private void PredictImageDetection()
{
treeListDetection.Clear();
//var attachmentStream = await httpClient.GetStreamAsync(imageUrl);
MemoryStream testImage = GetStream(pictureBox1.BackgroundImage);
//MemoryStream testImage = new MemoryStream(File.ReadAllBytes("test.jpg"));
try
{
var result = endpoint.PredictImage(project.Id, testImage);
// Loop over each prediction and write out the results
foreach (var c in result.Predictions)
{
treeListDetection.Add(new TreeData(c.TagName, c.Probability, new RectangleBox(c.BoundingBox.Left, c.BoundingBox.Top, c.BoundingBox.Width, c.BoundingBox.Height)));
}
}
catch (Microsoft.Rest.HttpOperationException exception)
{
labelInfo.Text = exception.ToString();
}
if (treeListDetection.Count > 1)
{
treeListDetection.Sort((a, b) => b.Probability.CompareTo(a.Probability));
}
if (treeListDetection.Count > 0)
{
pictureBox1.Invalidate();
}
}
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}");
}
}
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($"\t{c.Tag}: {c.Probability:P1}");
}
Console.ReadKey();
}
private void MediaService_Saving(IMediaService sender, SaveEventArgs <IMedia> e)
{
var umbracoHelper = new Umbraco.Web.UmbracoHelper(Umbraco.Web.UmbracoContext.Current);
_customVisionPredictionKey = umbracoHelper.TypedContent(1127).GetPropertyValue <string>("customVisionPredictionKey");
_customVisionApiProjectId = umbracoHelper.TypedContent(1127).GetPropertyValue <string>("customVisionProjectId");
if (!string.IsNullOrWhiteSpace(_customVisionPredictionKey) && !string.IsNullOrWhiteSpace(_customVisionApiProjectId))
{
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = _customVisionPredictionKey
};
foreach (IMedia media in e.SavedEntities.Where(a => a.ContentType.Name.Equals(Constants.Conventions.MediaTypes.Image)))
{
string relativeImagePath = ImagePathHelper.GetImageFilePath(media);
using (Stream imageFileStream = _fs.OpenFile(relativeImagePath))
{
var result = endpoint.PredictImage(Guid.Parse(_customVisionApiProjectId), imageFileStream);
IEnumerable <string> tags = result.Predictions.Where(a => a.Probability > 0.75).Select(a => a.Tag);
media.SetTags("customVisionTags", tags, true);
}
}
}
}
private string connectToAnalyze()
{
// custom vision
TrainingApi trainingAPI = new TrainingApi()
{
ApiKey = "1360135bcfaa45d5b6d69dc06dcb04e4"
};
Guid _projectkey = new Guid("ea8591bc-bff1-47d6-b46d-64938d2d8b58");
project = trainingAPI.GetProject(_projectkey);
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = "65125a9d5a774acaaeaa0f9705404307"
};
// 28bf5d1c-1025-4d3f-a7d7-4dfd4b65f4a1 iteration key
ArrayList lists = new ArrayList();
byte[] imgArr = GetFileAsByteArray(App._file.AbsolutePath);
System.IO.MemoryStream stream = new System.IO.MemoryStream(imgArr);
var result = endpoint.PredictImage(project.Id, stream, new Guid("28bf5d1c-1025-4d3f-a7d7-4dfd4b65f4a1"));
foreach (var prediction in result.Predictions)
{
lists.Add($"{prediction.Tag}");
}
return(lists.Get(0).ToString());
}
// GET: RecognitionModels
public async Task <ActionResult> Index([Bind(Include = "Id,Key,ImageUpload")] RecognitionModel recognitionModel)
{
ViewBag.Message = "Result will show here.";
Trace.WriteLine("Starting Prediction...");
if (recognitionModel.ImageUpload != null)
{
// Create image.
