@epfml/discojs 1.0.0 → 2.0.0

package/dist/client/decentralized/sec_agg.js

@@ -1,169 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.SecAgg = void 0;
-var tslib_1 = require("tslib");
-var immutable_1 = require("immutable");
-var msgpack_lite_1 = (0, tslib_1.__importDefault)(require("msgpack-lite"));
-var __1 = require("../..");
-var base_1 = require("./base");
-var messages = (0, tslib_1.__importStar)(require("./messages"));
-var secret_shares = (0, tslib_1.__importStar)(require("./secret_shares"));
-/**
- * Decentralized client that utilizes secure aggregation so client updates remain private
- */
-var SecAgg = /** @class */ (function (_super) {
-    (0, tslib_1.__extends)(SecAgg, _super);
-    function SecAgg() {
-        var _this = _super !== null && _super.apply(this, arguments) || this;
-        // list of weights received from other clients
-        _this.receivedShares = (0, immutable_1.List)();
-        // list of partial sums received by client
-        _this.receivedPartialSums = (0, immutable_1.List)();
-        // the partial sum calculated by the client
-        _this.mySum = [];
-        return _this;
-    }
-    /*
-    generates shares and sends to all ready peers adds differential privacy
-     */
-    SecAgg.prototype.sendShares = function (noisyWeights, round, trainingInformant) {
-        return (0, tslib_1.__awaiter)(this, void 0, void 0, function () {
-            var weightShares, i, weights, msg, encodedMsg;
-            var _a;
-            return (0, tslib_1.__generator)(this, function (_b) {
-                switch (_b.label) {
-                    case 0:
-                        weightShares = secret_shares.generateAllShares(noisyWeights, this.peers.length, this.maxShareValue);
-                        i = 0;
-                        _b.label = 1;
-                    case 1:
-                        if (!(i < this.peers.length)) return [3 /*break*/, 4];
-                        weights = weightShares.get(i);
-                        if (weights === undefined) {
-                            throw new Error('weight shares generated incorrectly');
-                        }
-                        _a = {
-                            type: messages.messageType.clientSharesMessageServer,
-                            peerID: this.ID
-                        };
-                        return [4 /*yield*/, __1.serialization.weights.encode(weights)];
-                    case 2:
-                        msg = (_a.weights = _b.sent(),
-                            _a.destination = this.peers[i],
-                            _a);
-                        encodedMsg = msgpack_lite_1.default.encode(msg);
-                        this.sendMessagetoPeer(encodedMsg);
-                        _b.label = 3;
-                    case 3:
-                        i++;
-                        return [3 /*break*/, 1];
-                    case 4: return [2 /*return*/];
-                }
-            });
-        });
-    };
-    /*
-  sends partial sums to connected peers so final update can be calculated
-   */
-    SecAgg.prototype.sendPartialSums = function () {
-        return (0, tslib_1.__awaiter)(this, void 0, void 0, function () {
-            var i, msg, encodedMsg;
-            var _a;
-            return (0, tslib_1.__generator)(this, function (_b) {
-                switch (_b.label) {
-                    case 0:
-                        // calculating my personal partial sum from received shares that i will share with peers
-                        this.mySum = __1.aggregation.sumWeights((0, immutable_1.List)(Array.from(this.receivedShares.values())));
-                        i = 0;
-                        _b.label = 1;
-                    case 1:
-                        if (!(i < this.peers.length)) return [3 /*break*/, 4];
-                        _a = {
-                            type: messages.messageType.clientPartialSumsMessageServer,
-                            peerID: this.ID
-                        };
-                        return [4 /*yield*/, __1.serialization.weights.encode(this.mySum)];
-                    case 2:
-                        msg = (_a.partials = _b.sent(),
