# ResNet optimization with PTQ on CPU
This is a sample use case of olive to optimize a ResNet model using onnx conversion and onnx dynamic/static quantization tuner.

## Prerequisites
Please go to example repository [Quickstart ResNet Example](https://github.com/microsoft/Olive/tree/main/examples/resnet_ptq_cpu)
### Prepare data and model
To Prepare the model and necessary data:
```
python prepare_model_data.py --num_epochs 5
```

### Pip requirements
Install the necessary python packages:
```
python -m pip install -r requirements.txt
```

## Run sample using config
```
python -m olive.workflows.run --config resnet_{dynamic,static}_config.json
```
or run simply with python code:
```python
from olive.workflows import run as olive_run
olive_run("resnet_dynamic_config.json")
olive_run("resnet_static_config.json")
```