learning_model 1.0.3 → 1.0.5

package/build/learning/mobilenet_image.js

@@ -36,48 +36,21 @@ var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, ge
         step((generator = generator.apply(thisArg, _arguments || [])).next());
     });
 };
-var __generator = (this && this.__generator) || function (thisArg, body) {
-    var _ = { label: 0, sent: function() { if (t[0] & 1) throw t[1]; return t[1]; }, trys: [], ops: [] }, f, y, t, g;
-    return g = { next: verb(0), "throw": verb(1), "return": verb(2) }, typeof Symbol === "function" && (g[Symbol.iterator] = function() { return this; }), g;
-    function verb(n) { return function (v) { return step([n, v]); }; }
-    function step(op) {
-        if (f) throw new TypeError("Generator is already executing.");
-        while (g && (g = 0, op[0] && (_ = 0)), _) try {
-            if (f = 1, y && (t = op[0] & 2 ? y["return"] : op[0] ? y["throw"] || ((t = y["return"]) && t.call(y), 0) : y.next) && !(t = t.call(y, op[1])).done) return t;
-            if (y = 0, t) op = [op[0] & 2, t.value];
-            switch (op[0]) {
-                case 0: case 1: t = op; break;
-                case 4: _.label++; return { value: op[1], done: false };
-                case 5: _.label++; y = op[1]; op = [0]; continue;
-                case 7: op = _.ops.pop(); _.trys.pop(); continue;
-                default:
-                    if (!(t = _.trys, t = t.length > 0 && t[t.length - 1]) && (op[0] === 6 || op[0] === 2)) { _ = 0; continue; }
-                    if (op[0] === 3 && (!t || (op[1] > t[0] && op[1] < t[3]))) { _.label = op[1]; break; }
-                    if (op[0] === 6 && _.label < t[1]) { _.label = t[1]; t = op; break; }
-                    if (t && _.label < t[2]) { _.label = t[2]; _.ops.push(op); break; }
-                    if (t[2]) _.ops.pop();
-                    _.trys.pop(); continue;
-            }
-            op = body.call(thisArg, _);
-        } catch (e) { op = [6, e]; y = 0; } finally { f = t = 0; }
-        if (op[0] & 5) throw op[1]; return { value: op[0] ? op[1] : void 0, done: true };
-    }
-};
 Object.defineProperty(exports, "__esModule", { value: true });
-var tf = __importStar(require("@tensorflow/tfjs"));
-var LearningMobilenetImage = /** @class */ (function () {
-    function LearningMobilenetImage(_a) {
-        var _b = _a === void 0 ? {} : _a, _c = _b.modelURL, modelURL = _c === void 0 ? 'https://storage.googleapis.com/tfjs-models/tfjs/mobilenet_v1_0.25_224/model.json' : _c, // 디폴트 mobilenet 이미지 
-        _d = _b.epochs, // 디폴트 mobilenet 이미지 
-        epochs = _d === void 0 ? 10 : _d, _e = _b.batchSize, batchSize = _e === void 0 ? 16 : _e;
+const tf = __importStar(require("@tensorflow/tfjs"));
+class LearningMobilenetImage {
+    constructor({ modelURL = 'https://storage.googleapis.com/tfjs-models/tfjs/mobilenet_v1_0.25_224/model.json', // 디폴트 mobilenet 이미지 
+    epochs = 10, batchSize = 16, limitSize = 2, } = {}) {
         this.trainImages = [];
         this.MOBILE_NET_INPUT_WIDTH = 224;
         this.MOBILE_NET_INPUT_HEIGHT = 224;
         this.MOBILE_NET_INPUT_CHANNEL = 3;
         this.IMAGE_NORMALIZATION_FACTOR = 255.0;
         // 진행 상태를 나타내는 이벤트를 정의합니다.
