public static void Run(VGGModel modelType) { OpenFileDialog ofd = new OpenFileDialog { Filter = "画像ファイル(*.jpg;*.png;*.gif;*.bmp)|*.jpg;*.png;*.gif;*.bmp|すべてのファイル(*.*)|*.*" }; if (ofd.ShowDialog() == DialogResult.OK) { int vggId = (int)modelType; Console.WriteLine("Model Loading."); string modelFilePath = InternetFileDownloader.Donwload(Urls[vggId], FileNames[vggId], Hashes[vggId]); List <Function> vggNet = CaffemodelDataLoader.ModelLoad(modelFilePath); string[] classList = File.ReadAllLines(CLASS_LIST_PATH); //GPUを初期化 for (int i = 0; i < vggNet.Count - 1; i++) { if (vggNet[i] is CPU.Convolution2D || vggNet[i] is CPU.Linear || vggNet[i] is CPU.MaxPooling2D) { vggNet[i] = (Function)CLConverter.Convert(vggNet[i]); } } FunctionStack nn = new FunctionStack(vggNet.ToArray()); //層を圧縮 nn.Compress(); Console.WriteLine("Model Loading done."); do { //ネットワークへ入力する前に解像度を 224px x 224px x 3ch にしておく Bitmap baseImage = new Bitmap(ofd.FileName); Bitmap resultImage = new Bitmap(224, 224, PixelFormat.Format24bppRgb); Graphics g = Graphics.FromImage(resultImage); g.DrawImage(baseImage, 0, 0, 224, 224); g.Dispose(); Real[] bias = { -123.68, -116.779, -103.939 }; //補正値のチャンネル順は入力画像に従う(標準的なBitmapならRGB) NdArray imageArray = BitmapConverter.Image2NdArray(resultImage, false, true, bias); Console.WriteLine("Start predict."); Stopwatch sw = Stopwatch.StartNew(); NdArray result = nn.Predict(imageArray)[0]; sw.Stop(); Console.WriteLine("Result Time : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μs"); int maxIndex = Array.IndexOf(result.Data, result.Data.Max()); Console.WriteLine("[" + result.Data[maxIndex] + "] : " + classList[maxIndex]); } while (ofd.ShowDialog() == DialogResult.OK); } }
public static void Run() { OpenFileDialog ofd = new OpenFileDialog { Filter = "画像ファイル(*.jpg;*.png;*.gif;*.bmp)|*.jpg;*.png;*.gif;*.bmp|すべてのファイル(*.*)|*.*" }; if (ofd.ShowDialog() == DialogResult.OK) { Console.WriteLine("Model Loading."); string modelFilePath = InternetFileDownloader.Donwload(DOWNLOAD_URL, MODEL_FILE); List <Function> alexNet = CaffemodelDataLoader.ModelLoad(modelFilePath); string[] classList = File.ReadAllLines(CLASS_LIST_PATH); //GPUを初期化 for (int i = 0; i < alexNet.Count - 1; i++) { if (alexNet[i] is Convolution2D || alexNet[i] is Linear || alexNet[i] is MaxPooling) { ((IParallelizable)alexNet[i]).SetGpuEnable(true); } } FunctionStack nn = new FunctionStack(alexNet.ToArray()); //層を圧縮 nn.Compress(); Console.WriteLine("Model Loading done."); do { //ネットワークへ入力する前に解像度を 224px x 224px x 3ch にしておく Bitmap baseImage = new Bitmap(ofd.FileName); Bitmap resultImage = new Bitmap(227, 227, PixelFormat.Format24bppRgb); Graphics g = Graphics.FromImage(resultImage); g.DrawImage(baseImage, 0, 0, 227, 227); g.Dispose(); Real[] bias = { -123.68, -116.779, -103.939 }; //補正値のチャンネル順は入力画像に従う NdArray imageArray = NdArrayConverter.Image2NdArray(resultImage, false, true, bias); Console.WriteLine("Start predict."); Stopwatch sw = Stopwatch.StartNew(); NdArray result = nn.Predict(imageArray)[0]; sw.Stop(); Console.WriteLine("Result Time : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μs"); int maxIndex = Array.IndexOf(result.Data, result.Data.Max()); Console.WriteLine("[" + result.Data[maxIndex] + "] : " + classList[maxIndex]); } while (ofd.ShowDialog() == DialogResult.OK); } }
