private void timer1_Tick(object sender, EventArgs e) { //移植元では同じ教育画像で教育しているが、より実践に近い学習に変更 if (this.counter < 11) { //ランダムに点が打たれた画像を生成 NdArray img_p = getRandomImage(); //目標とするフィルタで学習用の画像を出力 NdArray[] img_core = this.decon_core.Forward(img_p); //未学習のフィルタで画像を出力 NdArray[] img_y = this.model.Forward(img_p); //img_yを暗黙的にNdArrayとして使用 this.BackgroundImage = NdArrayConverter.NdArray2Image(img_y[0].GetSingleArray(0)); Real loss = this.meanSquaredError.Evaluate(img_y, img_core); this.model.Backward(img_y); this.model.Update(); this.Text = "[epoch" + this.counter + "] Loss : " + string.Format("{0:F4}", loss); this.counter++; } else { this.timer1.Enabled = false; } }
private void timer1_Tick(object sender, EventArgs e) { //At the transplant source, we are educating with the same educational image, but changing to learning closer to practice if (this.counter < 11) { //Generate random dotted images NdArray img_p = getRandomImage(); //Output a learning image with a target filter NdArray[] img_core = this.decon_core.Forward(img_p); //Output an image with an unlearned filter NdArray[] img_y = this.model.Forward(img_p); //Implicitly use img_y as NdArray this.BackgroundImage = NdArrayConverter.NdArray2Image(img_y[0].GetSingleArray(0)); Real loss = this.meanSquaredError.Evaluate(img_y, img_core); this.model.Backward(img_y); this.model.Update(); this.Text = "[epoch" + this.counter + "] Loss : " + string.Format("{0:F4}", loss); this.counter++; } else { this.timer1.Enabled = false; } }
private void timer1_Tick(object sender, EventArgs e) { // I am educating with the same educational image at the transplanting source, but changing to learning closer to practice if (counter < 11) { // Generate an image with randomly struck points NdArray img_p = getRandomImage(); // Output a learning image with a target filter NdArray[] img_core = decon_core?.Forward(true, img_p); // Output an image with an unlearned filter NdArray[] img_y = model?.Forward(true, img_p); // implicitly use img_y as NdArray BackgroundImage = NdArrayConverter.NdArray2Image(img_y[0].GetSingleArray(0)); Real loss = meanSquaredError.Evaluate(img_y, img_core); model.Backward(true, img_y); model.Update(); Text = "[epoch" + counter + "] Loss : " + $"{loss:F4}"; counter++; } else { timer1.Enabled = false; } }
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 Convolution2D || vggNet[i] is Linear || vggNet[i] is MaxPooling) { ((IParallelizable)vggNet[i]).SetGpuEnable(true); } } 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 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(ResnetModel 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 resnetId = (int)modelType; Console.WriteLine("Mean Loading."); string meanFilePath = InternetFileDownloader.Donwload(DOWNLOAD_URL_MEAN, MODEL_FILE_MEAN, MODEL_FILE_MEAN_HASH); NdArray mean = CaffemodelDataLoader.ReadBinary(meanFilePath); Console.WriteLine("Model Loading."); string modelFilePath = InternetFileDownloader.Donwload(Urls[resnetId], FileNames[resnetId], Hashes[resnetId]); FunctionDictionary nn = CaffemodelDataLoader.LoadNetWork(modelFilePath); string[] classList = File.ReadAllLines(CLASS_LIST_PATH); //GPUを初期化 foreach (FunctionStack resNetFunctionBlock in nn.FunctionBlocks) { SwitchGPU(resNetFunctionBlock); } 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.InterpolationMode = InterpolationMode.Bilinear; g.DrawImage(baseImage, 0, 0, 224, 224); g.Dispose(); NdArray imageArray = NdArrayConverter.Image2NdArray(resultImage, false, true); imageArray -= mean; imageArray.ParentFunc = null; 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 button3_Click(object sender, EventArgs e) { SaveFileDialog sfd = new SaveFileDialog { Filter = "pngファイル(*.png)|*.png|すべてのファイル(*.