public async Task <IActionResult> Image(HomeImageModel homeIndexModel)
{
if (homeIndexModel.FileUpload?.Length > 0 && homeIndexModel.FileUpload.Length < 1024000 && ((Path.GetExtension(homeIndexModel.FileUpload.FileName).ToLower() == ".jpg") || (Path.GetExtension(homeIndexModel.FileUpload.FileName).ToLower() == ".png")))
{
var filePath = $"{hostingEnvironment.WebRootPath}\\uploads\\{homeIndexModel.FileUpload.FileName}";
var saveFilePath = Utility.IdentityFileName(filePath);
using (var stream = new FileStream(saveFilePath, FileMode.Create))
{
await homeIndexModel.FileUpload.CopyToAsync(stream);
}
ImageData imageToPredict = new ImageData
{
ImagePath = saveFilePath
};
var perdictionResult = mLImageEngine.Predict(imageToPredict);
var index = perdictionResult.PredictedLabel;
homeIndexModel.Name = GetDiseasesNameForImageClassification(mLImageEngine.GetOriginalLabel(index));
homeIndexModel.PerdictionPercentage = Utility.CalculatePercentage(perdictionResult.Score[index]);
}
else
{
ModelState.AddModelError("FileUpload", "Dữ Liệu không hợp lệ.");
}
return(View(homeIndexModel));
}
private void Form1_Load(object sender, EventArgs e)
{
var imgRepo = new ScreenRepository(Image.FromFile("screenshot.png"));
//var img = imgRepo.GetPart(PartScreenType.ManaPool).Source;
var img = imgRepo.Source;
var solutionDirectory = Path.GetFullPath(Path.Combine(AppContext.BaseDirectory, "../../../../"));
var workspaceRelativePath = Path.Combine(solutionDirectory, "workspace");
var modelRelativePath = Path.Combine(workspaceRelativePath, "model.zip");
var mlEngine = new MLModelEngine <ModelInput, ModelOutput>(modelRelativePath);
//取得 label list, 對應 score 順序
//var labels = mlEngine.RetriveLabels();
foreach (var part in imgRepo.Parts)
{
ModelInput inputData = new ModelInput();
using (var ms = new MemoryStream())
{
part.Source.Save(ms, img.RawFormat);
inputData.Image = ms.ToArray();
}
ModelOutput prediction = mlEngine.Predict(inputData);
//var index = Array.IndexOf(labels, prediction.PredictedLabel);
//var score = prediction.Score[index];
img.TagImage(part.Location, prediction);
}
pictureBox1.Image = img;
}
private bool OnGetPredictSentiment(string SentimentText)
{
SentimentData sampleData = new SentimentData()
{
SentimentText = SentimentText
};
SentimentPrediction prediction = _modelEngine.Predict(sampleData);
return(prediction.Prediction);
}
public IActionResult Index(HomeIndexModel homeIndexModel)
{
if (ModelState.IsValid)
{
var diseasesTraining = new DiseasesSymptomTraining()
{
Syptom = homeIndexModel.Syptom
};
var perdictionResult = mLSymptomEngine.Predict(diseasesTraining);
homeIndexModel.Name = perdictionResult.Name;
homeIndexModel.PerdictionPercentage = Utility.CalculatePercentage(perdictionResult.Score.Max());
}
return(View(homeIndexModel));
}
// (OPTIONAL) Try/test a single prediction with the trained model and any test data
private static void TrySinglePrediction(MLContext mlContext, ITransformer model, IDataView dataView)
{
// Load data to test. Could be any test data. Since this is generated code, a row from a dataView is used
// But here you can try wit any sample data to make a prediction
var sample = mlContext.Data.CreateEnumerable <SampleObservation>(dataView, false).First();
//Create ModelScorer with current available model/transformer and mlContext
var mlModel = new MLModelEngine <SampleObservation, SamplePrediction>(model, mlContext);
// Predict
var resultprediction = mlModel.Predict(sample);
Console.WriteLine($"=============== Single Prediction ===============");
Console.WriteLine($"Actual value: {sample.Fare_amount} | Predicted value: {resultprediction.Score}");
Console.WriteLine($"==================================================");
}
public ActionResult <string> PredictSentiment([FromQuery] string sentimentText)
{
SampleObservation sampleData = new SampleObservation()
{
SentimentText = sentimentText
};
//Predict sentiment
SamplePrediction prediction = _modelEngine.Predict(sampleData);
bool isToxic = prediction.IsToxic;
float probability = CalculatePercentage(prediction.Score);
string retVal = $"Prediction: Is Toxic?: '{isToxic.ToString()}' with {probability.ToString()}% probability of toxicity for the text '{sentimentText}'";
return(retVal);
}
static void Main(string[] args)
{
CancellationTokenSource cts = new CancellationTokenSource();
// Create an opportunity for the user to cancel.
