# Unified Vision Service Model Customization
## Intro
Unified Vision Service Model Customization is a model training service that allows users like developers to easily train an image classification model (Multiclass only for now) or object detection model, with low-code experience and very little understanding in machine learning or computer vision required.
This is an example repo showing how to train a model and predict with the trained model in Unified Vision Service. A manually crafted Python SDK is provdied. **Note this is NOT an official UVS SDK that is ready for production usage/integration, but more for convenience of trying out UVS model customization service at the absence of official SDK support.**
## SDK Tutorial
For tutorial about how to use this python SDK to train and predict with UVS, checkout [this tutorial in Python notebook](./tutorial.ipynb).
## Vision Studio Tutorial
For tutorial about how to use Vision Studio to train and predict with UVS, checkout [this Vision Studio tutorial](VisionStudioDemo.md).
## Existing Custom Vision Customers
Refer to [export_cvs_data_to_coco.ipynb](export_cvs_data_to_coco.ipynb) for instructions or directly run [export_cvs_data_to_coco.py](export_cvs_data_to_coco.py) to export Custom Vision images and annotations to your own blob storage, which can be later used for UVS model customization training.
Once data is exported, you can use either SDK or Vision Studio to train with it.
## FAQ
For frequently asked questions or quick trouble shoot, checkout [FAQ](FAQ.md).
Raw data
{
"_id": null,
"home_page": "",
"name": "uvs-training-sdk",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "vision datasets classification detection",
"author": "Ping Jin",
"author_email": "",
"download_url": "https://files.pythonhosted.org/packages/ac/fe/82dc0348f256c011db47357a90d62865d027e8751220e9b32e1c3bb3aa96/uvs-training-sdk-0.0.3.tar.gz",
"platform": null,
"description": "# Unified Vision Service Model Customization\n\n## Intro\n\nUnified Vision Service Model Customization is a model training service that allows users like developers to easily train an image classification model (Multiclass only for now) or object detection model, with low-code experience and very little understanding in machine learning or computer vision required.\n\nThis is an example repo showing how to train a model and predict with the trained model in Unified Vision Service. A manually crafted Python SDK is provdied. **Note this is NOT an official UVS SDK that is ready for production usage/integration, but more for convenience of trying out UVS model customization service at the absence of official SDK support.**\n\n## SDK Tutorial\n\nFor tutorial about how to use this python SDK to train and predict with UVS, checkout [this tutorial in Python notebook](./tutorial.ipynb).\n\n## Vision Studio Tutorial\n\nFor tutorial about how to use Vision Studio to train and predict with UVS, checkout [this Vision Studio tutorial](VisionStudioDemo.md).\n\n## Existing Custom Vision Customers\n\nRefer to [export_cvs_data_to_coco.ipynb](export_cvs_data_to_coco.ipynb) for instructions or directly run [export_cvs_data_to_coco.py](export_cvs_data_to_coco.py) to export Custom Vision images and annotations to your own blob storage, which can be later used for UVS model customization training.\n\nOnce data is exported, you can use either SDK or Vision Studio to train with it.\n\n## FAQ\n\nFor frequently asked questions or quick trouble shoot, checkout [FAQ](FAQ.md).\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A sample python SDK for training and prediction with Unified Vision Service.",
"version": "0.0.3",
"split_keywords": [
"vision",
"datasets",
"classification",
"detection"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "c7499eabca00636232e8de4368c6ca4c764c488c5407a66e97d90382156beb81",
"md5": "971e8836fc9d79cdac85b9344f3ffa12",
"sha256": "7ce69965e86dd1c5208179c33d4e598e5e46891c02d9221ca6242eb22e3dda33"
},
"downloads": -1,
"filename": "uvs_training_sdk-0.0.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "971e8836fc9d79cdac85b9344f3ffa12",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 11116,
"upload_time": "2023-01-15T21:41:49",
"upload_time_iso_8601": "2023-01-15T21:41:49.548807Z",
"url": "https://files.pythonhosted.org/packages/c7/49/9eabca00636232e8de4368c6ca4c764c488c5407a66e97d90382156beb81/uvs_training_sdk-0.0.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "acfe82dc0348f256c011db47357a90d62865d027e8751220e9b32e1c3bb3aa96",
"md5": "4e4c0a97cebcd5657e2d18ab1d8307ba",
"sha256": "2d6a4676e7726483a66e605e8c7314ee69fd3241b1916eca42442e83c091ea53"
},
"downloads": -1,
"filename": "uvs-training-sdk-0.0.3.tar.gz",
"has_sig": false,
"md5_digest": "4e4c0a97cebcd5657e2d18ab1d8307ba",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 7729,
"upload_time": "2023-01-15T21:41:51",
"upload_time_iso_8601": "2023-01-15T21:41:51.018716Z",
"url": "https://files.pythonhosted.org/packages/ac/fe/82dc0348f256c011db47357a90d62865d027e8751220e9b32e1c3bb3aa96/uvs-training-sdk-0.0.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-01-15 21:41:51",
"github": false,
"gitlab": false,
"bitbucket": false,
"lcname": "uvs-training-sdk"
}
JSON