Inference module.
Project description
How to use
Use directly
- model_file_path: Model file path(ONNX, TFLite)
- dataset_file_path: The path to the compressed file or the individual npy files where the delimiter of the input layer is used as the file name.
python3 inference.py --model_file_path tests/your_model_file.tflite --dataset_file_path tests/your_dataset_file.npy
Import and use
from netspresso_inference_package.inference.inference_service import InferenceService
inf_service = InferenceService(
model_file_path="/app/tests/people_detection.onnx",
dataset_file_path="/app/tests/dataset_for_onnx.npy"
)
inf_service.run()
print(inf_service.result_file_path)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file netspresso_inference_package-0.1.0.tar.gz
.
File metadata
- Download URL: netspresso_inference_package-0.1.0.tar.gz
- Upload date:
- Size: 6.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.11.9
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | d0c05c3c0797d350a26905d1a2021187af46a067c303cc87b98db118af7175b6 |
|
MD5 | 399f3760109d45933ac3d85b49bbf314 |
|
BLAKE2b-256 | 6d41f803d1f776053fad1606aebc87ace0c25a66ebf98e792bb594475b9bf12a |
File details
Details for the file netspresso_inference_package-0.1.0-py3-none-any.whl
.
File metadata
- Download URL: netspresso_inference_package-0.1.0-py3-none-any.whl
- Upload date:
- Size: 17.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.11.9
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 131362caebdfbed8518f63b44c185db6f9c03085931d243fd403649b47d05bf3 |
|
MD5 | 8f117cbbb4bc121e14dbeab6a9bb8f5b |
|
BLAKE2b-256 | 3f48e4af03cbbbd37322933c12c6f896509629918e3b36b1a6ae95d88593cc2d |