enabled = false;
labelStatus.Text = "PREDICTING";
treeListToUpload = new List <TreeData>();
treeListDetection = new List <TreeData>();
treeListClassification = new List <TreeData>();
}
/// <summary>
/// Uses Cognitive Services Custom Vision API to determine whether an object was found in an image
/// with some degree of certainty
/// </summary>
/// <param name="imageUrl"></param>
/// <returns>Boolean</returns>
private static async Task <bool> ObjectFound(string imageUrl, double minimumScore = 0.5)
{
bool objectFound = false;
try
{
// Initialize prediction endpoint
PredictionEndpoint predictionEndpoint = new PredictionEndpoint()
{
ApiKey = ConfigurationManager.AppSettings["CustomVisionApiKey"]
};
// Call custom vision prediction API to predict image
ImagePredictionResultModel predictionResult = await predictionEndpoint.PredictImageUrlAsync(
new Guid(ConfigurationManager.AppSettings["CustomVisionProjectId"]),
new ImageUrl(imageUrl));
// Query for the object tag
var objectTag = predictionResult.Predictions.Where(x => x.Tag == "Object").FirstOrDefault();
// Check if the object tag probability surpassed the minimum score
if (objectTag != null && objectTag.Probability >= minimumScore)
{
objectFound = true;
}
}
catch (Exception e)
{
throw e;
}
// Return result
return(objectFound);
}
public SubmitPhotoController(IOptions <AppSettings> options)
{
_appSettings = options.Value;
_endpoint = new PredictionEndpoint {
ApiKey = _appSettings.PredictionEndpointApiKey
};
}
private static PredictionEndpoint GetPredictionEndpoint()
{
var predictionEndpoint = new PredictionEndpoint();
predictionEndpoint.ApiKey = Properties.Settings.Default.Classifier_PredictionApiKey;
return(predictionEndpoint);
}
private string connectToAnalyze()
{
// custom vision
TrainingApi trainingAPI = new TrainingApi()
{
ApiKey = "1360135bcfaa45d5b6d69dc06dcb04e4"
};
Guid _projectkey = new Guid("ea8591bc-bff1-47d6-b46d-64938d2d8b58");
project = trainingAPI.GetProject(_projectkey);
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = "65125a9d5a774acaaeaa0f9705404307"
};
// 28bf5d1c-1025-4d3f-a7d7-4dfd4b65f4a1 iteration key
ArrayList lists = new ArrayList();
byte[] imgArr = GetFileAsByteArray(App._file.AbsolutePath);
System.IO.MemoryStream stream = new System.IO.MemoryStream(imgArr);
var result = endpoint.PredictImage(project.Id, stream, new Guid("28bf5d1c-1025-4d3f-a7d7-4dfd4b65f4a1"));
foreach (var prediction in result.Predictions)
{
lists.Add($"{prediction.Tag}");
}
return(lists.Get(0).ToString());
}
public static IActionResult Run([HttpTrigger(AuthorizationLevel.Anonymous, "get", "post", Route = null)] HttpRequest req, TraceWriter log)
{
log.Info("C# HTTP trigger function processed a request.");
try
{
string requestBody = new StreamReader(req.Body).ReadToEnd();
var prediction = JsonConvert.DeserializeObject <Prediction>(requestBody);
var api = new TrainingApi(new TrainingApiCredentials(prediction.TrainingId));
var account = api.GetAccountInfo();
var predictionKey = account.Keys.PredictionKeys.PrimaryKey;
var creds = new PredictionEndpointCredentials(predictionKey);
var endpoint = new PredictionEndpoint(creds);
//This is where we run our prediction against the default iteration
var result = endpoint.PredictImageUrl(new Guid(prediction.ProjectId), new ImageUrl(prediction.ImageUrl));
prediction.Results = new Dictionary <string, decimal>();
// Loop over each prediction and write out the results
foreach (var outcome in result.Predictions)
{
if (outcome.Probability > .70)
{
prediction.Results.Add(outcome.Tag, (decimal)outcome.Probability);
}
}
return((ActionResult) new OkObjectResult(prediction));
}
catch (Exception e)
{
return(new BadRequestObjectResult(e.GetBaseException().Message));
}
}
public static async Task <string> GetPredictionsAsync2(byte[] imageBytes, string intent)
{
Debug.WriteLine("inside GetPredictionsAsync2 ");
string projectid, apikey;
GetProjectBasedOnIntent(intent, out projectid, out apikey);
// Create a prediction endpoint, passing in the obtained prediction key
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = apikey
};
// Make a prediction against the new project
Debug.WriteLine("Making a prediction:");
var result = await endpoint.PredictImageAsync(new Guid(projectid), new MemoryStream(imageBytes));
var pn = result.Predictions.Where(e => e.Probability > 0.5).FirstOrDefault();