public static void Run() { OpenFileDialog ofd = new OpenFileDialog { Filter = ". Image file (*. Jpg; *. Png; *. Gif; *. Bmp) | *. Jpg; *. Png; *. Gif; *. Bmp | all files (*. *) | *. *" }; if (ofd.ShowDialog() == DialogResult.OK) { Console.WriteLine("Model Loading."); string modelFilePath = InternetFileDownloader.Donwload(DOWNLOAD_URL, MODEL_FILE); List <Function> vgg16Net = CaffemodelDataLoader.ModelLoad(modelFilePath); string[] classList = File.ReadAllLines(CLASS_LIST_PATH); //Initialize GPU for (int i = 0; i < vgg16Net.Count - 1; i++) { if (vgg16Net[i] is Convolution2D || vgg16Net[i] is Linear || vgg16Net[i] is MaxPooling) { ((IParallelizable)vgg16Net[i]).SetGpuEnable(true); } } FunctionStack nn = new FunctionStack(vgg16Net.ToArray()); //Compress layer nn.Compress(); Console.WriteLine("Model Loading done."); do { //Before inputting to the network, set the resolution to 224px x 224px x 3ch Bitmap baseImage = new Bitmap(ofd.FileName); Bitmap resultImage = new Bitmap(224, 224, PixelFormat.Format24bppRgb); Graphics g = Graphics.FromImage(resultImage); g.DrawImage(baseImage, 0, 0, 224, 224); g.Dispose(); Real[] bias = { -123.68, -116.779, -103.939 }; //The channel order of the correction value follows the input image NdArray imageArray = NdArrayConverter.Image2NdArray(resultImage, false, true, bias); Console.WriteLine("Start predict."); Stopwatch sw = Stopwatch.StartNew(); NdArray result = nn.Predict(imageArray)[0]; sw.Stop(); Console.WriteLine("Result Time : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μs"); int maxIndex = Array.IndexOf(result.Data, result.Data.Max()); Console.WriteLine("[" + result.Data[maxIndex] + "] : " + classList[maxIndex]); } while (ofd.ShowDialog() == DialogResult.OK); } }
private void button1_Click(object sender, EventArgs e) { OpenFileDialog ofd = new OpenFileDialog { Filter = "Json file (*. Json) | *. Json | all files (*. *) | *. *", }; if (ofd.ShowDialog() == DialogResult.OK) { int layerCounter = 1; var json = DynamicJson.Parse(File.ReadAllText(ofd.FileName)); List <Function> functionList = new List <Function>(); //Please ignore Microsoft.CSharp.RuntimeBinder.RuntimeBinderException foreach (var data in json) { Real[,,,] weightData = new Real[(int)data["nOutputPlane"], (int)data["nInputPlane"], (int)data["kW"], (int)data["kH"]]; var target = (double[][][][])data["weight"]; for (int i = 0; i < weightData.GetLength(0); i++) { for (int j = 0; j < weightData.GetLength(1); j++) { for (int k = 0; k < weightData.GetLength(2); k++) { for (int l = 0; l < weightData.GetLength(3); l++) { if (weightData.GetLength(0) == target.GetLength(0)) { weightData[i, j, k, l] = target[i][j][k][l]; } else { weightData[i, j, k, l] = target[j][i][k][l]; } } } } } //Make a pad and adjust the size of the input and the output image functionList.Add(new Convolution2D((int)data["nInputPlane"], (int)data["nOutputPlane"], (int)data["kW"], pad: (int)data["kW"] / 2, initialW: weightData, initialb: (Real[])data["bias"], name: "Convolution2D l" + layerCounter++, gpuEnable: true)); functionList.Add(new LeakyReLU(0.1, name: "LeakyReLU l" + layerCounter++)); } nn = new FunctionStack(functionList.ToArray()); nn.Compress(); MessageBox.Show("Read complete"); } }