Guid projectid = new Guid("57471653-6e79-455f-b874-ee00d1014c37");
// Create a prediction endpoint, passing in a prediction credentials object that contains the obtained prediction key
PredictionEndpointCredentials predictionEndpointCredentials = new PredictionEndpointCredentials(recognitionModel.Key);
PredictionEndpoint endpoint = new PredictionEndpoint(predictionEndpointCredentials);
if (recognitionModel.ImageUpload != null && recognitionModel.ImageUpload.ContentLength > 0)
{
//var uploadDir = "~/uploads";
//var imagePath = Path.Combine(Server.MapPath(uploadDir), recognitionModel.ImageUpload.FileName);
//var imageUrl = Path.Combine(uploadDir, recognitionModel.ImageUpload.FileName);
//Trace.WriteLine("ImageUrl:" + imageUrl);
//Trace.WriteLine("Image path:" + imagePath);
//recognitionModel.ImageUpload.SaveAs(imagePath);
Trace.WriteLine("createing memory stream");
//MemoryStream memStream = new MemoryStream(System.IO.File.ReadAllBytes(imagePath));
MemoryStream memStream = new MemoryStream();
recognitionModel.ImageUpload.InputStream.Position = 0;
recognitionModel.ImageUpload.InputStream.CopyTo(memStream);
memStream.Position = 0;
// Make a prediction against the new project
Trace.WriteLine("Making a prediction:");
try
{
var result = endpoint.PredictImage(projectid, memStream);
// Loop over each prediction and write out the results
var predicition = result.Predictions.FirstOrDefault(P => P.Probability >= 0.8);
if (predicition == null)
{
ViewBag.Message = "Could not find a good match for the uploaded image. Please try again.";
}
else
{
ViewBag.Message = "Your image is of type " + predicition.Tag + " with the probability of " + predicition.Probability;
}
}
catch (Exception e)
{
ViewBag.Message = "Could not make a predicition of image " + recognitionModel.ImageUpload.FileName + "! Error message: " + e.Message;
}
}
}
return(View(recognitionModel));
}
private ImageTagPredictionModel GetBestTag(MediaFile file)
{
using (var stream = file.GetStream())
{
return(_endpoint.PredictImage(ApiKeys.ProjectId, stream)
.Predictions
.OrderByDescending(p => p.Probability)
.FirstOrDefault(p => p.Probability > ProbabilityThreshold));
}
}
public List <ImageTagPrediction> GetListOfPredictions(Bitmap image)
{
MemoryStream memoryStream = new MemoryStream();
image.Save(memoryStream, System.Drawing.Imaging.ImageFormat.Jpeg);
//We need to seek to begin
memoryStream.Seek(0, SeekOrigin.Begin);
var result = endpoint.PredictImage(projectId, memoryStream, iterationId);
return(result.Predictions.ToList());
}
/// <summary>
/// Process an image: perform object detection for price tags, crop each detected object, perform OCR on each object.
/// OCR is performed on a cropped image to improve accuracy of the OCRing.
/// </summary>
/// <param name="imagePath"></param>
/// <param name="saveLocation"></param>
/// <returns></returns>
public async Task ProcessImage(string imagePath, string saveLocation)
{
using (var stream = File.OpenRead(imagePath))
{
Console.WriteLine($"Processing file {imagePath}...");
Console.WriteLine("\tDetecting price tags...");
// Create a Custom Vision prediction endpoint
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = this._customVisionPredictionKey
};
// Invoke the prediction endpoint to detect price tags
var result = endpoint.PredictImage(this._customVisionProjectId, stream);
int tagCount = 0;
Console.WriteLine($"\tDetected {result.Predictions.Count} tags:");
// Loop over each prediction and write out the results
foreach (var c in result.Predictions)
{
// Filter the detected objects to be of the right class and high enough probability
if (_detectionLabels.Contains(c.TagName) && c.Probability > this._probabilityThreshold)
{
// Recalculate bounding boxes from normalized values [0;1]
Image sourceImage = Image.FromFile(imagePath);
Rectangle box = CalculateBoundingBox(c.BoundingBox, sourceImage.Width, sourceImage.Height);
// Crop image to the recalculated bounded box
var cropped = CropImage(sourceImage, box);
Console.WriteLine($"\t\t{c.TagName}: {c.Probability:P1} [ {box.Left}, {box.Top}, {box.Width}, {box.Height} ]");
// Save the extracted objects to disk
cropped.Save(Path.Combine(saveLocation, $"tag_{tagCount}.jpg"));
Console.WriteLine("\t\tPerforming OCR...");
// Perform OCR on the detected price tags
await ReadText(cropped);
// Increment the counter
tagCount++;
}
}
