Metadata-Version: 2.1
Name: netspresso
Version: 1.8.0
Summary: PyNetsPresso
Home-page: https://github.com/Nota-NetsPresso/PyNetsPresso
Author: NetsPresso
Author-email: netspresso@nota.ai
License: UNKNOWN
Description: <div align=right>
          <a href="https://hits.seeyoufarm.com"><img src="https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fgithub.com%2FNota-NetsPresso%2Fnetspresso-python&count_bg=%2323E7E7E7&title_bg=%23555555&icon=&icon_color=%23E7E7E7&title=hits&edge_flat=false"/></a>
        </div>
        
        <div align="center">
            <a href="https://netspresso.ai/?utm_source=git&utm_medium=banner_py&utm_campaign=np_renew" target="_blank"><img src="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/banner/NetsPresso2.0_banner.png"/>
        </div>
        </br>
        
        <div align="center">
          ☀️ NetsPresso Model Zoo ☀️ <br>
              <a href="https://github.com/Nota-NetsPresso/ModelZoo-YOLOFastest-for-ARM-U55-M85"> YOLO Fastest </a>
            | <a href="https://github.com/Nota-NetsPresso/yolox_nota"> YOLOX </a>
            | <a href="https://github.com/Nota-NetsPresso/ultralytics_nota"> YOLOv8 </a> 
            | <a href="https://github.com/Nota-NetsPresso/ModelZoo-YOLOv7"> YOLOv7 </a> 
            | <a href="https://github.com/Nota-NetsPresso/yolov5_nota"> YOLOv5 </a> 
            | <a href="https://github.com/Nota-NetsPresso/PIDNet_nota"> PIDNet </a>     
            | <a href="https://github.com/Nota-NetsPresso/pytorch-cifar-models_nota"> PyTorch-CIFAR-Models</a>
        </div>
        </br>
        
        <div align="center">
          🌟 STMicro x NetsPresso 🌟 <br>
              <a href="https://github.com/STMicroelectronics/stm32ai-modelzoo"> STM32 model zoo</a>
        </div>
        </br>
        
        <div align="center">
            <p align="center">
                <a href="https://www.python.org/downloads/" target="_blank"><img src="https://img.shields.io/badge/python-3.8%20%7C%203.9%20%7C%203.10-blue?style=flat&logo=python&logoColor=blue" />
                <a href="https://pytorch.org/" target="_blank"><img src="https://img.shields.io/badge/PyTorch-1.11.x ~ 1.13.x.-EE4C2C?style=flat&logo=pytorch&logoColor=#EE4C2C"/></a>
                <a href="https://www.tensorflow.org/install/pip" target="_blank"><img src="https://img.shields.io/badge/TensorFlow-2.3.x ~ 2.8.x.-FF6F00?style=flat&logo=tensorflow&logoColor=#FF6F00&link=https://www.tensorflow.org/install/pip"/></a>
                <br>
                <a href="https://netspresso.ai/?utm_source=git&utm_medium=badge&utm_campaign=np_renew"><img src="https://img.shields.io/badge/NetsPresso-Open in Website-1BD2EB?style=flat&link=https://netspresso.ai/"/></a>
                <a href="https://colab.research.google.com/drive/15HBp88qfUDQl5PaEcZ5J-dnLo-1kvw-a" target="_blank"><img src="https://img.shields.io/badge/Best Practice-Open in Colab-F9AB00?style=flat&logo=googlecolab&logoColor=#F9AB00"/></a>
            </p>
        </div>
        </br>
        
        Use **NetsPresso** for a seamless model optimization process. 
        NetsPresso resolves AI-related constraints in business use cases and enables cost-efficiency and enhanced performance by removing the requirement for high-spec servers and network connectivity and preventing high latency and personal data breaches.
        
        Easily compress various models with our resources. Please browse the [Docs] for details, and join our [Discussion Forum] for providing feedback or sharing your use cases.
        
        To get started with NetsPresso, you'll need to sign up [here](https://netspresso.ai/?utm_source=git&utm_medium=text_signup&utm_campaign=np_renew).
        