private void button1_Click(object sender, EventArgs e) { OpenFileDialog ofd = new OpenFileDialog { Filter = "Jsonファイル(*.json)|*.json|すべてのファイル(*.*)|*.*", }; if (ofd.ShowDialog() == DialogResult.OK) { int layerCounter = 1; var json = DynamicJson.Parse(File.ReadAllText(ofd.FileName)); List <Function> functionList = new List <Function>(); //Microsoft.CSharp.RuntimeBinder.RuntimeBinderExceptionは無視して下さい foreach (var data in json) { Real[,,,] weightData = new Real[(int)data["nOutputPlane"], (int)data["nInputPlane"], (int)data["kW"], (int)data["kH"]]; for (int i = 0; i < weightData.GetLength(0); i++) { for (int j = 0; j < weightData.GetLength(1); j++) { for (int k = 0; k < weightData.GetLength(2); k++) { for (int l = 0; l < weightData.GetLength(3); l++) { weightData[i, j, k, l] = data["weight"][i][j][k][l]; } } } } //padを行い入力と出力画像のサイズを合わせる functionList.Add(new Convolution2D((int)data["nInputPlane"], (int)data["nOutputPlane"], (int)data["kW"], pad: (int)data["kW"] / 2, initialW: weightData, initialb: (Real[])data["bias"], name: "Convolution2D l" + layerCounter++, gpuEnable: true)); functionList.Add(new LeakyReLU(0.1, name: "LeakyReLU l" + layerCounter++)); } nn = new FunctionStack(functionList.ToArray()); nn.Compress(); MessageBox.Show("読み込み完了"); } }
static void SwitchGPU(FunctionStack functionStack) { for (int i = 0; i < functionStack.Functions.Length; i++) { if (functionStack.Functions[i] is CPU.Convolution2D || functionStack.Functions[i] is CPU.Linear || functionStack.Functions[i] is CPU.MaxPooling2D) { functionStack.Functions[i] = (Function)CLConverter.Convert(functionStack.Functions[i]); } if (functionStack.Functions[i] is SplitFunction splitFunction) { for (int j = 0; j < splitFunction.SplitedFunctions.Length; j++) { SwitchGPU((FunctionStack)splitFunction.SplitedFunctions[j]); } } } //ブロック単位で層の圧縮を実行 functionStack.Compress(); }
static void SwitchGPU(FunctionStack functionStack) { foreach (Function function in functionStack.Functions) { if (function is Convolution2D || function is Linear || function is MaxPooling) { ((IParallelizable)function).SetGpuEnable(true); } if (function is SplitFunction) { SplitFunction splitFunction = (SplitFunction)function; for (int i = 0; i < splitFunction.SplitedFunctions.Length; i++) { SwitchGPU(splitFunction.SplitedFunctions[i]); } } } //ブロック単位で層の圧縮を実行 functionStack.Compress(); }
static void SwitchGPU(FunctionStack functionStack) { foreach (Function function in functionStack.Functions) { if (function is Convolution2D || function is Linear || function is MaxPooling) { ((IParallelizable)function).SetGpuEnable(true); } if (function is SplitFunction) { SplitFunction splitFunction = (SplitFunction)function; foreach (var t in splitFunction.SplitedFunctions) { SwitchGPU(t); } } } // Compact layer on block basis functionStack.Compress(); }
private static void RunAsync() { var trainData = new NdArray(new[] { 2, 3, 4 }); for (int i = 0; i < trainData.Data.Length; i++) { trainData.Data[i] = (float)i / trainData.Data.Length; } var functions = new List <Function>(); functions.Add(new Convolution2D(2, 1, 3)); var nn = new FunctionStack(functions.ToArray()); nn.Compress(); var optimizer = new Adam(); nn.SetOptimizer(optimizer); var result = nn.Predict(trainData)[0]; }