}
}
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 async Task Procesar(Stream img)
{
Indicador.IsRunning = true;
var sproject = trainingApi.GetProjects().ToArray();
var project = sproject[0];
var result = endpoint.PredictImage(project.Id, img);
var c = result.Predictions.ToArray();
await Task.Delay(10000);
for (int i = 0; i < c.Length; i++)
{
Informacion = Informacion + "Con: " + c[i].Tag + "," + String.Format(" Total: {0:P2}.", c[i].Probability) + "\n";
}
Indicador.IsRunning = false;
Mensaje.Text = "Listo";
}
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);
}
static void Main(string[] args)
{
MemoryStream testImage = null;
Guid projectId;
string predictionKey;
try
{
Console.Write("Enter a local image URL: ");
var imagePath = Console.ReadLine();
testImage = new MemoryStream(File.ReadAllBytes(imagePath));
Console.Write("Enter Project Id Guid: ");
var projectIdGuid = Console.ReadLine();
projectId = Guid.Parse(projectIdGuid);
Console.Write("Enter Prediction Key: ");
predictionKey = Console.ReadLine();
Console.WriteLine();
Console.WriteLine();
// Utilizing the Microsoft.Cognitive.CustomVision NuGet Package to establish Credentials and the Endpoint
PredictionEndpointCredentials predictionEndpointCredentials = new PredictionEndpointCredentials(predictionKey);
PredictionEndpoint endpoint = new PredictionEndpoint(predictionEndpointCredentials);
ImagePredictionResultModel result = endpoint.PredictImage(projectId, testImage);
Console.WriteLine("Prediction results for the given image are...");
foreach (ImageTagPrediction prediction in result.Predictions)
{
Console.WriteLine($"{prediction.Tag}: {prediction.Probability:P1}");
}
Console.WriteLine();
exitInNSeconds(5);
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
Console.WriteLine();
exitInNSeconds(5);
}
}
public int Execute()
{
List <string> imagePaths = _pathArgument.Values;
foreach (string imagePath in imagePaths)
{
if (!File.Exists(imagePath))
{
return(Util.Fail($"The path '{imagePath}' does not exist."));
}
}
TrainingApi trainingApi = new TrainingApi()
{
ApiKey = _trainingKey
};
IList <Iteration> iterations = trainingApi.GetIterations(_projectId);
if (iterations.Count == 0)
{
return(Util.Fail("You must train the classifier before trying to make any prediction.\r\nUse the [upload] command to upload at least 5 images to a given classification (tag), and then use the command [train] to train the classifier."));
}
Guid iterationId = iterations.OrderByDescending(i => i.IsDefault).ThenByDescending(i => i.TrainedAt).First().Id;
PredictionEndpoint predictionEndpoint = new PredictionEndpoint()
{
ApiKey = _predictionKey
};
foreach (string imagePath in imagePaths)
{
Console.WriteLine($"\r\n{imagePath}:");
ImagePredictionResultModel result;
using (var imageStream = new MemoryStream(File.ReadAllBytes(imagePath)))
result = predictionEndpoint.PredictImage(_projectId, imageStream, iterationId);
foreach (ImageTagPredictionModel predictedTag in result.Predictions)
{
Console.WriteLine($"\t{predictedTag.Tag}: {predictedTag.Probability:P2}");
}
}
return(0);
}
public async Task <ImageClassificationResult> ClassifyImage(SoftwareBitmap bitmap)
{
var endpoint = new PredictionEndpoint()
{
ApiKey = _Configuration.CognitiveServicesCustomVisionApiKey
};
using (var stream = new InMemoryRandomAccessStream())
{
var encoder = await BitmapEncoder.CreateAsync(BitmapEncoder.JpegEncoderId, stream);
encoder.BitmapTransform.Flip = BitmapFlip.Horizontal;
encoder.SetSoftwareBitmap(bitmap);
await encoder.FlushAsync();
var result = endpoint.PredictImage(
_Configuration.CognitiveServicesCustomVisionProjectId,
stream.AsStream()
);
double highestProbability = 0;
ImageTagPredictionModel predictedModel = null;
foreach (var prediction in result.Predictions)
{
if (prediction.Probability > highestProbability)
{
highestProbability = prediction.Probability;
predictedModel = prediction;
}
}
if (predictedModel == null)
{
return(null);
}
return(new ImageClassificationResult()
{
Tag = predictedModel.Tag,
Probability = predictedModel.Probability
});
}
}
static void Main(string[] args)
{
var keys = GetApiKeys();
var trainingApi = new TrainingApi {
ApiKey = keys.TrainingKey
};
var predictionEndpoint = new PredictionEndpoint {
ApiKey = keys.PredictionKey
};
var projects = trainingApi.GetProjects();
var herbProject = projects.Where(p => p.Name == "Herbs").FirstOrDefault();