        We offer a comprehensive guide to walk you through the process of optimizing an AI model using NetsPresso. A full tutorial can be found [Google Colab](https://colab.research.google.com/drive/15HBp88qfUDQl5PaEcZ5J-dnLo-1kvw-a).
        </br>
        </br>
        
        <div align="center">
          <a href="https://github.com/Nota-NetsPresso" style="text-decoration:none;">
            <picture>
              <source media="(prefers-color-scheme: dark)" srcset="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/github_white.png">
              <source media="(prefers-color-scheme: light)" srcset="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/github.png">
              <img alt="github" src="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/github.png" width="3%">
            </picture>
          </a>
          <img src="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/logo-transparent.png" width="3%" alt="" />
          <a href="https://www.facebook.com/NotaAI" style="text-decoration:none;">
            <picture>
              <source media="(prefers-color-scheme: dark)" srcset="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/facebook_white.png">
              <source media="(prefers-color-scheme: light)" srcset="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/facebook.png">
              <img alt="facebook" src="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/facebook.png" width="3%">
            </picture>
          </a>
          <img src="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/logo-transparent.png" width="3%" alt="" />
          <a href="https://twitter.com/nota_ai" style="text-decoration:none;">
            <picture>
              <source media="(prefers-color-scheme: dark)" srcset="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/twitter_white.png">
              <source media="(prefers-color-scheme: light)" srcset="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/twitter.png">
              <img alt="twitter" src="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/twitter.png" width="3%">
            </picture>
          </a>
          <img src="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/logo-transparent.png" width="3%" alt="" />
          <a href="https://www.youtube.com/channel/UCeewYFAqb2EqwEXZCfH9DVQ" style="text-decoration:none;">
            <picture>
              <source media="(prefers-color-scheme: dark)" srcset="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/youtube_white.png">
              <source media="(prefers-color-scheme: light)" srcset="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/youtube.png">
              <img alt="youtube" src="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/youtube.png" width="3%">
            </picture>
          </a>
          <img src="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/logo-transparent.png" width="3%" alt="" />
          <a href="https://www.linkedin.com/company/nota-incorporated" style="text-decoration:none;">
            <picture>
              <source media="(prefers-color-scheme: dark)" srcset="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/linkedin_white.png">
              <source media="(prefers-color-scheme: light)" srcset="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/linkedin.png">
              <img alt="youtube" src="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/common/linkedin.png" width="3%">
            </picture>
          </a>
        </div>
        </br>
        </br>
        
        <div align="center">
            <img width="100%" src="https://netspresso-docs-imgs.s3.ap-northeast-2.amazonaws.com/imgs/banner/github_pipeline_temp.png">
        </div>
        </br>
        
        <div width="9%" align="center">
          <table width="90%" align="center">
              <tr>
                  <th>Step</th>
                  <th>Type</th>
                  <th>Description</th>
              </tr>
              <tr>
                  <td width="30%" align="center" rowspan="2">Train</td>
                  <td width="30%" align="center">np.trainer</td>
                  <td width="40%" align="center" rowspan="2">Build and train a model.</td>
              </tr>
              <tr>
                  <td width="30%" align="center">
                    <details>
                      <summary>Model Zoo</summary>
                      <details>
                          <summary>Image Classification</summary>
                          <a href="https://github.com/Nota-NetsPresso/pytorch-cifar-models_nota">PyTorch-CIFAR-Models</a>
                      </details>
                      <details>
                          <summary>Object Detection</summary>
                          <a href="https://github.com/Nota-NetsPresso/ModelZoo-YOLOFastest-for-ARM-U55-M85">YOLO Fastest</a><br>
                          <a href="https://github.com/Nota-NetsPresso/yolox_nota">YOLOX</a><br>
                          <a href="https://github.com/Nota-NetsPresso/yolov5_nota">YOLOv5</a><br>
                          <a href="https://github.com/Nota-NetsPresso/ModelZoo-YOLOv7">YOLOv7</a>
                      </details>
                      <details>
                          <summary>Semantic Segmentation</summary>
                          <a href="https://github.com/Nota-NetsPresso/PIDNet_nota">PIDNet</a>
                      </details>
                      <details>
                          <summary>Pose Estimation</summary>
                          <a href="https://github.com/Nota-NetsPresso/ultralytics_nota">YOLOv8</a>
                      </details>
                    </details>
                  </td>
              </tr>
              <tr>
                  <td width="30%" align="center">Compress</td>
                  <td width="30%" align="center">np.compressor</td>
                  <td width="40%" align="center">Compress and optimize the user’s model.</td>
              </tr>
              <tr>
                  <td width="30%" align="center">Convert</td>
                  <td width="30%" align="center">np.converter</td>
                  <td width="40%" align="center">Convert and quantize the user’s model to run efficiently on device.</td>
              </tr>
              <tr>
                  <td width="30%" align="center">Benchmark</td>
                  <td width="30%" align="center">np.benchmarker</td>
                  <td width="40%" align="center">Benchmark the user's model to measure model inference speed on diverse device.</td>
              </tr>
          </table>
        </div>
        
        ## Installation
        
        ### Prerequisites
        
        - Python `3.8` | `3.9` | `3.10`
        - PyTorch `1.13.0` (recommended) (compatible with: `1.11.x` - `1.13.x`)
        - TensorFlow `2.8.0` (recommended) (compatible with: `2.3.x` - `2.8.x`)
        
        ### Install with PyPI (stable)
        
        ```bash
        pip install netspresso
        ```
        
        To use **editable mode** or **docker**, see [INSTALLATION.md](INSTALLATION.md).
        