Task.Run(() =>
{
if (Console.ReadKey().KeyChar == 'c' || Console.ReadKey().KeyChar == 'C')
{
cts.Cancel();
}
});
MLContext mlContext = new MLContext(seed: 1);
string modelFolder = $"Forecast/ModelFiles";
string modelFilePathName = $"ModelFiles/country_month_fastTreeTweedie.zip";
var countrySalesModel = new MLModelEngine <CountryData, CountrySalesPrediction>(mlContext,
modelFilePathName,
minPredictionEngineObjectsInPool: 50,
maxPredictionEngineObjectsInPool: 2000,
expirationTime: 30000);
Console.WriteLine("Current number of objects in pool: {0:####.####}", countrySalesModel.CurrentPredictionEnginePoolSize);
//Single Prediction
var singleCountrySample = new CountryData("Australia", 2017, 1, 477, 164, 2486, 9, 10345, 281, 1029);
var singleNextMonthPrediction = countrySalesModel.Predict(singleCountrySample);
Console.WriteLine("Prediction: {0:####.####}", singleNextMonthPrediction.Score);
// Create a high demand for the modelEngine objects.
Parallel.For(0, 1000000, (i, loopState) =>
{
//Sample country data
//next,country,year,month,max,min,std,count,sales,med,prev
//4.23056080166201,Australia,2017,1,477.34,164.916,2486.1346772137,9,10345.71,281.7,1029.11
var countrySample = new CountryData("Australia", 2017, 1, 477, 164, 2486, 9, 10345, 281, i);
// This is the bottleneck in our application. All threads in this loop
// must serialize their access to the static Console class.
Console.CursorLeft = 0;
var nextMonthPrediction = countrySalesModel.Predict(countrySample);
//(Wait for a 1/10 second)
//System.Threading.Thread.Sleep(1000);
Console.WriteLine("Prediction: {0:####.####}", nextMonthPrediction.Score);
Console.WriteLine("-----------------------------------------");
Console.WriteLine("Current number of objects in pool: {0:####.####}", countrySalesModel.CurrentPredictionEnginePoolSize);
if (cts.Token.IsCancellationRequested)
{
loopState.Stop();
}
});
Console.WriteLine("-----------------------------------------");
Console.WriteLine("Current number of objects in pool: {0:####.####}", countrySalesModel.CurrentPredictionEnginePoolSize);
Console.WriteLine("Press the Enter key to exit.");
Console.ReadLine();
cts.Dispose();
}
public static void PredictionImage(this MLModelEngine <ModelInput, ModelOutput> mlEngine,
Image img)
{
var solutionDirectory = Path.GetFullPath(Path.Combine(AppContext.BaseDirectory, "../../../../"));
var assetsRelativePath = Path.Combine(solutionDirectory, "assets");
var undefinedRelativePath = Path.Combine(assetsRelativePath, "undefined");
BlockingCollection <dynamic> predictions = new BlockingCollection <dynamic>();
var imgRawFormat = img.RawFormat;
var imgRepo = new ScreenRepository(img);
var prefixFileName = DateTime.Now.ToString("yyyyMMddHHmmssfff");
System.Threading.Tasks.Parallel.ForEach(imgRepo.Parts, part =>
{
ModelInput inputData = new ModelInput();
using (var ms = new MemoryStream())
{
part.Source.Save(ms, imgRawFormat);
inputData.Image = ms.ToArray();
}
ModelOutput prediction = mlEngine.Predict(inputData);
predictions.Add(new
{
PartImg = part,
Prediction = prediction,
});
var isPredictFail = false;
if (part.PartType == PartScreenType.LifePool && !prediction.PredictedLabel.StartsWith("HP"))
{
isPredictFail = true;
}
else if (part.PartType == PartScreenType.ManaPool && !prediction.PredictedLabel.StartsWith("MP"))
{
isPredictFail = true;
}
else if (prediction.PredictedLabel.StartsWith("HP") && part.PartType != PartScreenType.LifePool)
{
isPredictFail = true;
}
else if (prediction.PredictedLabel.StartsWith("MP") && part.PartType != PartScreenType.ManaPool)
{
isPredictFail = true;
}
else if (part.PartType == PartScreenType.FlaskSlot1 && !prediction.PredictedLabel.StartsWith("LF") &&
!prediction.PredictedLabel.StartsWith("EF"))
{
isPredictFail = true;
}
else if (part.PartType == PartScreenType.FlaskSlot2 && !prediction.PredictedLabel.StartsWith("MF") &&
!prediction.PredictedLabel.StartsWith("EF"))
{
isPredictFail = true;
}
else if (part.PartType == PartScreenType.FlaskSlot3 && !prediction.PredictedLabel.StartsWith("MF") &&
!prediction.PredictedLabel.StartsWith("EF"))
{
isPredictFail = true;
}
else if (part.PartType == PartScreenType.FlaskSlot4 && !prediction.PredictedLabel.StartsWith("MF") &&
!prediction.PredictedLabel.StartsWith("EF"))
{
isPredictFail = true;
}
else if (part.PartType == PartScreenType.FlaskSlot5 && !prediction.PredictedLabel.StartsWith("MF") &&
!prediction.PredictedLabel.StartsWith("EF"))
{
isPredictFail = true;
}
if (isPredictFail || prediction.MaxScore < 0.5)
{
if (!UndefinedImageAllowSaveDate.HasValue || DateTime.Now > UndefinedImageAllowSaveDate.Value)
{
UndefinedImageAllowSaveDate = DateTime.Now.AddMinutes(1);
var filePath = Path.Combine(undefinedRelativePath, $"{prefixFileName}_{part.PartType}.png");
part.Source.Save(filePath);
}
}
});
foreach (var d in predictions)
{
PartScreen part = d.PartImg;
ModelOutput prediction = d.Prediction;
img.TagImage(part.Location, prediction);
}
}