netspresso 1.0.2

NetsPresso Python Package

NetsPresso Python Package

Use PyNetsPresso for a seamless model optimization process. PyNetsPresso 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.

The NetsPresso Python package is a python interface with the NetsPresso web application and REST API.

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 the NetsPresso Python package, you will need to sign up either at NetsPresso or PyNetsPresso.

Installation

There are two ways you can install the NetsPresso Python Package: using pip or manually through our project GitHub repository.

To install this package, please use Python 3.8 or higher.

From PyPI (Recommended)

pip install netspresso

From Github

git clone https://github.com/Nota-NetsPresso/netspresso-python.git
pip install -e .

Quick Start

Login

To use the NetsPresso Python package, please enter the email and password registered in NetsPresso.

from netspresso.compressor import ModelCompressor

compressor = ModelCompressor(email="YOUR_EMAIL", password="YOUR_PASSWORD")

Upload Model

To upload your trained model, simply enter the required information.

When a model is successfully uploaded, a unique 'model.model_id' is generated to allow repeated use of the uploaded model.

from netspresso.compressor import Task, Framework

model = compressor.upload_model(
    model_name="YOUR_MODEL_NAME",
    task=Task.IMAGE_CLASSIFICATION,
    framework=Framework.TENSORFLOW_KERAS,
    file_path="YOUR_MODEL_PATH", # ex) ./model.h5
    input_shapes="YOUR_MODEL_INPUT_SHAPES",  # ex) [{"batch": 1, "channel": 3, "dimension": [32, 32]}]
)

Automatic Compression

Automatically compress the model by setting the compression ratio for the model.

Enter the ID of the uploaded model, the name and storage path of the compressed model, and the compression ratio.

compressed_model = compressor.automatic_compression(
    model_id=model.model_id,
    model_name="YOUR_COMPRESSED_MODEL_NAME",
    output_path="OUTPUT_PATH",  # ex) ./compressed_model.h5
    compression_ratio=0.5,
)

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.
Or you can also do it via email([e-mail]) or phone[phone])!