-                            _a.destination = this.peers[i],
-                            _a);
-                        encodedMsg = msgpack_lite_1.default.encode(msg);
-                        this.sendMessagetoPeer(encodedMsg);
-                        _b.label = 3;
-                    case 3:
-                        i++;
-                        return [3 /*break*/, 1];
-                    case 4: return [2 /*return*/];
-                }
-            });
-        });
-    };
-    SecAgg.prototype.sendAndReceiveWeights = function (noisyWeights, round, trainingInformant) {
-        return (0, tslib_1.__awaiter)(this, void 0, void 0, function () {
-            var _this = this;
-            return (0, tslib_1.__generator)(this, function (_a) {
-                switch (_a.label) {
-                    case 0:
-                        // reset fields at beginning of each round
-                        this.receivedShares = this.receivedShares.clear();
-                        this.receivedPartialSums = this.receivedPartialSums.clear();
-                        // PHASE 1 COMMUNICATION --> send additive shares to ready peers, pause program until shares are received from all peers
-                        return [4 /*yield*/, this.sendShares(noisyWeights, round, trainingInformant)];
-                    case 1:
-                        // PHASE 1 COMMUNICATION --> send additive shares to ready peers, pause program until shares are received from all peers
-                        _a.sent();
-                        return [4 /*yield*/, this.pauseUntil(function () { return _this.receivedShares.size >= _this.peers.length; })
-                            // PHASE 2 COMMUNICATION --> send partial sums to ready peers
-                        ];
-                    case 2:
-                        _a.sent();
-                        // PHASE 2 COMMUNICATION --> send partial sums to ready peers
-                        return [4 /*yield*/, this.sendPartialSums()
-                            // after all partial sums are received, return list of partial sums to be aggregated
-                        ];
-                    case 3:
-                        // PHASE 2 COMMUNICATION --> send partial sums to ready peers
-                        _a.sent();
-                        // after all partial sums are received, return list of partial sums to be aggregated
-                        return [4 /*yield*/, this.pauseUntil(function () { return _this.receivedPartialSums.size >= _this.peers.length; })];
-                    case 4:
-                        // after all partial sums are received, return list of partial sums to be aggregated
-                        _a.sent();
-                        return [2 /*return*/, this.receivedPartialSums];
-                }
-            });
-        });
-    };
-    /*
-    checks if message contains shares from a peer
-     */
-    SecAgg.prototype.instanceOfClientSharesMessageServer = function (msg) {
-        return msg.type === messages.messageType.clientSharesMessageServer;
-    };
-    /*
-    checks if message contains partial sums from a peer
-     */
-    SecAgg.prototype.instanceOfClientPartialSumsMessageServer = function (msg) {
-        return msg.type === messages.messageType.clientPartialSumsMessageServer;
-    };
-    /*
-  handles received messages from signaling server
-   */
-    SecAgg.prototype.clientHandle = function (msg) {
-        if (this.instanceOfClientSharesMessageServer(msg)) {
-            // update received weights by one weights reception
-            var weights = __1.serialization.weights.decode(msg.weights);
-            this.receivedShares = this.receivedShares.push(weights);
-        }
-        else if (this.instanceOfClientPartialSumsMessageServer(msg)) {
-            // update received partial sums by one partial sum
-            var partials = __1.serialization.weights.decode(msg.partials);
-            this.receivedPartialSums = this.receivedPartialSums.push(partials);
-        }
-        else {
-            throw new Error('Unexpected Message Type');
-        }
-    };
-    return SecAgg;
-}(base_1.Base));
-exports.SecAgg = SecAgg;