public static void Run(VGGModel modelType) { OpenFileDialog ofd = new OpenFileDialog { Filter = "画像ファイル(*.jpg;*.png;*.gif;*.bmp)|*.jpg;*.png;*.gif;*.bmp|すべてのファイル(*.*)|*.*" }; if (ofd.ShowDialog() == DialogResult.OK) { int vggId = (int)modelType; Console.WriteLine("Model Loading."); string modelFilePath = InternetFileDownloader.Donwload(Urls[vggId], FileNames[vggId], Hashes[vggId]); List <Function <Real> > vggNet = OnnxmodelDataLoader.LoadNetWork <Real>(modelFilePath); string[] classList = File.ReadAllLines(CLASS_LIST_PATH); //GPUを初期化 for (int i = 0; i < vggNet.Count - 1; i++) { if (vggNet[i] is CPU.Convolution2D <Real> || vggNet[i] is CPU.Linear <Real> || vggNet[i] is CPU.MaxPooling2D <Real> ) { vggNet[i] = (Function <Real>)CLConverter.Convert(vggNet[i]); } } FunctionStack <Real> nn = new FunctionStack <Real>(vggNet.ToArray()); //層を圧縮 nn.Compress(); Console.WriteLine("Model Loading done."); do { //ネットワークへ入力する前に解像度を 224px x 224px x 3ch にしておく Bitmap baseImage = new Bitmap(ofd.FileName); Bitmap resultImage = new Bitmap(224, 224, PixelFormat.Format24bppRgb); Graphics g = Graphics.FromImage(resultImage); g.DrawImage(baseImage, 0, 0, 224, 224); g.Dispose(); Real[] mean = new Real[] { 0.485f, 0.456f, 0.406f }; Real[] std = new Real[] { 0.229f, 0.224f, 0.225f }; NdArray <Real> imageArray = BitmapConverter.Image2NdArray <Real>(resultImage); int dataSize = imageArray.Shape[1] * imageArray.Shape[2]; for (int ch = 0; ch < imageArray.Shape[0]; ch++) { for (int i = 0; i < dataSize; i++) { imageArray.Data[ch * dataSize + i] = (imageArray.Data[ch * dataSize + i] - mean[ch]) / std[ch]; } } Console.WriteLine("Start predict."); Stopwatch sw = Stopwatch.StartNew(); NdArray <Real> result = nn.Predict(imageArray)[0]; sw.Stop(); Console.WriteLine("Result Time : " + (sw.ElapsedTicks / (Stopwatch.Frequency / (1000L * 1000L))).ToString("n0") + "μs"); int maxIndex = Array.IndexOf(result.Data, result.Data.Max()); Console.WriteLine("[" + result.Data[maxIndex] + "] : " + classList[maxIndex]); } while (ofd.ShowDialog() == DialogResult.OK); } }
public static void Main() { // platformIdは、OpenCL・GPUの導入の記事に書いてある方法でご確認ください // https://jinbeizame.hateblo.jp/entry/kelpnet_opencl_gpu Weaver.Initialize(ComputeDeviceTypes.Gpu, platformId: 1, deviceIndex: 0); // ネットからVGGの学習済みモデルをダウンロード string modelFilePath = InternetFileDownloader.Donwload(DOWNLOAD_URL, MODEL_FILE); // 学習済みモデルをFunctionのリストとして保存 List <Function> vgg16Net = CaffemodelDataLoader.ModelLoad(modelFilePath); // VGGの出力層とその活性化関数を削除 vgg16Net.RemoveAt(vgg16Net.Count() - 1); vgg16Net.RemoveAt(vgg16Net.Count() - 1); // VGGの各FunctionのgpuEnableをtrueに for (int i = 0; i < vgg16Net.Count - 1; i++) { // GPUに対応している層であれば、GPU対応へ if (vgg16Net[i] is Convolution2D || vgg16Net[i] is Linear || vgg16Net[i] is MaxPooling) { ((IParallelizable)vgg16Net[i]).SetGpuEnable(true); } } // VGGをリストからFunctionStackに変換 FunctionStack vgg = new FunctionStack(vgg16Net.ToArray()); // 層を圧縮 vgg.Compress(); // 新しく出力層とその活性化関数を用意 FunctionStack nn = new FunctionStack( new Linear(4096, 1, gpuEnable: true), new Sigmoid() ); // 最適化手法としてAdamをセット nn.SetOptimizer(new Adam()); Console.WriteLine("DataSet Loading..."); // 訓練・テストデータ用のNdArrayを用意 // データセットは以下のURLからダウンロードを行い、 // VGGTransfer /bin/Debug/Data にtrainフォルダを置いてください。 // https://www.kaggle.com/c/dogs-vs-cats/data NdArray[] trainData = new NdArray[TRAIN_DATA_LENGTH * 2]; NdArray[] trainLabel = new NdArray[TRAIN_DATA_LENGTH * 2]; NdArray[] testData = new NdArray[TEST_DATA_LENGTH * 2]; NdArray[] testLabel = new NdArray[TEST_DATA_LENGTH * 2]; for (int i = 0; i < TRAIN_DATA_LENGTH + TEST_DATA_LENGTH; i++) { // 犬・猫の画像読み込み Bitmap baseCatImage = new Bitmap("Data/train/cat." + i + ".jpg"); Bitmap baseDogImage = new Bitmap("Data/train/dog." + i + ".jpg"); // 変換後の画像を格納するBitmapを定義 Bitmap catImage = new Bitmap(224, 224, PixelFormat.Format24bppRgb); Bitmap dogImage = new Bitmap(224, 224, PixelFormat.Format24bppRgb); // Graphicsオブジェクトに変換 Graphics gCat = Graphics.FromImage(catImage); Graphics gDog = Graphics.FromImage(dogImage); // Graphicsオブジェクト(の中のcatImageに)baseImageを変換して描画 gCat.DrawImage(baseCatImage, 0, 0, 224, 224); gDog.DrawImage(baseDogImage, 0, 0, 224, 224); // Graphicsオブジェクトを破棄し、メモリを解放 gCat.Dispose(); gDog.Dispose(); // 訓練・テストデータにデータを格納 // 先にテストデータの枚数分テストデータに保存し、その後訓練データを保存する // 画素値の値域は0 ~ 255のため、255で割ることで0 ~ 1に正規化 if (i < TEST_DATA_LENGTH) { // ImageをNdArrayに変換したものをvggに入力し、出力した特徴量を入力データとして保存 testData[i * 2] = vgg.Predict(NdArrayConverter.Image2NdArray(catImage, false, true) / 255.0)[0]; testLabel[i * 2] = new NdArray(new Real[] { 0 }); testData[i * 2 + 1] = vgg.Predict(NdArrayConverter.Image2NdArray(dogImage, false, true) / 255.0)[0]; testLabel[i * 2 + 1] = new NdArray(new Real[] { 1 }); } else { trainData[(i - TEST_DATA_LENGTH) * 2] = vgg.Predict(NdArrayConverter.Image2NdArray(catImage, false, true) / 255.0)[0]; trainLabel[(i - TEST_DATA_LENGTH) * 2] = new NdArray(new Real[] { 0 }); //new Real [] { 0 }; trainData[(i - TEST_DATA_LENGTH) * 2] = vgg.Predict(NdArrayConverter.Image2NdArray(dogImage, false, true) / 255.0)[0]; trainLabel[(i - TEST_DATA_LENGTH) * 2] = new NdArray(new Real[] { 1 }); // = new Real [] { 1 }; } } Console.WriteLine("Training Start..."); // ミニバッチ用のNdArrayを定義 NdArray batchData = new NdArray(new[] { 4096 }, BATCH_SIZE); NdArray batchLabel = new NdArray(new[] { 1 }, BATCH_SIZE); // 誤差関数を定義(今回は二値分類なので二乗誤差関数(MSE)) LossFunction lossFunction = new MeanSquaredError(); // エポックを回す for (int epoch = 0; epoch < 10; epoch++) { // 1エポックで訓練データ // バッチサイズ の回数分学習 for (int step = 0; step < TRAIN_DATA_COUNT; step++) { // ミニバッチを用意 for (int i = 0; i < BATCH_SIZE; i++) { // 0 ~ 訓練データサイズ-1 の中からランダムで整数を取得 int index = Mother.Dice.Next(trainData.Length); // trainData(NdArray[])を、batchData(NdArray)の形にコピー Array.Copy(trainData[index].Data, 0, batchData.Data, i * batchData.Length, batchData.Length); batchLabel.Data[i] = trainLabel[index].Data[0]; } // 学習(順伝播、誤差の計算、逆伝播、更新) NdArray[] output = nn.Forward(batchData); Real loss = lossFunction.Evaluate(output, batchLabel); nn.Backward(output); nn.Update(); } // 認識率(accuracy)の計算 // テストデータの回数データを回す Real accuracy = 0; for (int i = 0; i < TEST_DATA_LENGTH * 2; i++) { NdArray[] output = nn.Predict(testData[i]); // 出力outputと正解の誤差が0.5以下(正解が0のときにoutput<0.5、正解が1のときにoutput>0.5) // の際に正確に認識したとする if (Math.Abs(output[0].Data[0] - trainLabel[i].Data[0]) < 0.5) { accuracy += 1; } accuracy /= TEST_DATA_LENGTH * 2.0; Console.WriteLine("Epoch:" + epoch + "accuracy:" + accuracy); } } }