        ## Getting started
        
        ### Login
        
        Log-in to your netspresso account. Please sign-up [here](https://netspresso.ai/?utm_source=git&utm_medium=text_signup2&utm_campaign=np_renew) if you need one.
        
        ```python
        from netspresso import NetsPresso
        
        netspresso = NetsPresso(email="YOUR_EMAIL", password="YOUR_PASSWORD")
        ```
        
        ### Trainer
        
        #### Train
        
        To start training a model, first select a task. 
        
        Then configure the dataset, model, augmentation, and hyperparameters. 
        
        Once setup is finished, enter the GPU number and project name for training.
        
        ```python
        from netspresso.enums import Task
        from netspresso.trainer.optimizers import AdamW
        from netspresso.trainer.schedulers import CosineAnnealingWarmRestartsWithCustomWarmUp
        from netspresso.trainer.augmentations import Resize
        
        
        # 1. Declare trainer
        trainer = netspresso.trainer(task=Task.OBJECT_DETECTION)  # IMAGE_CLASSIFICATION, OBJECT_DETECTION, SEMANTIC_SEGMENTATION
        
        # 2. Set config for training
        # 2-1. Data
        trainer.set_dataset_config(
            name="traffic_sign_config_example",
            root_path="/root/traffic-sign",
            train_image="images/train",
            train_label="labels/train",
            valid_image="images/valid",
            valid_label="labels/valid",
            id_mapping=["prohibitory", "danger", "mandatory", "other"],
        )
        
        # 2-2. Model
        print(trainer.available_models)  # ['EfficientFormer', 'YOLOX-S', 'ResNet', 'MobileNetV3', 'MixNetL', 'MixNetM', 'MixNetS']
        trainer.set_model_config(model_name="YOLOX-S", img_size=512)
        
        # 2-3. Augmentation
        trainer.set_augmentation_config(
            train_transforms=[Resize()],
            inference_transforms=[Resize()],
        )
        
        # 2-4. Training
        optimizer = AdamW(lr=6e-3)
        scheduler = CosineAnnealingWarmRestartsWithCustomWarmUp(warmup_epochs=10)
        trainer.set_training_config(
            epochs=40,
            batch_size=16,
            optimizer=optimizer,
            scheduler=scheduler,
        )
        
        # 3. Train
        training_result = trainer.train(gpus="0, 1", project_name="PROJECT_TRAIN_SAMPLE")
        ```
        
        #### Retrain
        
        To start retraining a model, use `hparams.yaml` file which is one of the artifacts generated during the training of the original model.
        
        Then, enter the compressed model path, which is an artifact of the compressor in fx_model_path.
        
        Adjust the training hyperparameters as needed. (See 2-2. for detailed code.)
        
        ```python
        from netspresso.trainer.optimizers import AdamW
        
        # 1. Declare trainer
        trainer = netspresso.trainer(yaml_path="./temp/hparams.yaml")
        
        # 2. Set config for retraining
        # 2-1. FX Model
        trainer.set_fx_model(fx_model_path="./temp/FX_MODEL_PATH.pt")
        
        # 2-2. Training
        optimizer = AdamW(lr=6e-3)
        trainer.set_training_config(
            epochs=30,
            batch_size=16,
            optimizer=optimizer,
        )
        
        # 3. Train
        retraining_result = trainer.train(gpus="0, 1", project_name="PROJECT_RETRAIN_SAMPLE")
        ```
        
        ### Compressor
        
        #### Compress (Automatic compression)
        
        To start compressing a model, enter the model path to compress and the appropriate compression ratio.
        
        The compressed model will be saved in the specified output directory (`output_dir`).
        