package/dist/client/decentralized/secret_shares.d.ts

@@ -1,5 +0,0 @@
-import { List } from 'immutable';
-import { Weights } from '../..';
-export declare function lastShare(currentShares: Weights[], secret: Weights): Weights;
-export declare function generateAllShares(secret: Weights, nParticipants: number, maxShareValue: number): List<Weights>;
-export declare function generateRandomShare(secret: Weights, maxShareValue: number): Weights;

package/dist/client/decentralized/secret_shares.js

@@ -1,58 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.generateRandomShare = exports.generateAllShares = exports.lastShare = void 0;
-var tslib_1 = require("tslib");
-var immutable_1 = require("immutable");
-var tf = (0, tslib_1.__importStar)(require("@tensorflow/tfjs"));
-var crypto = (0, tslib_1.__importStar)(require("crypto"));
-var __1 = require("../..");
-var maxSeed = Math.pow(2, 47);
-/*
-Return Weights in the remaining share once N-1 shares have been constructed (where N is number of ready clients)
- */
-function lastShare(currentShares, secret) {
-    if (currentShares.length === 0) {
-        throw new Error('Need at least one current share to be able to subtract secret from');
-    }
-    var currentShares2 = (0, immutable_1.List)(currentShares);
-    var last = __1.aggregation.subtractWeights((0, immutable_1.List)([secret, __1.aggregation.sumWeights(currentShares2)]));
-    return last;
-}
-exports.lastShare = lastShare;
-/*
-Generate N additive shares that aggregate to the secret weights array (where N is number of ready clients)
- */
-function generateAllShares(secret, nParticipants, maxShareValue) {
-    var shares = [];
-    for (var i = 0; i < nParticipants - 1; i++) {
-        shares.push(generateRandomShare(secret, maxShareValue));
-    }
-    shares.push(lastShare(shares, secret));
-    var sharesFinal = (0, immutable_1.List)(shares);
-    return sharesFinal;
-}
-exports.generateAllShares = generateAllShares;
-/*
-generates one share in the same shape as the secret that is populated with values randomly chosend from
-a uniform distribution between (-maxShareValue, maxShareValue).
- */
-function generateRandomShare(secret, maxShareValue) {
-    var e_1, _a;
-    var share = [];
-    var seed = crypto.randomInt(maxSeed);
-    try {
-        for (var secret_1 = (0, tslib_1.__values)(secret), secret_1_1 = secret_1.next(); !secret_1_1.done; secret_1_1 = secret_1.next()) {
-            var t = secret_1_1.value;
-            share.push(tf.randomUniform(t.shape, -maxShareValue, maxShareValue, 'float32', seed));
-        }
-    }
-    catch (e_1_1) { e_1 = { error: e_1_1 }; }
-    finally {
-        try {
-            if (secret_1_1 && !secret_1_1.done && (_a = secret_1.return)) _a.call(secret_1);
-        }
-        finally { if (e_1) throw e_1.error; }
-    }
-    return share;
-}
-exports.generateRandomShare = generateRandomShare;

package/dist/client/decentralized/types.d.ts

@@ -1 +0,0 @@
-export declare type PeerID = number;

package/dist/client/federated.d.ts

@@ -1,30 +0,0 @@
-import { informant, MetadataID, Weights } from '..';
-import { Base } from './base';
-/**
- * Class that deals with communication with the centralized server when training
- * a specific task in the federated setting.
- */
-export declare class Federated extends Base {
-    private readonly clientID;
-    private readonly peer;
-    private round;
-    private urlTo;
-    private urlToMetadata;
-    /**
-     * Initialize the connection to the server. TODO: In the case of FeAI,
-     * should return the current server-side round for the task.
-     */
-    connect(): Promise<void>;
-    /**
-     * Disconnection process when user quits the task.
-     */
-    disconnect(): Promise<void>;
-    postWeightsToServer(weights: Weights): Promise<void>;
-    postMetadata(metadataID: string, metadata: string): Promise<void>;
-    getMetadataMap(metadataID: MetadataID): Promise<Map<string, unknown>>;
-    getLatestServerRound(): Promise<number>;
-    pullRoundAndFetchWeights(): Promise<Weights | undefined>;
-    pullServerStatistics(trainingInformant: informant.FederatedInformant): Promise<void>;
-    onRoundEndCommunication(updatedWeights: Weights, staleWeights: Weights, _: number, trainingInformant: informant.FederatedInformant): Promise<Weights>;
-    onTrainEndCommunication(): Promise<void>;
-}

