Edit this page

Hello Classification C Sample

This sample demonstrates how to execute inference of image classification networks like AlexNet and GoogLeNet using Synchronous Inference Request API and the input auto-resize feature. Source code for this example is also available on GitHub.

Hello Classification C sample application demonstrates how to use the following Inference Engine C API in applications:

Feature

API

Description

Basic Infer Flow

ie_core_create , ie_core_read_network , ie_core_load_network , ie_exec_network_create_infer_request , ie_infer_request_set_blob , ie_infer_request_get_blob

Common API to do inference: configure input and output blobs, loading model, create infer request

Synchronous Infer

ie_infer_request_infer

Do synchronous inference

Network Operations

ie_network_get_input_name , ie_network_get_inputs_number , ie_network_get_outputs_number , ie_network_set_input_precision , ie_network_get_output_name , ie_network_get_output_precision

Managing of network

Blob Operations

ie_blob_make_memory_from_preallocated , ie_blob_get_dims , ie_blob_get_cbuffer

Work with memory container for storing inputs, outputs of the network, weights and biases of the layers

Input auto-resize

ie_network_set_input_resize_algorithm , ie_network_set_input_layout

Set image of the original size as input for a network with other input size. Resize and layout conversions will be performed automatically by the corresponding plugin just before inference

Options

Values

Validated Models

alexnet , googlenet-v1

Model Format

Inference Engine Intermediate Representation (*.xml + *.bin), ONNX (*.onnx)

Validated images

The sample uses OpenCV* to read input image (*.bmp, *.png)

Supported devices

All

Other language realization

C++ , Python

How It Works

Upon the start-up, the sample application reads command line parameters, loads specified network and an image to the Inference Engine plugin. Then, the sample creates an synchronous inference request object. When inference is done, the application outputs data to the 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.

Building

To build the sample, please use instructions available at Build the Sample Applications section in Inference Engine Samples guide.

Running

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

NOTES :

  • 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 the Model Optimizer tool 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 Inference Engine format (*.xml + *.bin) using the Model Optimizer tool.

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

Example

  1. Download a pre-trained model using Model Downloader :

    python <path_to_omz_tools>/downloader.py --name alexnet

  2. If a model is not in the Inference Engine IR or ONNX format, it must be converted. You can do this using the model converter script:

python <path_to_omz_tools>/converter.py --name alexnet

  1. Perform inference of car.bmp using alexnet model on a GPU, for example:

<path_to_sample>/hello_classification_c <path_to_model>/alexnet.xml <path_to_image>/car.bmp GPU

Sample Output

The application outputs top-10 inference results.

Top 10 results:

Image /opt/intel/openvino/samples/scripts/car.png

classid probability
------- -----------
656       0.666479
654       0.112940
581       0.068487
874       0.033385
436       0.026132
817       0.016731
675       0.010980
511       0.010592
569       0.008178
717       0.006336

This sample is an API example, for any performance measurements please use the dedicated benchmark_app tool
Prev Next