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 IList <Prediction> PredictImage(Stream imageStream)
{
var account = TrainingApi.GetAccountInfo();
var predictionKey = account.Keys.PredictionKeys.PrimaryKey;
var predictionEndpointCredentials = new PredictionEndpointCredentials(predictionKey);
var endpoint = new PredictionEndpoint(predictionEndpointCredentials);
var result = endpoint.PredictImage(ProjectGuid, imageStream);
return(result.Predictions.Select(p => new Prediction
{
Tag = Enum.Parse <Models.Training.Tag>(p.Tag),
Probability = p.Probability
}).ToList());
}
public static bool IsValidCard(string url)
{
try
{
string trainingKey = Constants.CustomVisionTrainingAPIKey;
// Create the Api, passing in a credentials object that contains the training key
TrainingApiCredentials trainingCredentials = new TrainingApiCredentials(trainingKey);
TrainingApi trainingApi = new TrainingApi(trainingCredentials);
var projects = trainingApi.GetProjects();
ProjectModel project = projects.FirstOrDefault(e => e.Name == "IDVision");
// Get the prediction key, which is used in place of the training key when making predictions
var account = trainingApi.GetAccountInfo();
var predictionKey = account.Keys.PredictionKeys.PrimaryKey;
// 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);
byte[] byteData = Utilities.Utilities.GetImagesAsByteArrayFromUri(url);
MemoryStream stream = new MemoryStream(byteData);
// Make a prediction against the new project
var predictionResult = endpoint.PredictImage(project.Id, stream);
// Loop over each prediction and write out the results
foreach (var c in predictionResult.Predictions)
{
if ((c.Probability * 100) > 80)
{
return(true);
}
else
{
return(false);
}
}
}
catch (Exception ex)
{
throw ex;
}
return(false);
}
public static async Task <HttpResponseMessage> Run([HttpTrigger(AuthorizationLevel.Anonymous, "post", Route = "api/MakePrediction")] HttpRequestMessage req, TraceWriter log)
{
try
{
var stream = await req.Content.ReadAsStreamAsync();
var prediction = new Prediction
{
ProjectId = "36f167d1-82e0-45f4-8ddc-ffc6d3fe3a41", //36f167d1-82e0-45f4-8ddc-...
TrainingKey = "c63201c1e627428fb5c5d603430b5f62", //c63201c1e627428fb5c5d6...
TimeStamp = DateTime.UtcNow,
UserId = Guid.NewGuid().ToString(),
ImageUrl = await UploadImageToBlobStorage(stream)
};
var api = new TrainingApi(new TrainingApiCredentials(prediction.TrainingKey));
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 >= 0.0010)
{
prediction.Results.Add(outcome.Tag, (decimal)outcome.Probability);
}
}
await CosmosDataService.Instance.InsertItemAsync(prediction);
return(req.CreateResponse(HttpStatusCode.OK, prediction));
}
catch (Exception e)
{
var baseException = e.GetBaseException();
var operationException = baseException as HttpOperationException;
var reason = baseException.Message;
if (operationException != null)
{
var jobj = JObject.Parse(operationException.Response.Content);
var code = jobj.GetValue("Code");
if (code != null && !string.IsNullOrWhiteSpace(code.ToString()))
{
reason = code.ToString();
}
}
return(req.CreateErrorResponse(HttpStatusCode.BadRequest, reason));
}
async Task <string> UploadImageToBlobStorage(Stream stream)
{
//Create a new blob block Id
var blobId = Guid.NewGuid().ToString() + ".jpg";
if (_blobContainer == null)
{
//You can set your endpoint here as a string in code or just set it to pull from your App Settings
var containerName = "images";
var endpoint = $"https://mynewstorageaccountblob.blob.core.windows.net/{containerName}/?sv=2017-04-17&ss=b&srt=sco&sp=rwdlac&se=2019-01-06T04:57:40Z&st=2018-01-05T20:57:40Z&spr=https&sig=YE2ZWYTvRax4jRUmBpZSzaCFDd8ZwM3pxSDHYWVn0dY%3D";
_blobContainer = new CloudBlobContainer(new Uri(endpoint));
}
//Create a new block to store this uploaded image data
var blockBlob = _blobContainer.GetBlockBlobReference(blobId);
blockBlob.Properties.ContentType = "image/jpg";
//You can even store metadata with the content
blockBlob.Metadata.Add("createdFor", "This Awesome Hackathon");
//Upload and return the new URL associated w/ this blob content
await blockBlob.UploadFromStreamAsync(stream);
return(blockBlob.StorageUri.PrimaryUri.ToString());
}
}
static void Main(string[] args)
{
// You can either add your training key here, pass it on the command line, or type it in when the program runs
string trainingKey = GetTrainingKey("<your key here>", args);
// Create the Api, passing in a credentials object that contains the training key
TrainingApiCredentials trainingCredentials = new TrainingApiCredentials(trainingKey);
TrainingApi trainingApi = new TrainingApi(trainingCredentials);
// Create a new project
Console.WriteLine("Creating new project:");
var project = trainingApi.CreateProject("Car Assessment");
// Make two tags in the new project
var WriteOffTag = trainingApi.CreateTag(project.Id, "WriteOff");
var DentTag = trainingApi.CreateTag(project.Id, "Dent");
// Add some images to the tags
Console.WriteLine("\\tUploading images");
LoadImagesFromDisk();
// Images can be uploaded one at a time
foreach (var image in WriteOffImages)
{
trainingApi.CreateImagesFromData(project.Id, image, new List <string> ()
{
WriteOffTag.Id.ToString()
});
}
// Or uploaded in a single batch
trainingApi.CreateImagesFromData(project.Id, DentImages, new List <Guid> ()
{
DentTag.Id
});
// Now there are images with tags start training the project