-        this.onProgress = function () { };
-        this.onLoss = function () { };
+        this.onProgress = () => { };
+        this.onLoss = () => { };
+        this.onTrainBegin = () => { };
+        this.onTrainEnd = () => { };
         this.model = null;
         this.epochs = epochs;
         this.batchSize = batchSize;
@@ -85,12 +58,12 @@ var LearningMobilenetImage = /** @class */ (function () {
         this.modelURL = modelURL;
         this.isRunning = false;
         this.isReady = false;
-        this.limitSize = 2;
+        this.limitSize = limitSize;
     }
     // 학습 데이타 등록 
-    LearningMobilenetImage.prototype.addData = function (label, data) {
+    addData(label, data) {
         try {
-            var tensor = tf.browser.fromPixels(data);
+            const tensor = tf.browser.fromPixels(data);
             console.log('addData', tensor);
             this.trainImages.push(tensor);
             this.labels.push(label);
@@ -103,162 +76,139 @@ var LearningMobilenetImage = /** @class */ (function () {
             console.error('Model training failed', error);
             throw error;
         }
-    };
+    }
     // 모델 학습 처리
-    LearningMobilenetImage.prototype.train = function () {
-        return __awaiter(this, void 0, void 0, function () {
-            var customCallback, _a, inputData, targetData, history_1, error_1;
-            var _this = this;
-            return __generator(this, function (_b) {
-                switch (_b.label) {
-                    case 0:
-                        if (this.isRunning) {
-                            return [2 /*return*/, Promise.reject(new Error('Training is already in progress.'))];
-                        }
-                        customCallback = {
-                            onTrainBegin: function () {
-                                console.log('Training has started.');
-                            },
-                            onTrainEnd: function () {
-                                console.log('Training has ended.');
-                                _this.isRunning = false;
-                            },
-                            onBatchBegin: function (batch, logs) {
-                                console.log("Batch ".concat(batch, " is starting."));
-                            },
-                            onBatchEnd: function (batch, logs) {
-                                console.log("Batch ".concat(batch, " has ended."));
-                            },
-                            onEpochBegin: function (epoch, logs) {
-                                var progress = Math.floor(((epoch + 1) / _this.epochs) * 100);
-                                _this.onProgress(progress);
-                                console.log("Epoch ".concat(epoch + 1, " is starting."));
-                            },
-                            onEpochEnd: function (epoch, logs) {
-                                console.log("Epoch ".concat(epoch + 1, " has ended."));
-                                console.log('Loss:', logs.loss);
-                            }
-                        };
-                        _b.label = 1;
-                    case 1:
-                        _b.trys.push([1, 4, , 5]);
-                        this.isRunning = true;
-                        if (this.labels.length < this.limitSize) {
-                            return [2 /*return*/, Promise.reject(new Error('Please train Data need over 2 data length'))];
-                        }
-                        _a = this;
-                        return [4 /*yield*/, this._createModel(this.labels.length)];
-                    case 2:
-                        _a.model = _b.sent();
-                        inputData = this._preprocessedInputData(this.model);
-                        targetData = this._preprocessedTargetData();
-                        return [4 /*yield*/, this.model.fit(inputData, targetData, {
-                                epochs: this.epochs,
-                                batchSize: this.batchSize,
-                                callbacks: customCallback
-                            })];
-                    case 3:
-                        history_1 = _b.sent();
-                        console.log('Model training completed', history_1);
-                        return [2 /*return*/, history_1];
-                    case 4:
-                        error_1 = _b.sent();
