mini-jstorch 2.0.0 → 2.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +3 -3
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -202,7 +202,7 @@ git clone https://github.com/Rizal-HID11/mini-jstorch-github
|
|
|
202
202
|
|
|
203
203
|
# Quick Start (Recommended Loss)
|
|
204
204
|
|
|
205
|
-
|
|
205
|
+
## Multi-class Classification (SoftmaxCrossEntropy)
|
|
206
206
|
|
|
207
207
|
```javascript
|
|
208
208
|
import {
|
|
@@ -247,7 +247,7 @@ for (let epoch = 1; epoch <= 300; epoch++) {
|
|
|
247
247
|
```
|
|
248
248
|
`Important:` Do not combine `SoftmaxCrossEntropyLoss` with a `Softmax` layer.
|
|
249
249
|
|
|
250
|
-
|
|
250
|
+
## Binary Classifiaction (BCEWithLogitsLoss)
|
|
251
251
|
|
|
252
252
|
```javascript
|
|
253
253
|
import {
|
|
@@ -312,7 +312,7 @@ finalProbs.forEach((prob, i) => {
|
|
|
312
312
|
});
|
|
313
313
|
console.log(`\nAccuracy: ${(correct / X.length * 100).toFixed(2)}%`);
|
|
314
314
|
```
|
|
315
|
-
Do not combine `BCEWithLogitsLoss` with a `Sigmoid` layer.
|
|
315
|
+
`Important:` Do not combine `BCEWithLogitsLoss` with a `Sigmoid` layer.
|
|
316
316
|
|
|
317
317
|
---
|
|
318
318
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "mini-jstorch",
|
|
3
|
-
"version": "2.0.
|
|
3
|
+
"version": "2.0.1",
|
|
4
4
|
"type": "module",
|
|
5
5
|
"description": "A lightweight JavaScript neural network library for learning AI concepts and rapid Frontend experimentation. PyTorch-inspired, zero dependencies, perfect for educational use.",
|
|
6
6
|
"main": "index.js",
|