Asyncio Tensorflow Serving Communication.
Project description
aiotf
Asyncio-based
Tensorflow Serving
Prediction
Features
- asyncio: better use of your cpu idle time
- pep8 compliant: following best code standards
- high-performance prediction: we use
aio-grpc
Example
import aiotf
async def make_prediction(model_name: str, data):
async with aiotf.AsyncTensorflowServing('localhost:9000') as client:
predictions = await client.predict(model_name, data)
You can find more examples in the examples/
subdirectory.
Installation
$ pip install aiotf
License
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
aiotf-0.1.0.tar.gz
(3.5 kB
view hashes)
Built Distribution
Close
Hashes for aiotf-0.1.0-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 48a0e854db3ca26770723382dd56cab73df07bbe0c1420bc528bc8a0d4beab65 |
|
MD5 | e95873e2e29a92a73d23f87a8d81c5c2 |
|
BLAKE2b-256 | 07816448a6e9a17a55ee53425d8e786e48076354466dc9cc86cd53b9e37d60df |