potree-sdk/libs/npyjs

npy.js

Read .npy files directly in JS

Read .npy files from numpy in Node/JS.

Installation

Include npy.js in your project directly, or:

yarn add npyjs
# npm i npyjs

Import

import npyjs from "npyjs";

Usage

• Create a new npyjs object:

let n = new npyjs();
// Or with options:
let n = new npyjs({ convertFloat16: false }); // Disable float16 to float32 conversion

• This object can now be used load .npy files. Arrays can be returned via a JavaScript callback, so usage looks like this:

n.load("my-array.npy", (array, shape) => {
    // `array` is a one-dimensional array of the raw data
    // `shape` is a one-dimensional array that holds a numpy-style shape.
    console.log(`You loaded an array with ${array.length} elements and ${shape.length} dimensions.`);
});

• You can also use this library promise-style using either .then or async await:

n.load("test.npy").then((res) => {
    // res has { data, shape, dtype } members.
});

const npyArray = await n.load("test.npy");

Accessing multidimensional array elements

• You can conveniently access multidimensional array elements using the 'ndarray' library:

import ndarray from "ndarray";
const npyArray = ndarray(data, shape);
npyArray.get(10, 15);

Supported Data Types

The library supports the following NumPy data types:

• int8, uint8
• int16, uint16
• int32, uint32
• int64, uint64 (as BigInt)
• float32
• float64
• float16 (converted to float32 by default)

Float16 Support

By default, float16 arrays are automatically converted to float32 for compatibility, since JavaScript doesn't natively support float16. You can control this behavior with the constructor options:

// Default behavior - float16 is converted to float32
const n1 = new npyjs();
// Keep float16 as raw uint16 values without conversion
const n2 = new npyjs({ convertFloat16: false });

Unless otherwise specified, all code inside of this repository is covered under the license in LICENSE.

Please report bugs or contribute pull-requests on GitHub.

---

Made with ♥ at