Console.WriteLine("Input path to image to test:");
var imagePath = Console.ReadLine();
if (!File.Exists(imagePath))
{
Console.WriteLine("File does not exist. Press enter to exit.");
Console.ReadLine();
return;
}
Console.WriteLine("Image predictions:");
var imageFile = File.OpenRead(imagePath);
if (herbProject != null)
{
var result = predictionEndpoint.PredictImage(herbProject.Id, imageFile);
foreach (var prediction in result.Predictions)
{
Console.WriteLine($"Tag: {prediction.Tag} Probability: {String.Format("Value: {0:P2}.", prediction.Probability)}");
}
}
else
{
Console.WriteLine("Project doesn't exist.");
}
Console.ReadLine();
}
public bool IsValid(Stream imageData)
{
if (IsInitialized)
{
var predictionEndpoint = new PredictionEndpoint()
{
ApiKey = AzureCredentials.PredictionKey
};
var result = predictionEndpoint.PredictImage(CustomVisionProject.Id, imageData);
var overallProbability = result.Predictions.Average(x => x.Probability);
return(overallProbability >= PredictionThreashold);
}
else
{
throw new InvalidOperationException($"{nameof(NZDriverLicenceSmartIdReader)} is not yet initialized. You can monitor the status of the smart reader via the ${nameof(IsInitialized)} property.");
}
}
public static FoodSimResult CalcSim(string fullPath)
{
// Add your prediction key from the settings page of the portal
// The prediction key is used in place of the training key when making predictions
string predictionKey = "72de5d5f661e4114a737d5f56561b604";
// Create a prediction endpoint, passing in obtained prediction key
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = predictionKey
};
// Make a prediction against the new project
var testImage = new MemoryStream(System.IO.File.ReadAllBytes(fullPath));
Guid strProjectId = new Guid("6248af60-83de-4488-837e-6ba0d9e5ca14");
var result = endpoint.PredictImage(strProjectId, testImage);
//// Loop over each prediction and write out the results
//foreach (var c in result.Predictions)
//{
// Console.WriteLine($"\t{c.Tag}: {c.Probability:P1}");
//}
double max = 0;
var name = "";
foreach (var c in result.Predictions)
{
if (c.Probability > max)
{
max = c.Probability;
name = c.Tag;
}
}
return(new FoodSimResult()
{
Name = name, Similarity = max
});
}
static void Main(string[] args)
{
Guid projectId = Guid.Parse("[Insert project ID]");
string predictionKey = "[Insert prediction Key]";
string imagePath = @"d:\sample.jpg";
MemoryStream testImage = new MemoryStream(File.ReadAllBytes(imagePath));
PredictionEndpointCredentials predictionEndpointCredentials = new PredictionEndpointCredentials(predictionKey);
PredictionEndpoint endpoint = new PredictionEndpoint(predictionEndpointCredentials);
ImagePredictionResultModel result = endpoint.PredictImage(projectId, testImage);
// Loop over each prediction and write out the results
foreach (ImageTagPrediction prediction in result.Predictions)
{
Console.WriteLine($"\t{prediction.Tag}: {prediction.Probability:P1}");
}
Console.ReadKey();
}
static void Main(string[] args)
{
Keys keys = null;
using (var reader = new StreamReader("App.json"))
{
var json = reader.ReadToEnd();
keys = JsonConvert.DeserializeObject <Keys>(json);
}
var trainingApi = new TrainingApi {
ApiKey = keys.TrainingKey
};
var predictionEndpoint = new PredictionEndpoint {
ApiKey = keys.PredictionKey
};
var projects = trainingApi.GetProjects();
var herbProject = projects.Where(p => p.Name == "Herbs").FirstOrDefault();
Console.WriteLine("Predicting basil image");
var imageFile = File.OpenRead("basil_test.jpg");
if (herbProject != null)
{
var result = predictionEndpoint.PredictImage(herbProject.Id, imageFile);
foreach (var prediction in result.Predictions)
{
Console.WriteLine($"Tag: {prediction.Tag} Probability: {prediction.Probability}");
}
}
else
{
Console.WriteLine("Project doesn't exist.");
}
Console.ReadLine();
}
public static void MakePrediction()
{
var predictionKey = "031439b0f9ec4549995e53e32971c605";
PredictionEndpointCredentials predictionEndpointCredentials = new PredictionEndpointCredentials(predictionKey);
PredictionEndpoint endpoint = new PredictionEndpoint(predictionEndpointCredentials);
// Make a prediction against the new project
Console.WriteLine("Making a prediction:");
var testImage = HomeController.HaraFinalImage;
var projectId = new Guid("62ccee84-08f9-44e7-89f4-6b5b76894a8a");
