Image Classification Async Python Sample

This sample demonstrates how to do inference of image classification models using Asynchronous Inference Request API.

Models with only 1 input and output are supported.



Validated Models


Model Format

OpenVINO™ toolkit Intermediate Representation (.xml + .bin), ONNX (.onnx)

Supported devices


Other language realization


The following Python API is used in the application:




Asynchronous Infer

openvino.runtime.AsyncInferQueue , openvino.runtime.AsyncInferQueue.set_callback , openvino.runtime.AsyncInferQueue.start_async , openvino.runtime.AsyncInferQueue.wait_all , openvino.runtime.InferRequest.results

Do asynchronous inference

Basic OpenVINO™ Runtime API is covered by Hello Classification Python Sample.

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# Copyright (C) 2018-2023 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

import argparse
import logging as log
import sys

import cv2
import numpy as np
import openvino as ov

def parse_args() -> argparse.Namespace:
    """Parse and return command line arguments."""
    parser = argparse.ArgumentParser(add_help=False)
    args = parser.add_argument_group('Options')
    # fmt: off
    args.add_argument('-h', '--help', action='help',
                      help='Show this help message and exit.')
    args.add_argument('-m', '--model', type=str, required=True,
                      help='Required. Path to an .xml or .onnx file with a trained model.')
    args.add_argument('-i', '--input', type=str, required=True, nargs='+',
                      help='Required. Path to an image file(s).')
    args.add_argument('-d', '--device', type=str, default='CPU',
                      help='Optional. Specify the target device to infer on; CPU, GPU, GNA or HETERO: '
                      'is acceptable. The sample will look for a suitable plugin for device specified. '
                      'Default value is CPU.')
    # fmt: on
    return parser.parse_args()

def completion_callback(infer_request: ov.InferRequest, image_path: str) -> None:
    predictions = next(iter(infer_request.results.values()))

    # Change a shape of a numpy.ndarray with results to get another one with one dimension
    probs = predictions.reshape(-1)

    # Get an array of 10 class IDs in descending order of probability
    top_10 = np.argsort(probs)[-10:][::-1]

    header = 'class_id probability''Image path: {image_path}')'Top 10 results: ')'-' * len(header))

    for class_id in top_10:
        probability_indent = ' ' * (len('class_id') - len(str(class_id)) + 1)'{class_id}{probability_indent}{probs[class_id]:.7f}')'')

def main() -> int:
    log.basicConfig(format='[ %(levelname)s ] %(message)s', level=log.INFO, stream=sys.stdout)
    args = parse_args()

# --------------------------- Step 1. Initialize OpenVINO Runtime Core ------------------------------------------------'Creating OpenVINO Runtime Core')
    core = ov.Core()

# --------------------------- Step 2. Read a model --------------------------------------------------------------------'Reading the model: {args.model}')
    # (.xml and .bin files) or (.onnx file)
    model = core.read_model(args.model)

    if len(model.inputs) != 1:
        log.error('Sample supports only single input topologies')
        return -1

    if len(model.outputs) != 1:
        log.error('Sample supports only single output topologies')
        return -1

# --------------------------- Step 3. Set up input --------------------------------------------------------------------
    # Read input images
    images = [cv2.imread(image_path) for image_path in args.input]

    # Resize images to model input dims
    _, _, h, w = model.input().shape
    resized_images = [cv2.resize(image, (w, h)) for image in images]

    # Add N dimension
    input_tensors = [np.expand_dims(image, 0) for image in resized_images]

# --------------------------- Step 4. Apply preprocessing -------------------------------------------------------------
    ppp = ov.preprocess.PrePostProcessor(model)

    # 1) Set input tensor information:
    # - input() provides information about a single model input
    # - precision of tensor is supposed to be 'u8'
    # - layout of data is 'NHWC'
    ppp.input().tensor() \
        .set_element_type(ov.Type.u8) \
        .set_layout(ov.Layout('NHWC'))  # noqa: N400

    # 2) Here we suppose model has 'NCHW' layout for input

    # 3) Set output tensor information:
    # - precision of tensor is supposed to be 'f32'

    # 4) Apply preprocessing modifing the original 'model'
    model =

# --------------------------- Step 5. Loading model to the device -----------------------------------------------------'Loading the model to the plugin')
    compiled_model = core.compile_model(model, args.device)