package/dist/client/federated.js

@@ -1,218 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.Federated = void 0;
-var tslib_1 = require("tslib");
-var msgpack = (0, tslib_1.__importStar)(require("msgpack-lite"));
-var axios_1 = (0, tslib_1.__importDefault)(require("axios"));
-var uuid_1 = require("uuid");
-var __1 = require("..");
-var base_1 = require("./base");
-/**
- * Class that deals with communication with the centralized server when training
- * a specific task in the federated setting.
- */
-var Federated = /** @class */ (function (_super) {
-    (0, tslib_1.__extends)(Federated, _super);
-    function Federated() {
-        var _this = _super !== null && _super.apply(this, arguments) || this;
-        _this.clientID = (0, uuid_1.v4)();
-        _this.round = 0;
-        return _this;
-    }
-    Federated.prototype.urlTo = function (category) {
-        var url = new URL('', this.url);
-        url.pathname += [
-            'feai',
-            category,
-            this.task.taskID,
-            this.clientID
-        ].join('/');
-        return url.href;
-    };
-    Federated.prototype.urlToMetadata = function (metadataID) {
-        var url = new URL('', this.url);
-        url.pathname += [
-            'feai',
-            'metadata',
-            metadataID,
-            this.task.taskID,
-            this.round,
-            this.clientID
-        ].join('/');
-        return url.href;
-    };
-    /**
-     * Initialize the connection to the server. TODO: In the case of FeAI,
-     * should return the current server-side round for the task.
-     */
-    Federated.prototype.connect = function () {
-        return (0, tslib_1.__awaiter)(this, void 0, void 0, function () {
-            return (0, tslib_1.__generator)(this, function (_a) {
-                switch (_a.label) {
-                    case 0: return [4 /*yield*/, axios_1.default.get(this.urlTo('connect'))];
-                    case 1:
-                        _a.sent();
-                        return [2 /*return*/];
-                }
-            });
-        });
-    };
-    /**
-     * Disconnection process when user quits the task.
-     */
-    Federated.prototype.disconnect = function () {
-        return (0, tslib_1.__awaiter)(this, void 0, void 0, function () {
-            return (0, tslib_1.__generator)(this, function (_a) {
-                switch (_a.label) {
-                    case 0: return [4 /*yield*/, axios_1.default.get(this.urlTo('disconnect'))];
-                    case 1:
-                        _a.sent();
-                        return [2 /*return*/];
-                }
-            });
-        });
-    };
-    Federated.prototype.postWeightsToServer = function (weights) {
-        return (0, tslib_1.__awaiter)(this, void 0, void 0, function () {
-            var _a;
-            var _b, _c;
-            return (0, tslib_1.__generator)(this, function (_d) {
-                switch (_d.label) {
-                    case 0:
-                        _a = axios_1.default;
-                        _b = {
-                            method: 'post',
-                            url: this.urlTo('weights')
-                        };
-                        _c = {};
-                        return [4 /*yield*/, __1.serialization.weights.encode(weights)];
-                    case 1: return [4 /*yield*/, _a.apply(void 0, [(_b.data = (_c.weights = _d.sent(),
-                                _c.round = this.round,
-                                _c),
-                                _b)])];
-                    case 2:
-                        _d.sent();
-                        return [2 /*return*/];
-                }
-            });
-        });
-    };
-    Federated.prototype.postMetadata = function (metadataID, metadata) {
-        return (0, tslib_1.__awaiter)(this, void 0, void 0, function () {
-            return (0, tslib_1.__generator)(this, function (_a) {
-                switch (_a.label) {
-                    case 0: return [4 /*yield*/, (0, axios_1.default)({
-                            method: 'post',
-                            url: this.urlToMetadata(metadataID),
-                            data: {
-                                metadataID: metadata
-                            }
-                        })];
-                    case 1:
-                        _a.sent();
-                        return [2 /*return*/];
-                }
-            });
-        });
-    };
-    Federated.prototype.getMetadataMap = function (metadataID) {
-        return (0, tslib_1.__awaiter)(this, void 0, void 0, function () {
-            var response, body;
