triton_client.py

#
# SPDX-FileCopyrightText: Copyright (c) 1993-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#

import numpy as np
from torchvision import transforms
from PIL import Image
import tritonclient.http as httpclient
from tritonclient.utils import triton_to_np_dtype

def rn50_preprocess(img_path="img1.jpg"):
    img = Image.open(img_path)
    preprocess = transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
    ])
    return preprocess(img).numpy()

transformed_img = rn50_preprocess()

# Setup a connection with the Triton Inference Server.
triton_client = httpclient.InferenceServerClient(url="localhost:8000")

# Specify the names of the input and output layer(s) of our model.
test_input = httpclient.InferInput("input", transformed_img.shape, datatype="FP32")
test_input.set_data_from_numpy(transformed_img, binary_data=True)

test_output = httpclient.InferRequestedOutput("output", binary_data=True, class_count=1000)

# Querying the server
results = triton_client.infer(model_name="resnet50", inputs=[test_input], outputs=[test_output])
test_output_fin = results.as_numpy('output')

print(test_output_fin[:5])