-                        this.isRunning = false;
-                        console.error('Model training failed', error_1);
-                        throw error_1;
-                    case 5: return [2 /*return*/];
+    train() {
+        return __awaiter(this, void 0, void 0, function* () {
+            if (this.isRunning) {
+                return Promise.reject(new Error('Training is already in progress.'));
+            }
+            // 콜백 정의
+            const customCallback = {
+                onTrainBegin: (log) => {
+                    this.onTrainBegin(log);
+                    console.log('Training has started.');
+                },
+                onTrainEnd: (log) => {
+                    this.onTrainEnd(log);
+                    console.log('Training has ended.');
+                    this.isRunning = false;
+                },
+                onBatchBegin: (batch, logs) => {
+                    console.log(`Batch ${batch} is starting.`);
+                },
+                onBatchEnd: (batch, logs) => {
+                    console.log(`Batch ${batch} has ended.`);
+                },
+                onEpochBegin: (epoch, logs) => {
+                    //const progress = Math.floor(((epoch + 1) / this.epochs) * 100);
+                    this.onProgress(epoch + 1);
+                    console.log(`Epoch ${epoch + 1} is starting.`);
+                },
+                onEpochEnd: (epoch, logs) => {
+                    console.log(`Epoch ${epoch + 1} has ended.`);
+                    console.log('Loss:', logs.loss);
+                }
+            };
+            try {
+                this.isRunning = true;
+                if (this.labels.length < this.limitSize) {
+                    return Promise.reject(new Error('Please train Data need over 2 data length'));
                 }
-            });
+                this.model = yield this._createModel(this.labels.length);
+                const inputData = this._preprocessedInputData(this.model);
+                const targetData = this._preprocessedTargetData();
+                const history = yield this.model.fit(inputData, targetData, {
+                    epochs: this.epochs,
+                    batchSize: this.batchSize,
+                    callbacks: customCallback
+                });
+                console.log('Model training completed', history);
+                return history;
+            }
+            catch (error) {
+                this.isRunning = false;
+                console.error('Model training failed', error);
+                throw error;
+            }
         });
-    };
+    }
     // 추론하기
-    LearningMobilenetImage.prototype.infer = function (data) {
-        return __awaiter(this, void 0, void 0, function () {
-            var tensor, resizedTensor, reshapedTensor, predictions, predictionsData, classProbabilities, i, className, probability, existingProbability, error_2;
-            return __generator(this, function (_a) {
-                switch (_a.label) {
-                    case 0:
-                        if (this.model === null) {
-                            throw new Error('Model is null');
-                        }
-                        _a.label = 1;
-                    case 1:
-                        _a.trys.push([1, 3, , 4]);
-                        tensor = tf.browser.fromPixels(data);
-                        resizedTensor = tf.image.resizeBilinear(tensor, [this.MOBILE_NET_INPUT_WIDTH, this.MOBILE_NET_INPUT_HEIGHT]);
-                        reshapedTensor = resizedTensor.expandDims(0);
-                        predictions = this.model.predict(reshapedTensor);
-                        return [4 /*yield*/, predictions.data()];
-                    case 2:
-                        predictionsData = _a.sent();
-                        classProbabilities = new Map();
-                        for (i = 0; i < predictionsData.length; i++) {
-                            className = this.labels[i];
-                            probability = predictionsData[i];
-                            existingProbability = classProbabilities.get(className);
-                            if (existingProbability !== undefined) {
-                                classProbabilities.set(className, existingProbability + probability);
-                            }
-                            else {
-                                classProbabilities.set(className, probability);