-            return (0, tslib_1.__generator)(this, function (_a) {
-                switch (_a.label) {
-                    case 0: return [4 /*yield*/, axios_1.default.get(this.urlToMetadata(metadataID))];
-                    case 1:
-                        response = _a.sent();
-                        return [4 /*yield*/, response.data];
-                    case 2:
-                        body = _a.sent();
-                        return [2 /*return*/, new Map(msgpack.decode(body[metadataID]))];
-                }
-            });
-        });
-    };
-    Federated.prototype.getLatestServerRound = function () {
-        return (0, tslib_1.__awaiter)(this, void 0, void 0, function () {
-            var response;
-            return (0, tslib_1.__generator)(this, function (_a) {
-                switch (_a.label) {
-                    case 0: return [4 /*yield*/, axios_1.default.get(this.urlTo('round'))];
-                    case 1:
-                        response = _a.sent();
-                        if (response.status === 200) {
-                            return [2 /*return*/, response.data.round];
-                        }
-                        console.log('Error getting weights: code', response.status);
-                        return [2 /*return*/, -1];
-                }
-            });
-        });
-    };
-    Federated.prototype.pullRoundAndFetchWeights = function () {
-        return (0, tslib_1.__awaiter)(this, void 0, void 0, function () {
-            var serverRound, response, serverWeights;
-            return (0, tslib_1.__generator)(this, function (_a) {
-                switch (_a.label) {
-                    case 0: return [4 /*yield*/, this.getLatestServerRound()];
-                    case 1:
-                        serverRound = _a.sent();
-                        return [4 /*yield*/, axios_1.default.get(this.urlTo('weights'))];
-                    case 2:
-                        response = _a.sent();
-                        serverWeights = __1.serialization.weights.decode(response.data);
-                        if (this.round < serverRound) {
-                            // Update the local round to match the server's
-                            this.round = serverRound;
-                            return [2 /*return*/, serverWeights];
-                        }
-                        else {
-                            return [2 /*return*/, undefined];
-                        }
-                        return [2 /*return*/];
-                }
-            });
-        });
-    };
-    Federated.prototype.pullServerStatistics = function (trainingInformant) {
-        return (0, tslib_1.__awaiter)(this, void 0, void 0, function () {
-            var response;
-            return (0, tslib_1.__generator)(this, function (_a) {
-                switch (_a.label) {
-                    case 0: return [4 /*yield*/, axios_1.default.get(this.urlTo('statistics'))];
-                    case 1:
-                        response = _a.sent();
-                        trainingInformant.update(response.data.statistics);
-                        return [2 /*return*/];
-                }
-            });
-        });
-    };
-    Federated.prototype.onRoundEndCommunication = function (updatedWeights, staleWeights, _, trainingInformant) {
-        return (0, tslib_1.__awaiter)(this, void 0, void 0, function () {
-            var noisyWeights, serverWeights;
-            return (0, tslib_1.__generator)(this, function (_a) {
-                switch (_a.label) {
-                    case 0:
-                        noisyWeights = __1.privacy.addDifferentialPrivacy(updatedWeights, staleWeights, this.task);
-                        return [4 /*yield*/, this.postWeightsToServer(noisyWeights)];
-                    case 1:
-                        _a.sent();
-                        return [4 /*yield*/, this.pullServerStatistics(trainingInformant)];
-                    case 2:
-                        _a.sent();
-                        return [4 /*yield*/, this.pullRoundAndFetchWeights()];
-                    case 3:
-                        serverWeights = _a.sent();
-                        return [2 /*return*/, serverWeights !== null && serverWeights !== void 0 ? serverWeights : staleWeights];
-                }
-            });
-        });
-    };
-    Federated.prototype.onTrainEndCommunication = function () {
-        return (0, tslib_1.__awaiter)(this, void 0, void 0, function () { return (0, tslib_1.__generator)(this, function (_a) {
-            return [2 /*return*/];
-        }); });
-    };
-    return Federated;
-}(base_1.Base));
-exports.Federated = Federated;