Console.WriteLine("\\tTraining");
var iteration = trainingApi.TrainProject(project.Id);
// The returned iteration will be in progress, and can be queried periodically to see when it has completed
while (iteration.Status == "Training")
{
Thread.Sleep(1000);
// Re-query the iteration to get it's updated status
iteration = trainingApi.GetIteration(project.Id, iteration.Id);
}
// The iteration is now trained. Make it the default project endpoint
iteration.IsDefault = true;
trainingApi.UpdateIteration(project.Id, iteration.Id, iteration);
Console.WriteLine("Done!\\n");
// Now there is a trained endpoint, it can be used to make a prediction
// Get the prediction key, which is used in place of the training key when making predictions
var account = trainingApi.GetAccountInfo();
var predictionKey = account.Keys.PredictionKeys.PrimaryKey;
// 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
Console.WriteLine("Making a prediction:");
var result = endpoint.PredictImage(project.Id, testImage);
// 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();
}
public static HttpResponseMessage Run([HttpTrigger(AuthorizationLevel.Anonymous, "post", Route = nameof(AnalyseCustomImage))]
HttpRequestMessage req, TraceWriter log)
{
using (var analytic = new AnalyticService(new RequestTelemetry
{
Name = nameof(AnalyseCustomImage)
}))
{
try
{
var allTags = new List <string>();
var j = JObject.Parse(req.Content.ReadAsStringAsync().Result);
var imageUrl = (string)j["imageUrl"];
var treasureId = (string)j["treasureId"];
var gameId = (string)j["gameId"];
var game = CosmosDataService.Instance.GetItemAsync <Game>(gameId).Result;
if (game == null)
{
return(req.CreateErrorResponse(HttpStatusCode.NotFound, "Game not found"));
}
var treasure = game.Treasures.SingleOrDefault(t => t.Id == treasureId);
if (treasure == null)
{
return(req.CreateErrorResponse(HttpStatusCode.NotFound, "Treasure not found"));
}
var api = new TrainingApi(new TrainingApiCredentials(ConfigManager.Instance.CustomVisionTrainingKey));
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(game.CustomVisionProjectId), new ImageUrl(imageUrl));
bool toReturn = false;
// Loop over each prediction and write out the results
foreach (var outcome in result.Predictions)
{
if (treasure.Attributes.Any(a => a.Name.Equals(outcome.Tag, StringComparison.InvariantCultureIgnoreCase)))
{
if (outcome.Probability >= ConfigManager.Instance.CustomVisionMinimumPredictionProbability)
{
toReturn = true;
break;
}
}
}
return(req.CreateResponse(HttpStatusCode.OK, toReturn));
}
catch (Exception e)
{
analytic.TrackException(e);
return(req.CreateErrorResponse(HttpStatusCode.BadRequest, e));
}
}
}
/// <summary>
/// 获取PredictionKey
/// </summary>
/// <returns></returns>
public string GetPredictionKey()
{
return(trainingApi.GetAccountInfo().Keys.PredictionKeys.PrimaryKey);
}
static void Main(string[] args)
{
// You can either add your training key here, pass it on the command line, or type it in when the program runs
string trainingKey = GetTrainingKey("<your key here>", args);
// Create the Api, passing in the training key
TrainingApi trainingApi = new TrainingApi()
{
ApiKey = trainingKey
};
// Create a new project
Console.WriteLine("Creating new project:");
var project = trainingApi.CreateProject("My New Project");
// Make two tags in the new project
var hemlockTag = trainingApi.CreateTag(project.Id, "Hemlock");
var japaneseCherryTag = trainingApi.CreateTag(project.Id, "Japanese Cherry");
// Add some images to the tags
Console.WriteLine("\tUploading images");
LoadImagesFromDisk();
// Images can be uploaded one at a time
foreach (var image in hemlockImages)
{
using (var stream = new MemoryStream(File.ReadAllBytes(image)))
{
trainingApi.CreateImagesFromData(project.Id, stream, new List <string>()
{
hemlockTag.Id.ToString()
});
}
}
// Or uploaded in a single batch
var imageFiles = japaneseCherryImages.Select(img => new ImageFileCreateEntry(Path.GetFileName(img), File.ReadAllBytes(img))).ToList();
trainingApi.CreateImagesFromFiles(project.Id, new ImageFileCreateBatch(imageFiles, new List <Guid>()
{
japaneseCherryTag.Id
}));
// Now there are images with tags start training the project
Console.WriteLine("\tTraining");
var iteration = trainingApi.TrainProject(project.Id);
// The returned iteration will be in progress, and can be queried periodically to see when it has completed
while (iteration.Status == "Training")
{
Thread.Sleep(1000);
// Re-query the iteration to get it's updated status
iteration = trainingApi.GetIteration(project.Id, iteration.Id);
}
// The iteration is now trained. Make it the default project endpoint
iteration.IsDefault = true;
trainingApi.UpdateIteration(project.Id, iteration.Id, iteration);
Console.WriteLine("Done!\n");
// Now there is a trained endpoint, it can be used to make a prediction
// Get the prediction key, which is used in place of the training key when making predictions
var account = trainingApi.GetAccountInfo();
var predictionKey = account.Keys.PredictionKeys.PrimaryKey;
// Create a prediction endpoint, passing in obtained prediction key
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = predictionKey
};
// Make a prediction against the new project
Console.WriteLine("Making a prediction:");
var result = endpoint.PredictImage(project.Id, testImage);
// 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();
}