-                            }
-                        }
-                        console.log('Class Probabilities:', classProbabilities);
-                        return [2 /*return*/, classProbabilities];
-                    case 3:
-                        error_2 = _a.sent();
-                        throw error_2;
-                    case 4: return [2 /*return*/];
+    infer(data) {
+        return __awaiter(this, void 0, void 0, function* () {
+            if (this.model === null) {
+                throw new Error('Model is null');
+            }
+            try {
+                const tensor = tf.browser.fromPixels(data);
+                const resizedTensor = tf.image.resizeBilinear(tensor, [this.MOBILE_NET_INPUT_WIDTH, this.MOBILE_NET_INPUT_HEIGHT]);
+                const reshapedTensor = resizedTensor.expandDims(0); // 배치 크기 1을 추가하여 4차원으로 변환
+                const predictions = this.model.predict(reshapedTensor);
+                const predictionsData = yield predictions.data(); // 예측 텐서의 데이터를 비동기로 가져옴
+                const classProbabilities = new Map(); // 클래스별 확률 누적값을 저장할 맵
+                for (let i = 0; i < predictionsData.length; i++) {
+                    const className = this.labels[i]; // 클래스 이름
+                    const probability = predictionsData[i];
+                    const existingProbability = classProbabilities.get(className);
+                    if (existingProbability !== undefined) {
+                        classProbabilities.set(className, existingProbability + probability);
+                    }
+                    else {
+                        classProbabilities.set(className, probability);
+                    }
                 }
-            });
+                console.log('Class Probabilities:', classProbabilities);
+                return classProbabilities;
+            }
+            catch (error) {
+                throw error;
+            }
         });
-    };
+    }
     // 모델 저장
-    LearningMobilenetImage.prototype.saveModel = function () {
+    saveModel() {
         console.log('saved model');
-    };
+    }
     // 진행중 여부
-    LearningMobilenetImage.prototype.running = function () {
+    running() {
         return this.isRunning;
-    };
-    LearningMobilenetImage.prototype.ready = function () {
+    }
+    ready() {
         return this.isReady;
-    };
+    }
     // target 라벨 데이타
-    LearningMobilenetImage.prototype._preprocessedTargetData = function () {
-        var _this = this;
+    _preprocessedTargetData() {
         // 라벨 unique 처리 & 배열 리턴
         console.log('uniqueLabels.length', this.labels, this.labels.length);
-        var labelIndices = this.labels.map(function (label) { return _this.labels.indexOf(label); });
+        const labelIndices = this.labels.map((label) => this.labels.indexOf(label));
         console.log('labelIndices', labelIndices);
-        var oneHotEncode = tf.oneHot(tf.tensor1d(labelIndices, 'int32'), this.labels.length);
+        const oneHotEncode = tf.oneHot(tf.tensor1d(labelIndices, 'int32'), this.labels.length);
         console.log('oneHotEncode', oneHotEncode);
         return oneHotEncode;
-    };
+    }
     // 입력 이미지 데이타 
-    LearningMobilenetImage.prototype._preprocessedInputData = function (model) {
-        var _this = this;
+    _preprocessedInputData(model) {
         // 이미지 배열을 배치로 변환 - [null, 224, 224, 3]
-        var inputShape = model.inputs[0].shape;
+        const inputShape = model.inputs[0].shape;
         console.log('inputShape', inputShape);
         // inputShape를 이와 같이 포멧 맞춘다. for reshape to [224, 224, 3]
-        var inputShapeArray = inputShape.slice(1);
+        const inputShapeArray = inputShape.slice(1);
         console.log('inputShapeArray', inputShapeArray);
-        var inputBatch = tf.stack(this.trainImages.map(function (image) {
+        const inputBatch = tf.stack(this.trainImages.map((image) => {
             // 이미지 전처리 및 크기 조정 등을 수행한 후에
             // 모델의 입력 형태로 변환하여 반환
-            var xs = _this._preprocessData(image); // 전처리 함수는 사용자 정의해야 함
+            const xs = this._preprocessData(image); // 전처리 함수는 사용자 정의해야 함
             return tf.reshape(xs, inputShapeArray);
         }));
         return inputBatch;
-    };
+    }
     // 모델 학습하기 위한 데이타 전처리 단계
-    LearningMobilenetImage.prototype._preprocessData = function (tensor) {
+    _preprocessData(tensor) {
         try {
