CODEWITHSUNDEEP
javascriptnode.jstensorflowcoco
uwe72
uwe72

Reputation: 13

Object Detection (coco-ssd) Node.js: Error: pixels passed to tf.browser.fromPixels() must be either an HTMLVideoElement

I am using on my iobroker on node.js tensorflow-models/coco-ssd'. How do i have to load the image?

When i do it like i do, i get an error: Error: pixels passed to tf.browser.fromPixels() must be either an HTMLVideoElement, HTMLImageElement, HTMLCanvasElement, ImageData in browser, or OffscreenCanvas,

This is my code:

const cocoSsd = require('@tensorflow-models/coco-ssd');
init();
function init() {
    (async () => {

        // Load the model.
        const model = await cocoSsd.load();
        
        // Classify the image.
        var image = fs.readFileSync('/home/iobroker/12-14-2020-tout.jpg');
    
        // Classify the image.
        const predictions = await model.detect(image);
    
        console.log('Predictions: ');
        console.log(predictions);

    })();
}

Upvotes: 1

Views: 1917

Answers (1)

tmilar
tmilar

Reputation: 1921

The error message you are seeing in this case is accurate.

First, in this part, you are initializing image with a file string / Buffer instance.

        // Classify the image.
        var image = fs.readFileSync('/home/iobroker/12-14-2020-tout.jpg');

Then, you are passing it to model.detect():

        // Classify the image.
        const predictions = await model.detect(image);

The issue is that model.detect() is actually expecting an HTML image/video/canvas element. Per the @tensorflow-models/coco-ssd Object detection docs:

It can take input as any browser-based image elements (<img>, <video>, <canvas> elements, for example) and returns an array of bounding boxes with class name and confidence level.

It won't work on a Node server env, as stated by the same document:

Note: The following shows how to use coco-ssd npm to transpile for web deployment, not an example on how to use coco-ssd in the node env.

However, you can follow the steps like the ones of this guide, that shows how to achieve your goal of running it on a Node server.

Example below:

 const cocoSsd = require('@tensorflow-models/coco-ssd');
 const tf = require('@tensorflow/tfjs-node');
 const fs = require('fs').promises;

 // Load the Coco SSD model and image.
 Promise.all([cocoSsd.load(), fs.readFile('/home/iobroker/12-14-2020-tout.jpg')])
 .then((results) => {
   // First result is the COCO-SSD model object.
   const model = results[0];
   // Second result is image buffer.
   const imgTensor = tf.node.decodeImage(new Uint8Array(results[1]), 3);
   // Call detect() to run inference.
   return model.detect(imgTensor);
 })
 .then((predictions) => {
   console.log(JSON.stringify(predictions, null, 2));
 });

Upvotes: 3

Related Questions