CODEWITHSUNDEEP
imagetensorflowtensortensorflow.js
Sir hennihau
Sir hennihau

Reputation: 1774

Create a tensor of multiple images with tf.browser.fromPixels with Tensorflow JS

I want to create a feature tensor of multiple images, using tf.browser.fromPixels.

const image1 = new ImageData(1, 1);
image1.data[0] = 100;
image1.data[1] = 150;
image1.data[2] = 200;
image1.data[3] = 255;

const image2 = new ImageData(1, 1);
image2.data[0] = 200;
image2.data[1] = 250;
image2.data[2] = 200;
image2.data[3] = 255;

const imageTensor1 = tf.browser.fromPixels(image1);
const imageTensor2 = tf.broser.fromPixels(image2);

// How do I now get imageTensor1 and imageTensor2 into one merged tensor?
const featureData = ???

How can I now merge two tensors into one tensor, contain information about both images? Are there any operations like tensor.push() or anything available? Do I need to keep the values as a array and only merge it into one tensor in the end?

Upvotes: 1

Views: 990

Answers (2)

CanobbioE
CanobbioE

Reputation: 232

You can concatenate tensors with tf.concat(tensors, axis?)

const a = tf.tensor1d([1, 2]);
const b = tf.tensor1d([3, 4]);
a.concat(b);

Or with multiple tensors

const a = tf.tensor1d([1, 2]);
const b = tf.tensor1d([3, 4]);
const c = tf.tensor1d([5, 6]);
tf.concat([a, b, c]);

Upvotes: 2

Sir hennihau
Sir hennihau

Reputation: 1774

Actually I learned that there is no need to do that in the first place, because model.fit() accepts an array of tensors, too. So you can just create an array out of multiple tensors.

https://js.tensorflow.org/api/latest/#tf.LayersModel.fit

Upvotes: 0

Related Questions