             // mobilenet model summary를 하면 위와 같이 224,224 사이즈의 입력값 설정되어 있다. ex) input_1 (InputLayer) [null,224,224,3]
-            var resizedImage = tf.image.resizeBilinear(tensor, [this.MOBILE_NET_INPUT_WIDTH, this.MOBILE_NET_INPUT_HEIGHT]);
+            const resizedImage = tf.image.resizeBilinear(tensor, [this.MOBILE_NET_INPUT_WIDTH, this.MOBILE_NET_INPUT_HEIGHT]);
             // 이미지를 [0,1] 범위로 정규화 255로 나뉜 픽셀값
-            var normalizedImage = resizedImage.div(this.IMAGE_NORMALIZATION_FACTOR);
+            const normalizedImage = resizedImage.div(this.IMAGE_NORMALIZATION_FACTOR);
             // expandDims(0)을 하여 차원을 추가하여 4D텐서 반환
             return normalizedImage.expandDims(0);
         }
@@ -266,50 +216,41 @@ var LearningMobilenetImage = /** @class */ (function () {
             console.error('Failed to _preprocessData data', error);
             throw error;
         }
-    };
+    }
     // 모델 저장
-    LearningMobilenetImage.prototype._createModel = function (numClasses) {
-        return __awaiter(this, void 0, void 0, function () {
-            var load_model, truncatedModel, _i, _a, layer, model, error_3;
-            return __generator(this, function (_b) {
-                switch (_b.label) {
-                    case 0:
-                        _b.trys.push([0, 2, , 3]);
-                        return [4 /*yield*/, tf.loadLayersModel(this.modelURL)];
-                    case 1:
-                        load_model = _b.sent();
-                        truncatedModel = tf.model({
-                            inputs: load_model.inputs,
-                            outputs: load_model.layers[load_model.layers.length - 2].output
-                        });
-                        // 모델을 학습 가능하게 설정하고 선택한 레이어까지 고정
-                        for (_i = 0, _a = truncatedModel.layers; _i < _a.length; _i++) {
-                            layer = _a[_i];
-                            layer.trainable = false;
-                        }
-                        model = tf.sequential();
-                        model.add(truncatedModel);
-                        model.add(tf.layers.flatten()); // 필요한 경우 Flatten 레이어 추가
-                        model.add(tf.layers.dense({
-                            units: numClasses,
-                            activation: 'softmax'
-                        }));
-                        model.compile({
-                            loss: (numClasses === 2) ? 'binaryCrossentropy' : 'categoricalCrossentropy',
-                            optimizer: tf.train.adam(),
-                            metrics: ['accuracy']
-                        });
-                        model.summary();
-                        return [2 /*return*/, model];
-                    case 2:
-                        error_3 = _b.sent();
-                        console.error('Failed to load model', error_3);
-                        throw error_3;
-                    case 3: return [2 /*return*/];
+    _createModel(numClasses) {
+        return __awaiter(this, void 0, void 0, function* () {
+            try {
+                const load_model = yield tf.loadLayersModel(this.modelURL);
+                // 기존 MobileNet 모델에서 마지막 레이어 제외
+                const truncatedModel = tf.model({
+                    inputs: load_model.inputs,
+                    outputs: load_model.layers[load_model.layers.length - 2].output
+                });
+                // 모델을 학습 가능하게 설정하고 선택한 레이어까지 고정
+                for (let layer of truncatedModel.layers) {
+                    layer.trainable = false;
                 }
-            });
+                const model = tf.sequential();
+                model.add(truncatedModel);
+                model.add(tf.layers.flatten()); // 필요한 경우 Flatten 레이어 추가
+                model.add(tf.layers.dense({
+                    units: numClasses,
+                    activation: 'softmax'
+                }));
+                model.compile({
+                    loss: (numClasses === 2) ? 'binaryCrossentropy' : 'categoricalCrossentropy',
+                    optimizer: tf.train.adam(),
+                    metrics: ['accuracy']
+                });
+                model.summary();
+                return model;
+            }
+            catch (error) {
+                console.error('Failed to load model', error);
+                throw error;
+            }
         });
-    };
-    return LearningMobilenetImage;
-}());
+    }
+}
 exports.default = LearningMobilenetImage;