Metadata-Version: 2.1
Name: dx-com
Version: 2.3.0
Summary: DXCOM Package
Author-email: Jangmin Son <jangmin@deepx.co.kr>
License: Copyright (C) 2018- DEEPX Ltd.
        All rights reserved.
        
        This software is the property of DEEPX and is provided exclusively to customers 
        who are supplied with DEEPX NPU (Neural Processing Unit). Unauthorized sharing 
        or usage is strictly prohibited by law. The license for this software is
        allocated to specific users or organizations associated with DEEPX, and any use
        by individuals or entities outside of this scope is illegal.
        
        Unauthorized use or sharing of the software will be considered as an
        infringement of DEEPX's intellectual property rights, which may result in legal
        action, claims for damages, and criminal penalties.
        
        If you intend to use the software, you must first contact DEEPX or the
        contracted user or organization authorized to obtain the license formally.
        
        This warning is provided to emphasize the strict policy regarding software 
        licenses and unauthorized sharing. The SDK may contain open-source components,
        each of which is subject to its respective software license. It is the
        responsibility of users to adhere to the terms of these licenses. 
        
        By reading this warning, you acknowledge the need to comply with the software's 
        license and usage terms. Failure to comply may result in legal liabilities.
        
Project-URL: Homepage, https://gh.deepx.ai/deepx/dx_com.git
Project-URL: Bug Tracker, https://gh.deepx.ai/deepx/dx_com/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: Other/Proprietary License
Classifier: Operating System :: OS Independent
Requires-Python: <3.13,>=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: mypy
Requires-Dist: pybind11~=2.13.1
Requires-Dist: numpy>=1.24.4
Requires-Dist: onnx>=1.16.1
Requires-Dist: onnxruntime>=1.18.0
Requires-Dist: opencv-python>=4.10.0.84
Requires-Dist: protobuf>=5.26.0
Requires-Dist: Pillow>=10.4.0
Requires-Dist: tqdm
Requires-Dist: scipy>=1.10.1
Requires-Dist: torch>=2.3.0
Requires-Dist: pycryptodome~=3.20.0
Requires-Dist: ordered-set~=4.1.0
Requires-Dist: sortedcontainers~=2.4.0
Requires-Dist: cloudpickle~=3.1.1
Requires-Dist: Rtree~=1.3.0
Requires-Dist: jinja2>=3.1.0
Requires-Dist: setuptools>=70.1
Requires-Dist: typing-extensions<4.14; python_version < "3.9"
Provides-Extra: test
Requires-Dist: pytest>=7.0.0; extra == "test"
Requires-Dist: pytest-mock>=3.10.0; extra == "test"
Requires-Dist: pytest-datadir>=1.5.0; extra == "test"
Requires-Dist: onnxscript; extra == "test"

# DXCOM

DXCOM is a compiler SDK by [DEEPX](https://www.deepx.ai) that compiles ONNX models into optimized `.dxnn` binaries for DEEPX NPU (Neural Processing Unit).

It performs hardware-aware quantization, graph optimization, and code generation — all in a single pipeline. The compiled `.dxnn` file can be deployed and executed on DEEPX NPU via [DX-RT](https://github.com/DEEPX-AI/dx_rt) (DEEPX Runtime).

## Installation

```bash
pip install dx-com
```

> **Requirements:** Python 3.8 – 3.14, Linux (x86_64)

## Quick Start

### CLI

```bash
dxcom -m model.onnx -c config.json -o output/
```

| Argument | Description |
|----------|-------------|
| `-m` | Path to the ONNX model file |
| `-c` | Path to the JSON configuration file |
| `-o` | Output directory for compiled artifacts |
| `--opt_level` | Optimization level: `0` (fast) or `1` (higher accuracy, default) |
| `--gen_log` | Generate a compilation log |
| `-v` | Show version |

### Python API

```python
import dx_com

dx_com.compile(
    model="model.onnx",
    config="config.json",
    output_dir="output/",
    opt_level=1,
)
```

#### Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| `model` | `str` | Path to the ONNX model file |
| `config` | `str` | Path to the JSON configuration file |
| `output_dir` | `str` | Output directory for compiled artifacts |
| `opt_level` | `int` | Optimization level: `0` (fast) or `1` (higher accuracy). Default: `1` |
| `calibration_method` | `str` | Calibration method. Options: `minmax`, `percentile`, `mse`, `entropy` |
| `aggressive_partitioning` | `bool` | Enable aggressive CPU/NPU partitioning. Default: `False` |

## Documentation

For detailed technical documentation and user manual, visit [DEEPX Developer Portal](https://developer.deepx.ai/).

## License

This software is the proprietary property of DEEPX Ltd. and is provided exclusively to authorized customers with DEEPX NPU hardware. See [LICENSE](https://github.com/DEEPX-AI/dx-compiler/blob/main/LICENSE) for details.
