File size: 2,268 Bytes
703811e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 |
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
API_URL = "https://puqif7goarh132kl.us-east-1.aws.endpoints.huggingface.cloud"
headers = {
"Authorization": "Bearer " + os.environ.get("HF_TOKEN"),
"Content-Type": "application/octet-stream",
}
def query(payload):
response = requests.post(API_URL, headers=headers, data=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]])
# Prepare the payload, including the evaluation keys which are needed server side
payload = {
"inputs": "fake",
"encrypted_inputs": encrypted_inputs,
"evaluation_keys": evaluation_keys,
}
# Run the inference on HF servers
duration -= time.time()
encrypted_prediction = query(payload)
duration += time.time()
encrypted_prediction = 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]}")
# 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")
|