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($"\t{c.Tag}: {c.Probability:P1}");
PredictionResults pr = new PredictionResults();
pr.tag = c.Tag;
pr.prediction = c.Probability;
}
}
public static List <PredictionModel> PredictionImage(string base64)
{
string predictionKey = "c5bda34631dc4e399c3114f35fc7f980";
var projectId = new Guid("9ad813c1-4f29-432a-9c9e-e0c53d51a1e9");
// Create a prediction endpoint, passing in the obtained prediction key
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = predictionKey
};
byte[] data = System.Convert.FromBase64String(base64);
MemoryStream ms = new MemoryStream(data);
var result = endpoint.PredictImage(projectId, ms);
List <PredictionModel> predictions = new List <PredictionModel>();
// Loop over each prediction and write out the results
var filterResult = result.Predictions.Where(p => p.Probability > 0.7).ToList();
foreach (var p in filterResult)
{
predictions.Add(p);
}
return(predictions);
}
private static IList <PredictionModel> GetPredictions(string documentbody, TraceWriter log)
{
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = predictionKey
};
log.Info("Making prediction(s):");
IList <PredictionModel> predictions;
using (MemoryStream ms = new MemoryStream(Convert.FromBase64String(documentbody)))
{
var result = endpoint.PredictImage(new Guid(projectId), ms, iterationId: new Guid(iterationId));
predictions = result.Predictions;
foreach (var p in result.Predictions)
{
log.Info($"\t{p.TagName}: {p.Probability:P1} [ {p.BoundingBox.Left}, {p.BoundingBox.Top}, {p.BoundingBox.Width}, {p.BoundingBox.Height} ]");
}
}
log.Info("Got prediction(s):");
return(predictions);
}
public static void RunCustomVisionService(Image image)
{
var predictionEndpointCredentials = new PredictionEndpointCredentials(
Config.Default.CustomVisionPredictionKey
);
var endpoint = new PredictionEndpoint(predictionEndpointCredentials);
var result = endpoint.PredictImage(
new Guid(Config.Default.CustomVisionProjectId),
new MemoryStream(image.Bytes),
new Guid(Config.Default.CustomVisionIterationId));
var waldo = result
.Predictions
.FirstOrDefault(p => p.Tag == "waldo");
if (waldo != null && waldo.Probability > 0.25d)
{
image.WaldoDetected = true;
}
image.ProcessedCustomVision = true;
}
public void Main(string[] args)
{
// Add your training & prediction key from the settings page of the portal
string trainingKey = "d7ba782c8051443c8557ff464418949f";
//string predictionKey = "<your prediction key here>";
// 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
// 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.TagName}: {c.Probability:P1}");
}
Console.ReadKey();
}
static void Main(string[] args)
{
// Add your training and prediction key from the settings page of the portal
string trainingKey = "<add your training key here>";
string predictionKey = "<add your prediction key here>";
// 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 First 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 are then uploaded
foreach (var image in hemlockImages)
{
trainingApi.CreateImagesFromData(project.Id, image, new List <string>()
{
hemlockTag.Id.ToString()
});
}
foreach (var image in japaneseCherryImages)
{
trainingApi.CreateImagesFromData(project.Id, image, new List <string>()
{
japaneseCherryTag.Id.ToString()
});
}
// 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
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.TagName}: {c.Probability:P1}");
}
Console.ReadKey();
}
private async Task MessageReceivedAsync(IDialogContext context, IAwaitable <object> result)
{
var activity = await result as Activity;
//// calculate something for us to return
//int length = (activity.Text ?? string.Empty).Length;
//// return our reply to the user
//await context.PostAsync($"You sent {activity.Text} which was {length} characters");
//context.Wait(MessageReceivedAsync);
var imageAttachment = activity.Attachments?.FirstOrDefault(a => a.ContentType.Contains("image"));
var connector = new ConnectorClient(new Uri(activity.ServiceUrl));
//if (imageAttachment != null)
//{
// using (var stream = await GetImageStream(connector, imageAttachment))
// {
// //return await this.captionService.GetCaptionAsync(stream);
// var textOfStream = await this.captionService.GetCaptionAsync(stream);
// await context.PostAsync($"{textOfStream}");
// }
//}
////ELSE --??