package/dist/dataset/index.d.ts

@@ -1,2 +0,0 @@
-export { Dataset, DatasetBuilder } from './dataset_builder';
-export * from './data_loader';

package/dist/dataset/index.js

@@ -1,7 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.DatasetBuilder = void 0;
-var tslib_1 = require("tslib");
-var dataset_builder_1 = require("./dataset_builder");
-Object.defineProperty(exports, "DatasetBuilder", { enumerable: true, get: function () { return dataset_builder_1.DatasetBuilder; } });
-(0, tslib_1.__exportStar)(require("./data_loader"), exports);

package/dist/model_actor.d.ts

@@ -1,16 +0,0 @@
-import { Logger } from '@/logging/logger';
-import { Task } from '@/task';
-/**
- * Base class for all actors of the system (e.g. trainer, tester, etc.)
- * containing commonly used parameters
- */
-export declare class ModelActor {
-    task: Task;
-    logger: Logger;
-    /**
-     * Constructor for Actor
-     * @param {Task} task - task on which the tasking shall be performed
-     * @param {Logger} logger - logging system (e.g. toaster)
-     */
-    constructor(task: Task, logger: Logger);
-}

package/dist/model_actor.js

@@ -1,20 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.ModelActor = void 0;
-/**
- * Base class for all actors of the system (e.g. trainer, tester, etc.)
- * containing commonly used parameters
- */
-var ModelActor = /** @class */ (function () {
-    /**
-     * Constructor for Actor
-     * @param {Task} task - task on which the tasking shall be performed
-     * @param {Logger} logger - logging system (e.g. toaster)
-     */
-    function ModelActor(task, logger) {
-        this.task = task;
-        this.logger = logger;
-    }
-    return ModelActor;
-}());
-exports.ModelActor = ModelActor;

package/dist/serialization/weights.d.ts

@@ -1,5 +0,0 @@
-import { Weights } from '@/types';
-export declare type Encoded = number[];
-export declare function isEncoded(raw: unknown): raw is Encoded;
-export declare function encode(weights: Weights): Promise<Encoded>;
-export declare function decode(encoded: Encoded): Weights;

package/dist/task/model_compile_data.d.ts

@@ -1,6 +0,0 @@
-export declare class ModelCompileData {
-    readonly optimizer: string;
-    readonly loss: string;
-    readonly metrics: string[];
-    constructor(optimizer: string, loss: string, metrics: string[]);
-}

package/dist/task/model_compile_data.js

@@ -1,12 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.ModelCompileData = void 0;
-var ModelCompileData = /** @class */ (function () {
-    function ModelCompileData(optimizer, loss, metrics) {
-        this.optimizer = optimizer;
-        this.loss = loss;
-        this.metrics = metrics;
-    }
-    return ModelCompileData;
-}());
-exports.ModelCompileData = ModelCompileData;

package/dist/tasks/lus_covid.d.ts

@@ -1,4 +0,0 @@
-import * as tf from '@tensorflow/tfjs';
-import { Task } from '../task';
-export declare const task: Task;
-export declare function model(imageHeight?: number, imageWidth?: number, imageChannels?: number, numOutputClasses?: number): tf.LayersModel;

