### Build ONNX Optimizer from Source

Source: https://github.com/onnx/optimizer/blob/main/README.md

Clone the repository, navigate to the directory, and install the package in editable mode. Ensure protobuf is installed beforehand.

```bash
git clone --recursive https://github.com/onnx/optimizer onnxoptimizer
cd onnxoptimizer
pip3 install -e .
```

--------------------------------

### Install ONNX Optimizer from PyPI

Source: https://github.com/onnx/optimizer/blob/main/README.md

Install the onnxoptimizer package using pip. Upgrade pip if you encounter issues.

```bash
pip3 install onnxoptimizer
```

```bash
pip3 install -U pip
```

--------------------------------

### ONNX Optimizer Command-Line Help

Source: https://github.com/onnx/optimizer/blob/main/README.md

Display help information for the onnxoptimizer command-line API, showing available arguments and their descriptions.

```bash
# python3 -m onnxoptimizer -h                                 
usage: python -m onnxoptimizer input_model.onnx output_model.onnx 

onnxoptimizer command-line api

optional arguments:
  -h, --help            show this help message and exit
  --print_all_passes    print all available passes
  --print_fuse_elimination_passes
                        print all fuse and elimination passes
  -p [PASSES ...], --passes [PASSES ...]
                        list of optimization passes name, if no set, fuse_and_elimination_passes will be used
  --fixed_point         fixed point
```

--------------------------------

### Run ONNX Optimizer from Command Line

Source: https://github.com/onnx/optimizer/blob/main/README.md

Optimize an ONNX model using the command-line interface. Specify input and output model paths.

```bash
python -m onnxoptimizer input_model.onnx output_model.onnx
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.