        ```python
        # 1. Declare compressor
        compressor = netspresso.compressor_v2()
        
        # 2. Run automatic compression
        compression_result = compressor.automatic_compression(
            input_shapes=[{"batch": 1, "channel": 3, "dimension": [224, 224]}],
            input_model_path="./examples/sample_models/graphmodule.pt",
            output_dir="./outputs/compressed/pytorch_automatic_compression",
            compression_ratio=0.5,
        )
        ```
        
        ### Converter
        
        #### Convert
        
        To start converting a model, enter the model path to convert and the target framework and device name.
        
        For NVIDIA GPUs and Jetson devices, enter the software version additionally due to the jetpack version.
        
        The converted model will be saved in the specified output directory (`output_dir`).
        
        ```python
        from netspresso.enums import DeviceName, Framework, SoftwareVersion
        
        # 1. Declare converter
        converter = netspresso.converter_v2()
        
        # 2. Run convert
        conversion_result = converter.convert_model(
            input_model_path="./examples/sample_models/test.onnx",
            output_dir="./outputs/converted/TENSORRT_JETSON_AGX_ORIN_JETPACK_5_0_1",
            target_framework=Framework.TENSORRT,
            target_device_name=DeviceName.JETSON_AGX_ORIN,
            target_software_version=SoftwareVersion.JETPACK_5_0_1,
        )
        ```
        
        ### Benchmarker
        
        #### Benchmark
        
        To start benchmarking a model, enter the model path to benchmark and the target device name.
        
        For NVIDIA GPUs and Jetson devices, device name and software version have to be matched with the target device of the conversion.
        
        TensorRT Model has strong dependency with the device type and its jetpack version.
        
        ```python
        from netspresso.enums import DeviceName, SoftwareVersion
        
        # 1. Declare benchmarker
        benchmarker = netspresso.benchmarker_v2()
        
        # 2. Run benchmark
        benchmark_result = benchmarker.benchmark_model(
            input_model_path="./outputs/converted/TENSORRT_JETSON_AGX_ORIN_JETPACK_5_0_1/TENSORRT_JETSON_AGX_ORIN_JETPACK_5_0_1.trt",
            target_device_name=DeviceName.JETSON_AGX_ORIN,
            target_software_version=SoftwareVersion.JETPACK_5_0_1,
        )
        print(f"model inference latency: {benchmark_result['result']['latency']} ms")
        print(f"model gpu memory footprint: {benchmark_result['result']['memory_footprint_gpu']} MB")
        print(f"model cpu memory footprint: {benchmark_result['result']['memory_footprint_cpu']} MB")
        ```
        
        <details open>
          <summary>Supported options for Converter & Benchmarker</summary>
          <div markdown="1">
        
          ### Frameworks that support conversion for model's framework
        
          | Target / Source Framework | ONNX | TENSORFLOW_KERAS | TENSORFLOW |
          |:--------------------------|:----:|:----------------:|:----------:|
          | TENSORRT                  |  ✔️  |                  |            |
          | DRPAI                     |  ✔️  |                  |            |
          | OPENVINO                  |  ✔️  |                  |            |
          | TENSORFLOW_LITE           |  ✔️  |        ✔️        |     ✔️     |
        
          ### Devices that support benchmarks for model's framework
        
          | Device / Framework           | ONNX | TENSORRT | TENSORFLOW_LITE | DRPAI | OPENVINO |
          |:-----------------------------|:----:|:--------:|:---------------:|:-----:|:--------:|
          | RASPBERRY_PI_5               |  ✔️  |          |       ✔️        |       |          |
          | RASPBERRY_PI_4B              |  ✔️  |          |       ✔️        |       |          |
          | RASPBERRY_PI_3B_PLUS         |  ✔️  |          |       ✔️        |       |          |
          | RASPBERRY_PI_ZERO_W          |  ✔️  |          |       ✔️        |       |          |
          | RASPBERRY_PI_ZERO_2W         |  ✔️  |          |       ✔️        |       |          |
          | ARM_ETHOS_U_SERIES           |      |          |  ✔️(only INT8)  |       |          |
          | ALIF_ENSEMBLE_E7_DEVKIT_GEN2 |      |          |  ✔️(only INT8)  |       |          |
          | RENESAS_RA8D1                |      |          |  ✔️(only INT8)  |       |          |
          | NXP_iMX93                    |      |          |  ✔️(only INT8)  |       |          |
          | ARDUINO_NICLA_VISION         |      |          |  ✔️(only INT8)  |       |          |
          | RENESAS_RZ_V2L               |  ✔️  |          |                 |  ✔️   |          |
          | RENESAS_RZ_V2M               |  ✔️  |          |                 |  ✔️   |          |
          | JETSON_NANO                  |  ✔️  |    ✔️    |                 |       |          |
          | JETSON_TX2                   |  ✔️  |    ✔️    |                 |       |          |
          | JETSON_XAVIER                |  ✔️  |    ✔️    |                 |       |          |
          | JETSON_NX                    |  ✔️  |    ✔️    |                 |       |          |
          | JETSON_AGX_ORIN              |  ✔️  |    ✔️    |                 |       |          |
          | JETSON_ORIN_NANO             |  ✔️  |    ✔️    |                 |       |          |
          | AWS_T4                       |  ✔️  |    ✔️    |                 |       |          |
          | INTEL_XEON_W_2233            |      |          |                 |       |    ✔️    |
        
