play_with_endpoint.py

import numpy as np
import time
import os, sys

from pathlib import Path

from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split

from concrete.ml.deployment import FHEModelClient

import requests


def to_json(python_object):
    if isinstance(python_object, bytes):
        return {"__class__": "bytes", "__value__": list(python_object)}
    raise TypeError(repr(python_object) + " is not JSON serializable")


def from_json(python_object):
    if "__class__" in python_object:
        return bytes(python_object["__value__"])


API_URL = "https://puqif7goarh132kl.us-east-1.aws.endpoints.huggingface.cloud"
headers = {
    "Authorization": "Bearer " + os.environ.get("HF_TOKEN"),
    "Content-Type": "application/json",
}


def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()


path_to_model = Path("compiled_model")
x, y = make_classification(n_samples=1000, class_sep=2, n_features=30, random_state=42)
_, X_test, _, y_test = train_test_split(x, y, test_size=0.2, random_state=42)

# Recover parameters for client side
fhemodel_client = FHEModelClient(path_to_model)

# Generate the keys
fhemodel_client.generate_private_and_evaluation_keys()
evaluation_keys = fhemodel_client.get_serialized_evaluation_keys()

# Test the handler
nb_good = 0
nb_samples = len(X_test)
verbose = False
time_start = time.time()
duration = 0

for i in range(nb_samples):

    # Quantize the input and encrypt it
    encrypted_inputs = fhemodel_client.quantize_encrypt_serialize([X_test[i]])

    if verbose:
        print(f"Size of encrypted input: {sys.getsizeof(encrypted_inputs) / 1024 / 1024} megabytes")
        print(f"Size of keys: {sys.getsizeof(evaluation_keys) / 1024 / 1024} megabytes")

    # Prepare the payload, including the evaluation keys which are needed server side
    payload = {
        "inputs": "fake",
        "encrypted_inputs": to_json(encrypted_inputs),
        "evaluation_keys": to_json(evaluation_keys),
    }

    # Run the inference on HF servers
    duration -= time.time()
    duration_inference = -time.time()
    encrypted_prediction = query(payload)
    duration += time.time()
    duration_inference += time.time()

    encrypted_prediction = from_json(encrypted_prediction)

    # Decrypt the result and dequantize
    prediction_proba = fhemodel_client.deserialize_decrypt_dequantize(encrypted_prediction)[0]
    prediction = np.argmax(prediction_proba)

    if verbose or True:
        print(
            f"for {i}-th input, {prediction=} with expected {y_test[i]} in {duration_inference:.3f} seconds"
        )

    # Measure accuracy
    nb_good += y_test[i] == prediction

print(f"Accuracy on {nb_samples} samples is {nb_good * 1. / nb_samples}")
print(f"Total time: {time.time() - time_start} seconds")
print(f"Duration in inferences: {duration} seconds")
print(f"Duration per inference: {duration / nb_samples} seconds")