# --------------------------- Step 6. Create infer request queue ------------------------------------------------------'Starting inference in asynchronous mode')
    # create async queue with optimal number of infer requests
    infer_queue = ov.AsyncInferQueue(compiled_model)

# --------------------------- Step 7. Do inference --------------------------------------------------------------------
    for i, input_tensor in enumerate(input_tensors):
        infer_queue.start_async({0: input_tensor}, args.input[i])

# ----------------------------------------------------------------------------------------------------------------------'This sample is an API example, for any performance measurements please use the dedicated benchmark_app tool\n')
    return 0

if __name__ == '__main__':

How It Works

At startup, the sample application reads command-line parameters, prepares input data, loads a specified model and image(s) to the OpenVINO™ Runtime plugin, performs synchronous inference, and processes output data, logging each step in a standard output stream.

You can see the explicit description of each sample step at Integration Steps section of “Integrate OpenVINO™ Runtime with Your Application” guide.


Run the application with the -h option to see the usage message:

python -h

Usage message:

usage: [-h] -m MODEL -i INPUT [INPUT ...]
                                      [-d DEVICE]

  -h, --help            Show this help message and exit.
  -m MODEL, --model MODEL
                        Required. Path to an .xml or .onnx file with a trained
  -i INPUT [INPUT ...], --input INPUT [INPUT ...]
                        Required. Path to an image file(s).
  -d DEVICE, --device DEVICE
                        Optional. Specify the target device to infer on; CPU,
                        GPU or HETERO: is acceptable. The sample
                        will look for a suitable plugin for device specified.
                        Default value is CPU.

To run the sample, you need specify a model and image:

  • You can use public or Intel’s pre-trained models from the Open Model Zoo. The models can be downloaded using the Model Downloader.

  • You can use images from the media files collection available here .


  • By default, OpenVINO™ Toolkit Samples and demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the sample or demo application or reconvert your model using model conversion API with reverse_input_channels argument specified. For more information about the argument, refer to When to Reverse Input Channels section of Embedding Preprocessing Computation.

  • Before running the sample with a trained model, make sure the model is converted to the intermediate representation (IR) format (*.xml + *.bin) using model conversion API.

  • The sample accepts models in ONNX format (.onnx) that do not require preprocessing.

  • Stating flags that take only single option like -m multiple times, for example python -m model.xml -m model2.xml, results in only the last value being used.

  • The sample supports NCHW model layout only.


  1. Install the openvino-dev Python package to use Open Model Zoo Tools:

    python -m pip install openvino-dev[caffe]
  2. Download a pre-trained model:

    omz_downloader --name alexnet
  3. If a model is not in the IR or ONNX format, it must be converted. You can do this using the model converter:

    omz_converter --name alexnet
  4. Perform inference of banana.jpg and car.bmp using the alexnet model on a GPU, for example:

    python -m alexnet.xml -i banana.jpg car.bmp -d GPU

Sample Output

The sample application logs each step in a standard output stream and outputs top-10 inference results.

[ INFO ] Creating OpenVINO Runtime Core
[ INFO ] Reading the model: C:/test_data/models/alexnet.xml
[ INFO ] Loading the model to the plugin
[ INFO ] Starting inference in asynchronous mode
[ INFO ] Image path: /test_data/images/banana.jpg
[ INFO ] Top 10 results:
[ INFO ] class_id probability
[ INFO ] --------------------
[ INFO ] 954      0.9707602
[ INFO ] 666      0.0216788
[ INFO ] 659      0.0032558
[ INFO ] 435      0.0008082
[ INFO ] 809      0.0004359
[ INFO ] 502      0.0003860
[ INFO ] 618      0.0002867
[ INFO ] 910      0.0002866
[ INFO ] 951      0.0002410
[ INFO ] 961      0.0002193
[ INFO ]
[ INFO ] Image path: /test_data/images/car.bmp
[ INFO ] Top 10 results:
[ INFO ] class_id probability
[ INFO ] --------------------
[ INFO ] 656      0.5120340
[ INFO ] 874      0.1142275
[ INFO ] 654      0.0697167
[ INFO ] 436      0.0615163
[ INFO ] 581      0.0552262
[ INFO ] 705      0.0304179
[ INFO ] 675      0.0151660
[ INFO ] 734      0.0151582
[ INFO ] 627      0.0148493
[ INFO ] 757      0.0120964
[ INFO ]
[ INFO ] This sample is an API example, for any performance measurements please use the dedicated benchmark_app tool