          ### Software versions that support conversions and benchmarks for specific devices 
        
          Software Versions requires only Jetson Device. If you are using a different device, you do not need to enter it.
        
          | Software Version / Device | JETSON_NANO | JETSON_TX2 | JETSON_XAVIER | JETSON_NX | JETSON_AGX_ORIN | JETSON_ORIN_NANO |
          |:--------------------------|:-----------:|:----------:|:-------------:|:---------:|:---------------:|:----------------:|
          | JETPACK_4_4_1             |     ✔️      |            |               |           |                 |                  |
          | JETPACK_4_6               |     ✔️      |     ✔️     |      ✔️       |    ✔️     |                 |                  |
          | JETPACK_5_0_1             |             |            |               |           |       ✔️        |                  |
          | JETPACK_5_0_2             |             |            |               |    ✔️     |                 |                  |
          | JETPACK_6_0               |             |            |               |           |                 |        ✔️        |
        
          The code below is an example of using software version.
        
          ```python
          conversion_result = converter.convert_model(
              input_model_path=INPUT_MODEL_PATH,
              output_dir=OUTPUT_DIR,
              target_framework=Framework.TENSORRT,
              target_device_name=DeviceName.JETSON_AGX_ORIN,
              target_software_version=SoftwareVersion.JETPACK_5_0_1,
          )
          benchmark_result = benchmarker.benchmark_model(
              input_model_path=CONVERTED_MODEL_PATH,
              target_device_name=DeviceName.JETSON_AGX_ORIN,
              target_software_version=SoftwareVersion.JETPACK_5_0_1,
          )
          ```
        
          ### Hardware type that support benchmarks for specific devices
        
          Benchmark and compare models with and without Arm Helium.
        
          `RENESAS_RA8D1` and `ALIF_ENSEMBLE_E7_DEVKIT_GEN2` are available for use.
        
          The benchmark results with Helium can be up to twice as fast as without Helium.
        
          The code below is an example of using hardware type.
        
          ```python
          benchmark_result = benchmarker.benchmark_model(
              input_model_path=CONVERTED_MODEL_PATH,
              target_device_name=DeviceName.RENESAS_RA8D1,
              target_data_type=DataType.INT8,
              target_hardware_type=HardwareType.HELIUM
          )
          ```
          </div>
        </details>
        
        
        ## Guide to Credit Consumption by Module
        
        <table width="90%">
          <tr>
              <th>Module</th>
              <th>Feature</th>
              <th>Credit</th>
          </tr>
          <tr>
              <td align="center" rowspan="2">Compressor</td>
              <td align="center">Automatic compression</td>
              <td align="center">25</td>
          </tr>
          <tr>
              <td align="center">Advanced compression</td>
              <td align="center">50</td>
          </tr>
          <tr>
              <td align="center">Converter</td>
              <td align="center">Convert</td>
              <td align="center">50</td>
          </tr>
          <tr>
              <td align="center">Benchmarker</td>
              <td align="center">Benchmark</td>
              <td align="center">25</td>
          </tr>
        </table>
        
        ## Contact
        
        Join our [Discussion Forum] for providing feedback or sharing your use cases, and if you want to talk more with Nota, please contact us [here].</br>
        Or you can also do it via email([netspresso@nota.ai]) or phone(+82 2-555-8659)!
        
        
        [Docs]: https://nota-netspresso.github.io/PyNetsPresso
        [Discussion Forum]: https://github.com/orgs/Nota-NetsPresso/discussions
        [NetsPresso]: https://netspresso.ai?utm_source=git_comp&utm_medium=text_np&utm_campaign=py_launch
        [NetsPresso-Sign-Up]: https://netspresso.ai/signup
        [here]: https://www.nota.ai/contact-us
        [netspresso@nota.ai]: mailto:netspresso@nota.ai
        
Platform: UNKNOWN
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Description-Content-Type: text/markdown