if (pn != null)
{
Debug.Write($"responese Prediction tag {pn.Tag}");
return(pn.Tag);
}
else
{
Debug.Write("We didnt get any prediction");
}
return(null);
}
async Task PredictPhoto(MediaFile photo)
{
var endpoint = new PredictionEndpoint
{
ApiKey = await KeyService.GetPredictionKey()
};
var results = await endpoint.PredictImageAsync(Guid.Parse(await KeyService.GetProjectId()),
photo.GetStream());
AllPredictions = results.Predictions
.Where(p => p.Probability > Probability)
.ToList();
// Create the Api, passing in the training key
CustomVisionTrainingClient trainingApi = new CustomVisionTrainingClient()
{
ApiKey = KeyService.TK,
Endpoint = KeyService.SouthCentralUsEndpoint
};
// Find the object detection domain
//var domains = trainingApi.GetDomains();
//var objDetectionDomain = domains.FirstOrDefault(d => d.Type == "ObjectDetection");
//upload to service
trainingApi.CreateImagesFromData(Guid.Parse(await KeyService.GetProjectId()), photo.GetStream(), null);
}
/// <summary>
/// ボタンをクリックした時の処理
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private async void _Click(object sender, RoutedEventArgs e)
{
var button = (Button)sender;
if (button.Name == "btnShot")
{
txtDisplay.Text = "";
var loader = new ResourceLoader();
try
{
// カメラで撮影する
var file = await _cameraHelper.CapturePhoto();
using (var stream = File.OpenRead(file.Path))
{
// クライアント生成
var client = new PredictionEndpoint
{
BaseUri = new Uri(Constants.ENDPOINT),
ApiKey = Constants.VISION_KEY,
};
// 画像を送ってタグを取得する
var result = await client.PredictImageWithHttpMessagesAsync(
new Guid(Constants.PROJECT_ID),
stream,
new Guid(Constants.ITERATION_ID));
var predictions = result.Body.Predictions;
// 合致率が高い順にソートして先頭を取得
var prediction = predictions.ToArray().OrderByDescending(p => p.Probability).ElementAt(0);
string text;
if (prediction.Tag == "ペットボトル")
{
text = prediction.Tag + " " + loader.GetString("MSG_TRUSH");
}
else if (prediction.Tag == "缶")
{
text = prediction.Tag + " " + loader.GetString("MSG_STAMP");
}
else if (prediction.Tag == "瓶")
{
text = prediction.Tag + " " + loader.GetString("MSG_SMASH");
}
else
{
text = loader.GetString("LABEL_UNKNOWN");
}
// 表示
txtDisplay.Text = text;
}
}
catch (Exception exp)
{
var dialog = new MessageDialog(exp.Message);
await dialog.ShowAsync();
}
}
}
private static PredictionEndpoint GetPredictionEndpoint()
{
var predictionEndpoint = new PredictionEndpoint
{
ApiKey = ConfigurationManager.AppSettings["predictionKey"]
};
return(predictionEndpoint);
}
public HotDogOrNotPage()
{
InitializeComponent();
endpoint = new PredictionEndpoint()
{
ApiKey = predictionKey
};
}
private void InvokeCognitive(string photoUrl)
{
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = PREDICTION_KEY
};
ImageUrl url = new ImageUrl(photoUrl);
var result = endpoint.PredictImageUrl(new Guid("152a2f03-5840-46b4-acfe-987a8342b47e"), url);
}
public MainViewModel()
{
TakePhotoCommand = new Command(async() => await TakePhoto());
PickPhotoCommand = new Command(async() => await PickPhoto());
endpoint = new PredictionEndpoint
{
ApiKey = ApiKeys.PredictionKey
};
}
private async Task <ImagePredictionResultModel> PredictImageAsync(Stream stream)
{
var ep = new PredictionEndpoint(new PredictionEndpointCredentials(AuthKeys.VisionPredictionKey))
{
BaseUri = new Uri(AuthKeys.VisionPredictionUrl)
};
var response = await ep.PredictImageWithHttpMessagesAsync(AuthKeys.GardenCenterProjectId, stream).ConfigureAwait(false);
return(response.Body);
}
private void button1_Click(object sender, EventArgs e)
{
// 変数定義
bool food = false; // "food" タグの有無
string tag = ""; // カテゴリタグ
ImageUrl url = new ImageUrl(textBox1.Text); //TextBoxからURLを取得
var cvEp = new PredictionEndpoint {
ApiKey = "PREDICTION_KEY"
};
var cvGuid = new Guid("PROJECT_ID");
var iterationId = new Guid("iterationId");
try
{
// 画像を判定
var cvResult = cvEp.PredictImageUrl(cvGuid, url, iterationId);
foreach (var item in cvResult.Predictions)
{
if (item.Probability > 0.8)
{
if (item.Tag == "食べ物")
{
food = true;
}
else
{
tag = item.Tag;
break;
}
}
}
if (tag != "")
{
// タグに応じてメッセージをセット
label1.Text = "この写真は " + tag + " です。";
}
else if (food == true)
{
//msg = "I'm not sure what it is ...";
label1.Text = "これは食べ物ってことしか分からないです。";
}
else
{
//msg = "Send me food photo you are eating!";
label1.Text = "食べ物の写真を送ってください。";
}
}
catch (Exception)
{
label1.Text = "エラー";
}
}