如何在服务器上托管 function，我可以从我的 python 脚本调用它？

Question

I recently made a program which runs a ML model on an image, and predicts what it is. The problem is that, including the model and the dependencies like tensorflow, causes it to be 500mb . So I was wondering if I could host the function in a server, where I could pass in my image, and it would return the output back. Here's the function I wish to host-

from keras.models import load_model
from PIL import Image, ImageOps
import numpy as np
labels= ["Banana", "Fan", "Clock","Coin","Leaf","Paper_airplane","Pen","Phone","Spoon","Tomato"]
model = load_model('keras_model.h5')
data = np.ndarray(shape=(1, 224, 224, 3), dtype=np.float32)

#Here I wish to pass the image, from my python program, and recieve the prediction
def RunPrediction(img):
    image = img
    size = (224, 224)
    image = ImageOps.fit(image, size, Image.ANTIALIAS)

    image_array = np.asarray(image)
    normalized_image_array = (image_array.astype(np.float32) / 127.0) - 1
    data[0] = normalized_image_array

    #And I want to recieve this output in my code
    prediction = model.predict(data)

    return prediction

And how do I go about calling this function, with my python script? Thanks!

How do I achieve this? Thanks!

Answer 1

Make a RestAPI and call it in your program.

here is a link for help on RestAPI's: https://blog.miguelgrinberg.com/post/the-flask-mega-tutorial-part-xxiii-application-programming-interfaces-apis