# End-to-end examples

Install the following additional packages in the container for running end-to-end
examples:

apt-get update
    apt-get install -y python-yaml libpng-dev
    
    pip3 install --upgrade pip
    pip3 install opencv-python-headless pyyaml scipy
    Copy to clipboard

End to end examples (cpp and python) for ResNet50 are available at -
`/opt/qti-aic/integrations/qaic_onnxrt/tests/`.

## Running the ResNet C++ sample

Compile the Sample Resnet C++ test using build\_tests.sh script. By
default, test is built using libs from onnxruntime\_qaic release build.
To enable debugging, re-build onnxruntime\_qaic project in Debug
configuration and run ./build\_test.sh with debug flag.

build_tests.sh [--release|--debug]
    Copy to clipboard

Run the executable. The commands below set the environment and run the
ResNet-50 model with the provided image on QAic or CPU backend. The
program outputs the most probable prediction class index for each
iteration.

cd build/release
    ./qaic-onnxrt-resnet50-test -i <path/to/input/png/image>
                                -m  ../../resnet50/resnet50.yaml
    Copy to clipboard

Test options

| Option | Description |
| --- | --- |
| `-m, --model-config` | [Required] Path to the model-setting yaml file |
| `-i, --input-path` | [Required] Path to the input PNG image file |
| `-b, --backend` | [Optional] Default=’qaic’, Specify qaic/cpu as backend |
| `-d, --device-id` | [Optional] Default=0 Specify qaic device ID |
| `-n, --num-iter` | [Optional] |

## Running the ResNet Python sample

Run test_resnet.py at /opt/qti-aic/integrations/qaic_onnxrt/tests/resnet50
    python test_resnet.py --model_config ./resnet50/resnet50.yaml
                          --input_file </path/to/png/image>
    Copy to clipboard

Test options

| Option | Description |
| --- | --- |
| `--model_config` | [Required] Path to the model-setting yaml file |
| `--input_file` | [Required] Path to the input PNG image file |
| `--backend` | [Optional] Default=’qaic’, Specify qaic/cpu as backend |
| `--device_id` | [Optional] Default=0 Specify qaic device ID |
| `--num_iter` | [Optional] |

## Running models with generic QAic EP test

`test_qaic_ep.py` is a generic test runner for compilation, execution
on AIC100.

Run `test_qaic_ep.py` at
`/opt/qti-aic/integrations/qaic_onnxrt/tests/` -

python test_qaic_ep.py --model_config ./resnet50/resnet50.yaml
                               --input_file_list </path/to/input/list>
    Copy to clipboard

Test options

| Option | Description |
| --- | --- |
| `--model_config` | [Required] Path to the model-setting yaml file |
| `--input_file_list` | [Required] Path of the file (.txt) containing list of batched inputs in .raw format |
| `--backend` | [Optional] Default=’qaic’, Specify qaic/cpu as backend |
| `--device_id` | [Optional] Default=0 Specify qaic device ID |
| `--num_iter` | [Optional] |
| `--max_threads` | [Optional] Default=1000 Maximum no. of threads to run inferences |
| `--log_level` | [Optional] |

## Execution through ONNX Runtime test framework

- QAic EP is enabled for execution with onnx\_test\_runner,
onnxruntime\_perf\_test.
- For model directory requirements and comprehensive list of options
supported, see [onnxruntime perf test
documentation](https://github.com/microsoft/onnxruntime/blob/v1.13.1/onnxruntime/test/perftest/README.md).
- [onnx_test_runner
documentation](https://github.com/microsoft/onnxruntime/blob/v1.13.1/onnxruntime/test/onnx/README.txt).
- Sample testdata can be downloaded
[here](https://github.com/onnx/models/raw/refs/heads/main/validated/vision/classification/resnet/model/resnet50-v1-7.tar.gz).

cd /opt/qti-aic/integrations/qaic_onnxrt/onnxruntime_qaic/build/Release
    
    ./onnxruntime_perf_test -e qaic -i 'config|/path/to/resnet50.yaml aic_device_id|0' -m times -r 1000 /path/to/model.onnx
    Copy to clipboard

./onnx_test_runner -e qaic /path/to/model/dir
    Copy to clipboard

Last Published: Aug 25, 2026

[Previous Topic
C++ Sample](https://docs.qualcomm.com/bundle/publicresource/80-99100-3/topics/qaic-onnxrt-cpp-sample.md)