I'm having trouble with the transition of Tensorflow Python to Tensorflow.js in regards to image preprocessing. What am I missing?

Question

I'm having trouble with the transition of Tensorflow Python to Tensorflow.js in regards to image preprocessing

in Python

single_coin = r"C:\temp\coins\20Saint-03o.jpg"
img = image.load_img(single_coin, target_size = (100, 100))
array = image.img_to_array(img)
x = np.expand_dims(array, axis=0)
vimage = np.vstack([x])
prediction =model.predict(vimage)
print(prediction[0])

I get the correct result

[2.8914417e-05 3.5085387e-03 1.9252902e-03 6.2635467e-05 3.7389682e-03 1.2983804e-03 7.4157811e-04 1.4608903e-04 2.7099697e-06 1.1844193e-02 1.3398369e-04 9.3798796e-03 9.7308388e-05 7.3931034e-05 1.9695959e-04 9.6496813e-05 4.2653349e-04 8.7305409e-05 8.1476872e-04 4.9094640e-04 1.3498703e-04 9.6476960e-01]

However in Tensorflow.js with the same image post the following preprocessing function:

function preprocess(img)
{
     let tensor = tf.browser.fromPixels(img)
     const resized = tf.image.resizeBilinear(tensor, [100, 100]).toFloat()
     const offset = tf.scalar(255.0);
     const normalized = tf.scalar(1.0).sub(resized.div(offset));
     const batched = normalized.expandDims(0)
     return batched
}

I get the following result:

[0.044167134910821915, 0.04726826772093773, 0.04546305909752846, 0.04596292972564697, 0.044733788818120956, 0.04367975518107414, 0.04373137652873993, 0.044592827558517456, 0.045657724142074585, 0.0449688546359539, 0.04648510739207268, 0.04426411911845207, 0.04494940862059593, 0.0457320399582386, 0.045905906707048416, 0.04473186656832695, 0.04691491648554802, 0.04441603645682335, 0.04782886058092117, 0.04696653410792351, 0.045027654618024826, 0.04655187949538231]

I'm obviously not translating the preprocessing appropriately. Does anyone see what I'm missing?

I think you're missing some javascript, there's no code that feeds your batch to your modelin the tensorflow.js code block — Frederik Bode, May 18 '20 at 08:21
There is no normalization applied in the python code but there is a normalization in the js code — edkeveked, May 18 '20 at 09:12

score 1 · Accepted Answer · answered May 18 '20 at 09:15

There is no normalization applied in the python code but there is a normalization in the js code. Either the same normalization applied in js is applied in python as well, or the normalization is removed from the js code.

I'm having trouble with the transition of Tensorflow Python to Tensorflow.js in regards to image preprocessing. What am I missing?

1 Answers1

Linked