*)|*.*", FileName = "result.png" }; if (sfd.ShowDialog() == DialogResult.OK) { Task.Factory.StartNew(() => { //ネットワークへ入力する前に予め拡大しておく必要がある Bitmap resultImage = new Bitmap(this._baseImage.Width * 2, this._baseImage.Height * 2, PixelFormat.Format24bppRgb); Graphics g = Graphics.FromImage(resultImage); //補間にニアレストネイバーを使用 g.InterpolationMode = InterpolationMode.NearestNeighbor; //画像を拡大して描画する g.DrawImage(this._baseImage, 0, 0, this._baseImage.Width * 2, this._baseImage.Height * 2); g.Dispose(); NdArray image = NdArrayConverter.Image2NdArray(resultImage); NdArray[] resultArray = this.nn.Predict(image); resultImage = NdArrayConverter.NdArray2Image(resultArray[0].GetSingleArray(0)); resultImage.Save(sfd.FileName); this.pictureBox1.Image = new Bitmap(resultImage); } ).ContinueWith(_ => { MessageBox.Show("変換完了"); }); MessageBox.Show("変換処理は開始されました。\n『変換完了』のメッセージが表示されるまで、しばらくお待ち下さい\n※非常に時間がかかります(64x64の画像で三分ほど)"); } }
private void button3_Click(object sender, EventArgs e) { SaveFileDialog sfd = new SaveFileDialog { Filter = "png file (*. png) | *. png | all files (*. *) | *. *", FileName = "result.png" }; if (sfd.ShowDialog() == DialogResult.OK) { Task.Factory.StartNew(() => { //It is necessary to enlarge in advance before entering the network Bitmap resultImage = new Bitmap(this._baseImage.Width * 2, this._baseImage.Height * 2, PixelFormat.Format24bppRgb); Graphics g = Graphics.FromImage(resultImage); //Use nearest neighbor for interpolation g.InterpolationMode = InterpolationMode.NearestNeighbor; //Draw an image enlarged g.DrawImage(this._baseImage, 0, 0, this._baseImage.Width * 2, this._baseImage.Height * 2); g.Dispose(); NdArray image = NdArrayConverter.Image2NdArray(resultImage); NdArray[] resultArray = this.nn.Predict(image); resultImage = NdArrayConverter.NdArray2Image(resultArray[0].GetSingleArray(0)); resultImage.Save(sfd.FileName); this.pictureBox1.Image = new Bitmap(resultImage); } ).ContinueWith(_ => { MessageBox.Show("Conversion complete"); }); MessageBox.Show("Conversion processing has been started. \n Please wait for a while until \"Conversion completed\" message is displayed \n * It will take a very long time (about three minutes with 64 x 64 images)"); } }
private void button3_Click(object sender, EventArgs e) { SaveFileDialog sfd = new SaveFileDialog { Filter = "png Files(*.png)|*.png|All Files(*.*)|*.*", FileName = "result.png" }; if (sfd.ShowDialog() == DialogResult.OK) { Task.Factory.StartNew(() => { // We need to enlarge in advance before entering the network Bitmap resultImage = new Bitmap(_baseImage.Width * 2, _baseImage.Height * 2, PixelFormat.Format24bppRgb); Graphics g = Graphics.FromImage(resultImage); // use nearest neighbor for interpolation g.InterpolationMode = InterpolationMode.NearestNeighbor; // Enlarge and draw the image g.DrawImage(_baseImage, 0, 0, _baseImage.Width * 2, _baseImage.Height * 2); g.Dispose(); NdArray image = NdArrayConverter.Image2NdArray(resultImage); NdArray[] resultArray = nn.Predict(true, image); resultImage = NdArrayConverter.NdArray2Image(resultArray[0].GetSingleArray(0)); resultImage.Save(sfd.FileName); pictureBox1.Image = new Bitmap(resultImage); } ).ContinueWith(_ => { MessageBox.Show("After the exchange finished"); }); MessageBox.Show("The conversion process has started. \n Please wait for a while until \"conversion complete\" message is displayed \n * It will take a very long time (about 3 minutes with 64 x 64 images)"); } }
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); } } }