//context.Wait(MessageReceivedAsync);
string predictionProjectId = "3e152a33-92ee-4326-b4c9-c8068edab9d8"; //"YOUR_PROJECT_ID", //This is the custom vision project we are predicting against
string predictionKey = "eafbd7b247bd41c1afd6d6da352f7099";
PredictionEndpoint endpoint = new PredictionEndpoint()
{
ApiKey = predictionKey
};
if (imageAttachment != null)
{
using (var stream = await GetImageStream(connector, imageAttachment))
{
var predictionImageResult = endpoint.PredictImage(new Guid(predictionProjectId), stream);
StringBuilder predictionImageResultString = new StringBuilder();
var resultsList = new List <PredictionResult>();
foreach (var c in predictionImageResult.Predictions)
{
if (c.Probability > .50)
{
predictionImageResultString.Append(c.Tag);
predictionImageResultString.Append(", ");
var probability = (decimal)c.Probability * 100;
var probabilityFixed = probability.ToString("#.##");
predictionImageResultString.Append(probabilityFixed);
predictionImageResultString.Append("%");
predictionImageResultString.Append("; ");
}
//resultsDictionary.Add(c.Tag, (decimal)c.Probability);
//resultsList.Add(new PredictionResult() { PredictionTag = c.Tag, PredictionProbability = (decimal)c.Probability});
}
await context.PostAsync($"Azure Custom Vision results: {predictionImageResultString}");
// var resultsDictionaryString = resultsDictionary.ToString();
// await context.PostAsync($"{resultsDictionaryString}");
var resultsListToString = String.Join <PredictionResult>(", ", resultsList.ToArray());
//await context.PostAsync($"{resultsListToString}");
}
context.Done(true);
}
else
{
context.Done(false);
}
//Original
//context.Wait(MessageReceivedAsync);
//if (imageAttachment != null)
//{
// using (var stream = await GetImageStream(connector, imageAttachment))
// {
// //return await this.captionService.GetCaptionAsync(stream);
// var textOfStream = await this.captionService.GetCaptionAsync(stream);
// await context.PostAsync($"{textOfStream}");
// }
//}
}
private static void TestingTheModel(string testingSetPath, Project project)
{
var predictionKey = ConfigurationManager.AppSettings["CustomVision_PredictionKey"];
var predictionEndpoint = new PredictionEndpoint()
{
ApiKey = predictionKey
};
var testModel = new List <Model>();
var testSet = Directory.GetDirectories(testingSetPath);
var predictionResult = new Dictionary <string, int>();
var labels = new List <string>();
foreach (var subdirectory in testSet)
{
var images = Directory.GetFiles($"{subdirectory}").Select(f =>
{
testModel.Add(new Model()
{
Label = subdirectory, Path = f
});
return(new MemoryStream(File.ReadAllBytes(f)));
}).ToList();
foreach (var testImage in images)
{
try
{
var dir = new DirectoryInfo(subdirectory);
var label = dir.Name;
labels.Add(label);
Console.WriteLine($"\tActual tag: {label}");
var result = predictionEndpoint.PredictImage(project.Id, testImage);
var highProbability = result.Predictions.OrderByDescending(x => x.Probability).First();
var predictedClass = highProbability.Tag;
var predictedProb = highProbability.Probability;
var key = $"{label}|{predictedClass}";
if (!predictionResult.ContainsKey(key))
{
predictionResult.Add(key, 0);
}
predictionResult[key] = predictionResult[key] + 1;
// Loop over each prediction and write out the results
foreach (var c in result.Predictions)
{
Console.WriteLine($"\t{c.Tag}: {c.Probability:P2}");
}
}
catch (Exception e)
{
//kill exception and carry on