package/dist/tasks/simple_face.d.ts

@@ -1,4 +0,0 @@
-import * as tf from '@tensorflow/tfjs';
-import { Task } from '../task';
-export declare const task: Task;
-export declare function model(imageHeight?: number, imageWidth?: number, imageChannels?: number, numOutputClasses?: number): tf.LayersModel;

package/dist/tasks/simple_face.js

@@ -1,84 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.model = exports.task = void 0;
-var tslib_1 = require("tslib");
-var tf = (0, tslib_1.__importStar)(require("@tensorflow/tfjs"));
-exports.task = {
-    taskID: 'simple_face',
-    displayInformation: {
-        taskTitle: 'Simple Face',
-        summary: {
-            preview: 'Can you detect if the person in a picture is a child or an adult?',
-            overview: 'Simple face is a small subset of face_task from Kaggle'
-        },
-        limitations: 'The training data is limited to small images of size 200x200.',
-        tradeoffs: 'Training success strongly depends on label distribution',
-        dataFormatInformation: '',
-        dataExampleText: 'Below you find an example',
-        dataExampleImage: './simple_face-example.png'
-    },
-    trainingInformation: {
-        modelID: 'simple_face-model',
-        epochs: 50,
-        roundDuration: 1,
-        validationSplit: 0.2,
-        batchSize: 10,
-        preprocessFunctions: [],
-        learningRate: 0.001,
-        modelCompileData: {
-            optimizer: 'sgd',
-            loss: 'categoricalCrossentropy',
-            metrics: ['accuracy']
-        },
-        dataType: 'image',
-        csvLabels: false,
-        IMAGE_H: 200,
-        IMAGE_W: 200,
-        LABEL_LIST: ['child', 'adult'],
-        scheme: 'Federated'
-    }
-};
-function model(imageHeight, imageWidth, imageChannels, numOutputClasses) {
-    if (imageHeight === void 0) { imageHeight = 200; }
-    if (imageWidth === void 0) { imageWidth = 200; }
-    if (imageChannels === void 0) { imageChannels = 3; }
-    if (numOutputClasses === void 0) { numOutputClasses = 2; }
-    var model = tf.sequential();
-    // In the first layer of our convolutional neural network we have
-    // to specify the input shape. Then we specify some parameters for
-    // the convolution operation that takes place in this layer.
-    model.add(tf.layers.conv2d({
-        inputShape: [imageHeight, imageWidth, imageChannels],
-        kernelSize: 5,
-        filters: 8,
-        strides: 1,
-        activation: 'relu',
-        kernelInitializer: 'varianceScaling'
-    }));
-    // The MaxPooling layer acts as a sort of downsampling using max values
-    // in a region instead of averaging.
-    model.add(tf.layers.maxPooling2d({ poolSize: [2, 2], strides: [2, 2] }));
-    // Repeat another conv2d + maxPooling stack.
-    // Note that we have more filters in the convolution.
-    model.add(tf.layers.conv2d({
-        kernelSize: 5,
-        filters: 16,
-        strides: 1,
-        activation: 'relu',
-        kernelInitializer: 'varianceScaling'
-    }));
-    model.add(tf.layers.maxPooling2d({ poolSize: [2, 2], strides: [2, 2] }));
-    // Now we flatten the output from the 2D filters into a 1D vector to prepare
-    // it for input into our last layer. This is common practice when feeding
-    // higher dimensional data to a final classification output layer.
-    model.add(tf.layers.flatten());
-    // Our last layer is a dense layer which has 10 output units, one for each
-    // output class (i.e. 0, 1, 2, 3, 4, 5, 6, 7, 8, 9).
-    model.add(tf.layers.dense({
-        units: numOutputClasses,
-        kernelInitializer: 'varianceScaling',
-        activation: 'softmax'
-    }));
-    return model;
-}
-exports.model = model;

package/dist/tfjs.d.ts

@@ -1,2 +0,0 @@
-import * as tf from '@tensorflow/tfjs';
-export { tf };