import time
import onnxruntime
import numpy as np

# Set the random seed
np.random.seed(0)

onnx_model_path = 'model.onnx'

# Load the ONNX model with the CPUExecutionProvider
ort_session = onnxruntime.InferenceSession(onnx_model_path, providers=['CPUExecutionProvider'])
ort_session.get_modelmeta()
inputs = ort_session.get_inputs()

nth = 100000

# Warm-up inference to cache optimizations

input_data = np.load("input.npy", allow_pickle=True).item()
ort_session.run(None, input_data)

# Measure inference time excluding input creation
total_time_ns = 0
for _ in range(nth):

    start_ns = time.perf_counter_ns()
    ort_session.run(None, input_data)
    end_ns = time.perf_counter_ns()

    total_time_ns += end_ns - start_ns

avg_time_ns = total_time_ns / nth
avg_time_ms = avg_time_ns / 1e6

print(f'[{onnxruntime.__version__}] Average inference time: {avg_time_ms:.5f} ms')