simple_grpc_aio_infer_client.py

#!/usr/bin/env python
# Copyright 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
# are met:
#  * Redistributions of source code must retain the above copyright
#    notice, this list of conditions and the following disclaimer.
#  * Redistributions in binary form must reproduce the above copyright
#    notice, this list of conditions and the following disclaimer in the
#    documentation and/or other materials provided with the distribution.
#  * Neither the name of NVIDIA CORPORATION nor the names of its
#    contributors may be used to endorse or promote products derived
#    from this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

import argparse
import numpy as np
import sys
import asyncio

import tritonclient.grpc.aio as grpcclient


def get_triton_client(FLAGS):

    try:
        triton_client = grpcclient.InferenceServerClient(
            url=FLAGS.url,
            verbose=FLAGS.verbose,
            ssl=FLAGS.ssl,
            root_certificates=FLAGS.root_certificates,
            private_key=FLAGS.private_key,
            certificate_chain=FLAGS.certificate_chain)
    except Exception as e:
        print("channel creation failed: " + str(e))
        sys.exit()

    return triton_client


def get_inputs_and_outputs():

    # Infer
    inputs = []
    outputs = []
    inputs.append(grpcclient.InferInput('INPUT0', [1, 16], "INT32"))
    inputs.append(grpcclient.InferInput('INPUT1', [1, 16], "INT32"))

    # Create the data for the two input tensors. Initialize the first
    # to unique integers and the second to all ones.
    input0_data = np.arange(start=0, stop=16, dtype=np.int32)
    input0_data = np.expand_dims(input0_data, axis=0)
    input1_data = np.ones(shape=(1, 16), dtype=np.int32)

    # Initialize the data
    inputs[0].set_data_from_numpy(input0_data)
    inputs[1].set_data_from_numpy(input1_data)

    outputs.append(grpcclient.InferRequestedOutput('OUTPUT0'))
    outputs.append(grpcclient.InferRequestedOutput('OUTPUT1'))

    return inputs, outputs, input0_data, input1_data


def get_output(input0_data, input1_data, results):

    # Get the output arrays from the results
    output0_data = results.as_numpy('OUTPUT0')
    output1_data = results.as_numpy('OUTPUT1')

    # Validate the output
    for i in range(16):
        print(
            str(input0_data[0][i]) + " + " + str(input1_data[0][i]) + " = " +
            str(output0_data[0][i]))
        print(
            str(input0_data[0][i]) + " - " + str(input1_data[0][i]) + " = " +
            str(output1_data[0][i]))
        if (input0_data[0][i] + input1_data[0][i]) != output0_data[0][i]:
            print("sync infer error: incorrect sum")
            sys.exit(1)
        if (input0_data[0][i] - input1_data[0][i]) != output1_data[0][i]:
            print("sync infer error: incorrect difference")
            sys.exit(1)


async def main(FLAGS):

    # Initialize
    triton_client = get_triton_client(FLAGS)
    model_name = "simple"
    inputs, outputs, input0_data, input1_data = get_inputs_and_outputs()

    # Test with outputs
    results = await triton_client.infer(
        model_name=model_name,
        inputs=inputs,
        outputs=outputs,
        client_timeout=FLAGS.client_timeout,
        headers={'test': '1'},
        compression_algorithm=FLAGS.grpc_compression_algorithm)

    statistics = await triton_client.get_inference_statistics(
        model_name=model_name)
    print(statistics)
    if len(statistics.model_stats) != 1:
        print("FAILED: Inference Statistics")
        sys.exit(1)

    get_output(input0_data, input1_data, results)

    # Test with no outputs, in parallel
    result_1, result_2 = await asyncio.gather(
        triton_client.infer(
            model_name=model_name,
            inputs=inputs,
            outputs=None,
            compression_algorithm=FLAGS.grpc_compression_algorithm),
        triton_client.infer(
            model_name=model_name,
            inputs=inputs,
            outputs=None,
            compression_algorithm=FLAGS.grpc_compression_algorithm))

    get_output(input0_data, input1_data, result_1)
    get_output(input0_data, input1_data, result_2)

    print('PASS: grpc aio infer')


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('-v',
                        '--verbose',
                        action="store_true",
                        required=False,
                        default=False,
                        help='Enable verbose output')
    parser.add_argument('-u',
                        '--url',
                        type=str,
                        required=False,
                        default='localhost:8001',
                        help='Inference server URL. Default is localhost:8001.')
    parser.add_argument('-s',
                        '--ssl',
                        action="store_true",
                        required=False,
                        default=False,
                        help='Enable SSL encrypted channel to the server')
    parser.add_argument('-t',
                        '--client-timeout',
                        type=float,
                        required=False,
                        default=None,
                        help='Client timeout in seconds. Default is None.')
    parser.add_argument(
        '-r',
        '--root-certificates',
        type=str,
        required=False,
        default=None,
        help='File holding PEM-encoded root certificates. Default is None.')
    parser.add_argument(
        '-p',
        '--private-key',
        type=str,
        required=False,
        default=None,
        help='File holding PEM-encoded private key. Default is None.')
    parser.add_argument(
        '-x',
        '--certificate-chain',
        type=str,
        required=False,
        default=None,
        help='File holding PEM-encoded certicate chain. Default is None.')
    parser.add_argument(
        '-C',
        '--grpc-compression-algorithm',
        type=str,
        required=False,
        default=None,
        help=
        'The compression algorithm to be used when sending request to server. Default is None.'
    )
    FLAGS = parser.parse_args()
    asyncio.run(main(FLAGS))