mini-jstorch 1.0.0 → 1.0.2

package/README.md

@@ -0,0 +1,24 @@
+# mini-jstorch
+*NOTICE!*:
+This versions is still on a **BETA** Versions of **mini-jstorch**!
+So maybe the features is not many and completely *SO* BE PATIENCE!!
+
+---
+
+**Version: 1.0.2**  
+A lightweight and browser-compatible deep learning framework inspired by **PyTorch** — written in pure JavaScript.  
+Perfect for CodePen, web demos, and fast prototyping.
+
+---
+
+## Features
+
+- # `Sequential` model API
+- # Fully modular layers (e.g., `Dense`)
+- # Activation functions: `ReLU`, `Sigmoid`
+- # Model serialization (`saveModel`, `loadModel`)
+- # Works on both **Node.js** and **browser**
+- # No native bindings, 100% JavaScript
+- # Inspired by PyTorch, but mini-sized
+
+---

package/activations/relu.js

@@ -0,0 +1,7 @@
+export function relu(x) {
+  return x.map(v => Math.max(0, v));
+}
+
+export function sigmoid(x) {
+  return x.map(v => 1 / (1 + Math.exp(-v)));
+}

package/index.js

@@ -0,0 +1,5 @@
+// index.js
+export { Sequential } from './models/Sequential.js';
+export { Dense } from './layers/Dense.js';
+export * as activations from './activations/relu.js';
+export * as io from './utils/io.js';

package/layers/Dense.js

@@ -0,0 +1,17 @@
+import { dot, add } from '../utils/math.js';
+
+export class Dense {
+  constructor(inputSize, outputSize, activation = x => x) {
+    this.weights = Array.from({ length: outputSize }, () =>
+      Array.from({ length: inputSize }, () => Math.random() * 0.1)
+    );
+    this.bias = Array(outputSize).fill(0);
+    this.activation = activation;
+    this.name = "Dense";
+  }
+
+  forward(input) {
+    const z = add(dot(this.weights, input), this.bias);
+    return z.map(this.activation);
+  }
+}

package/models/Sequential.js

@@ -0,0 +1,20 @@
+export class Sequential {
+  constructor() {
+    this.layers = [];
+  }
+
+  add(layer) {
+    this.layers.push(layer);
+  }
+
+  predict(input) {
+    return this.layers.reduce((out, layer) => layer.forward(out), input);
+  }
+
+  summary() {
+    console.log("Sequential model:");
+    this.layers.forEach((layer, i) => {
+      console.log(` Layer ${i + 1}: ${layer.name || "unnamed"}`);
+    });
+  }
+}

package/package.json

@@ -1,12 +1,21 @@
 {
   "name": "mini-jstorch",
-  "version": "1.0.0",
+  "version": "1.0.2",
+  "description": "A lightweight JavaScript neural network framework for browser & Node.js, inspired by PyTorch.",
   "main": "index.js",
-  "scripts": {
-    "test": "echo \"Error: no test specified\" && exit 1"
-  },
-  "keywords": [],
-  "author": "",
-  "license": "ISC",
-  "description": ""
+  "keywords": [
+    "neural-network",
+    "javascript",
+    "lightweight",
+    "ai",
+    "machine-learning",
+    "browser",
+    "mini"
+  ],
+  "author": "Rizal",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/rizal-editors/mini-jstorch.git"
+  }
 }

package/utils/io.js

@@ -0,0 +1,25 @@
+export function saveModel(model) {
+  const modelData = {
+    layers: model.layers.map(layer => ({
+      name: layer.name,
+      weights: layer.weights,
+      bias: layer.bias
+    }))
+  };
+  return JSON.stringify(modelData);
+}
+
+export function loadModel(json, ModelClass, LayerClass) {
+  const data = typeof json === 'string' ? JSON.parse(json) : json;
+  const model = new ModelClass();
+
+  data.layers.forEach(layer => {
+    const dense = new LayerClass(0, 0); // dummy init
+    dense.weights = layer.weights;
+    dense.bias = layer.bias;
+    dense.name = layer.name;
+    model.add(dense);
+  });
+
+  return model;
+}

package/utils/math.js

@@ -0,0 +1,9 @@
+export function dot(weights, input) {
+  return weights.map(row =>
+    row.reduce((sum, val, i) => sum + val * input[i], 0)
+  );
+}
+
+export function add(a, b) {
+  return a.map((val, i) => val + b[i]);
+}