Azure Machine Learning Hardware Accelerated models
Project description
Easily create and train a model using various deep neural networks (DNNs) as a featurizer for deployment to Azure or a Data Box Edge device for ultra-low latency inference. These models are currently available:
ResNet 50
ResNet 152
DenseNet-121
VGG-16
SSD-VGG
Setup
Follow these instructions to install the Azure ML SDK on your local machine, create an Azure ML workspace, and set up your notebook environment, which is required for the next step.
Once you have set up your environment, install the Azure ML Accel Models SDK:
pip install azureml-accel-modelsNote:* This package requires you to install tensorflow >= 1.6. This can be done using:
pip install azureml-accel-models[cpu]If your machine supports GPU, then you can leverage the tensorflow-gpu functionality using:
pip install azureml-accel-models[gpu]AzureML-Accel-Models
Create a featurizer using the Accelerated Models
Convert tensorflow model to ONNX format using AccelOnnxConverter
Create a container image with AccelContainerImage for deploying to either Azure or Data Box Edge
Use the sample PredictionClient for inference on a Accelerated Model Host or create your own GRPC client
Resources
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 Distributions
Built Distribution
File details
Details for the file azureml_accel_models-1.0.72-py3-none-any.whl.
File metadata
- Download URL: azureml_accel_models-1.0.72-py3-none-any.whl
- Upload date:
- Size: 53.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.11.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.2.0 requests-toolbelt/0.9.1 tqdm/4.36.1 CPython/3.5.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 12688d82968d0d8c9460068b380476f3954ccce61f98301b9cd406ee3ca5d2d4 |
|
| MD5 | e0ae29f21ad5a0b5beb32c6d85a5a9fc |
|
| BLAKE2b-256 | 7dd819681712d4b8b6fea6f30aeb0e3946132eb86403ce6d3edf9f6802624172 |