Console.WriteLine(e);
}
}
}
try
{
using (TextWriter writer = new StreamWriter($"{testingSetPath}\\testModel.csv"))
{
var csv = new CsvWriter(writer);
csv.WriteRecords(testModel);
}
}
catch (Exception e)
{
Console.WriteLine(e);
}
var array2D = GenerateConfusionMatrix(labels, predictionResult);
//pretty print
PrettyPrint(array2D);
ExporttoCSV(testingSetPath, array2D);
}
static void Main(string[] args)
{
var keys = GetApiKeys();
var trainingApi = new TrainingApi {
ApiKey = keys.TrainingKey
};
var predictionEndpoint = new PredictionEndpoint {
ApiKey = keys.PredictionKey
};
var projects = trainingApi.GetProjects();
var herbProject = projects.FirstOrDefault(p => p.Name == "Herbs");
Console.WriteLine("Press 1 to predict and 2 to train:");
var pathChoice = Console.ReadLine();
if ("1".Equals(pathChoice))
{
Console.WriteLine("Press 1 to predict on a URL or 2 to predict on a local file:");
var predictType = Console.ReadLine();
if ("1".Equals(predictType))
{
Console.WriteLine("Input the URL to an image to test:");
var imageUrl = Console.ReadLine();
if (herbProject != null)
{
var result = predictionEndpoint.PredictImageUrl(herbProject.Id, new Microsoft.Cognitive.CustomVision.Prediction.Models.ImageUrl(imageUrl));
PrintResults(result);
}
}
else
{
Console.WriteLine("Input path to image to test:");
var imagePath = Console.ReadLine();
if (!File.Exists(imagePath))
{
Console.WriteLine("File does not exist. Press enter to exit.");
Console.ReadLine();
return;
}
Console.WriteLine("Image predictions:");
var imageFile = File.OpenRead(imagePath);
if (herbProject != null)
{
var result = predictionEndpoint.PredictImage(herbProject.Id, imageFile);
PrintResults(result);
}
else
{
Console.WriteLine("Project doesn't exist.");
}
}
Console.ReadLine();
}
else
{
Console.WriteLine("Input path to image to train model with:");
var imagePath = Console.ReadLine();
Console.WriteLine("What tag would you give this image? Rosemary, cilantro, or basil?");
var imageTag = Console.ReadLine();
var capitilizedTag = char.ToUpper(imageTag.First()) + imageTag.Substring(1).ToLower();
if (!File.Exists(imagePath))
{
Console.WriteLine("File does not exist. Press enter to exit.");
Console.ReadLine();
return;
}
var imageFile = File.OpenRead(imagePath);
var tags = trainingApi.GetTags(herbProject.Id);
var matchedTag = tags.Tags.FirstOrDefault(t => t.Name == capitilizedTag);
var memoryStream = new MemoryStream();
imageFile.CopyTo(memoryStream);
var fileCreateEntry = new ImageFileCreateEntry(imageFile.Name, memoryStream.ToArray());
var fileCreateBatch = new ImageFileCreateBatch {
Images = new List <ImageFileCreateEntry> {
fileCreateEntry
}, TagIds = new List <Guid> {
matchedTag.Id
}
};
var result = trainingApi.CreateImagesFromFiles(herbProject.Id, fileCreateBatch);
var resultImage = result.Images.FirstOrDefault();
switch (resultImage.Status)
{
case "OKDuplicate":
Console.WriteLine("Image is already used for training. Please use another to train with");
Console.ReadLine();
break;
default:
break;
}
var iteration = trainingApi.TrainProject(herbProject.Id);
while (iteration.Status != "Completed")
{
System.Threading.Thread.Sleep(1000);
iteration = trainingApi.GetIteration(herbProject.Id, iteration.Id);
}
iteration.IsDefault = true;
trainingApi.UpdateIteration(herbProject.Id, iteration.Id, iteration);
Console.WriteLine("Done training!");
Console.ReadLine();
}
}
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();
}
