Probably world fastest binary tensor stream reader for numpy; Using n;n;...;n:data for example c;h;w:data of image
Project description
numpy-u8-tensor-dto
A minimal, high-performance utility for reading binary tensor streams into NumPy arrays.
Designed for low-overhead data pipelines on ARM devices (e.g., Orange Pi 3B, RK3566) and ML inference (RKNN, PyTorch).
Protocol Format
The stream uses a simple ASCII prefix followed by raw bytes:
dim0;dim1;...;dimN:raw_bytes
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
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file numpy_u8_tensor_dto-0.1.1.tar.gz.
File metadata
- Download URL: numpy_u8_tensor_dto-0.1.1.tar.gz
- Upload date:
- Size: 3.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
94cfb07a29171dc3c086888807c955679fb0241d006276717c974643ae09f584
|
|
| MD5 |
43e17947eaa7643c147e2b5fc2925f31
|
|
| BLAKE2b-256 |
f76c68dbd10dd5ec96f7f8f4acc4e0686b5cacdc63f9b981fc6ca67c92f8727b
|
File details
Details for the file numpy_u8_tensor_dto-0.1.1-py3-none-any.whl.
File metadata
- Download URL: numpy_u8_tensor_dto-0.1.1-py3-none-any.whl
- Upload date:
- Size: 3.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6b88321b1f2c0c1ecf9f2bc0c153c286536effdd12aa8480941d08d18043e92a
|
|
| MD5 |
8e0b059627efe324de1b75826acae082
|
|
| BLAKE2b-256 |
d0136632a87cd2f62867f373261189168a381656d85744399a4d063f8f1698ba
|
