Hello NV12 Input Classification C Sample¶
This sample demonstrates how to execute an inference of image classification networks such as AlexNet with images in NV12
color format using Synchronous Inference Request API.
Hello NV12 Input Classification C Sample demonstrates how to use the NV12
automatic input pre-processing API of the Inference Engine in your applications:
Feature |
API |
Description |
---|---|---|
Blob Operations |
Create a |
|
Input in |
Change the color format of the input data |
Basic Inference Engine API is described in Hello Classification C sample.
Options |
Values |
---|---|
Validated Models |
|
Model Format |
OpenVINO Intermediate Representation (*.xml + *.bin), ONNX (*.onnx) |
Validated images |
An uncompressed image in the |
Supported devices |
|
Other language realization |
How It Works¶
Upon the start-up, the sample application reads command-line parameters, loads specified network and an image in the NV12
color format to the Inference Engine plugin. Then, the sample creates a synchronous inference request object. When inference is done, the application outputs data to the standard output stream.
For more information, refer to the explicit description of Integration Steps in the Integrate OpenVINO Runtime with Your Application guide.
Building¶
To build the sample, use the instructions available in the Build the Sample Applications section in OpenVINO Toolkit Samples.
Running¶
To run the sample, you need to specify a model and an image:
You may use public or Intel’s pre-trained models from the Open Model Zoo. The models can be downloaded by using the Model Downloader.
You may use images from the media files collection, available online in the test data storage.
The sample accepts an uncompressed image in the NV12
color format. To run the sample, you need to convert your BGR
/ RGB
image to NV12
. To do this, use one of the widely available tools such as FFmpeg or GStreamer. The following command shows how to convert an ordinary image into an uncompressed NV12
image, using FFmpeg:
ffmpeg -i cat.jpg -pix_fmt nv12 cat.yuv
NOTES :
Since the sample reads raw image files, a correct image size along with the image path should be provided. The sample expects the logical size of the image, not the buffer size. For example, for 640x480
BGR
/RGB
image, the correspondingNV12
logical image size is also 640x480, whereas the buffer size is 640x720.By default, this sample expects that network input has
BGR
order of channels. If you trained your model to work with theRGB
order, you need to reconvert your model, using Model Optimizer with--reverse_input_channels
argument specified. For more information about the argument, refer to the When to Reverse Input Channels section of Embedding Preprocessing Computation.Before running the sample with a trained model, make sure that the model is converted to the OpenVINO Intermediate Representation (OpenVINO IR) format (*.xml + *.bin) by using Model Optimizer.
The sample accepts models in the ONNX format (.onnx) that do not require preprocessing.
Example¶
Download a pre-trained model, using Model Downloader :
python <path_to_omz_tools>/downloader.py --name alexnet
If a model is not in the OpenVINO IR or ONNX format. You can do this using the model converter script:
python <path_to_omz_tools>/converter.py --name alexnet
Perform inference of the
NV12
image, using thealexnet
model on aCPU
, for example:<path_to_sample>/hello_nv12_input_classification_c <path_to_model>/alexnet.xml <path_to_image>/cat.yuv 300x300 CPU
Sample Output¶
The application outputs top-10 inference results.
Top 10 results:
Image ./cat.yuv
classid probability
------- -----------
435 0.091733
876 0.081725
999 0.069305
587 0.043726
666 0.038957
419 0.032892
285 0.030309
700 0.029941
696 0.021628
855 0.020339
This sample is an API example. Use the dedicated `benchmark_app` tool for any performance measurements.