Embedded Network Optimization Technology
ENOT, or Embedded Network Optimization Technology, is a flexible tool for Deep Learning developers which automates
neural architecture optimization.
It can be useful in the following scenarios:
- Target metric maximization (e.g., classification accuracy or intersection over union);
- Target metric maximization with constrained computational resources (e.g., RAM, latency);
Framework advantages:
- Controlled ratio between latency and network performance;
- Networks in the pre-trained search space can exceed their stand-alone variants (in some scenarios);
- Compatibility with almost any DL task and simple integration with the existing training pipelines.
- Joint neural architecture search, prunning and distillation procedure can be applied to found optimal neural
network architecture.
To use this package please refer to our [documentation page](https://enot-autodl.rtd.enot.ai/en/stable/).
Visit [our website](https://enot.ai) for more information.
Raw data
{
"_id": null,
"home_page": "https://enot.ai",
"name": "enot-autodl-yandex",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "AI,Neural architecture search",
"author": "ENOT LLC",
"author_email": "enot@enot.ai",
"download_url": "",
"platform": null,
"description": "Embedded Network Optimization Technology\n\nENOT, or Embedded Network Optimization Technology, is a flexible tool for Deep Learning developers which automates\nneural architecture optimization.\nIt can be useful in the following scenarios:\n- Target metric maximization (e.g., classification accuracy or intersection over union);\n- Target metric maximization with constrained computational resources (e.g., RAM, latency);\n\nFramework advantages:\n- Controlled ratio between latency and network performance;\n- Networks in the pre-trained search space can exceed their stand-alone variants (in some scenarios);\n- Compatibility with almost any DL task and simple integration with the existing training pipelines.\n- Joint neural architecture search, prunning and distillation procedure can be applied to found optimal neural\nnetwork architecture.\n\nTo use this package please refer to our [documentation page](https://enot-autodl.rtd.enot.ai/en/stable/).\n\nVisit [our website](https://enot.ai) for more information.\n",
"bugtrack_url": null,
"license": "ENOT License v1.0",
"summary": "AutoDL framework for neural network compression & acceleration",
"version": "3.2.5",
"split_keywords": [
"ai",
"neural architecture search"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "ef9f7082ad2d97aa6f8c2a5c605bb9ef7eef6b89c763d10ef11f7f46a14839cc",
"md5": "174b60af391eecd5c48c165a0417ad60",
"sha256": "a7aa7bfecca954f63d1e5578effca75e3b8f1264b00e54bc3bde3bec6daf0ddc"
},
"downloads": -1,
"filename": "enot_autodl_yandex-3.2.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl",
"has_sig": false,
"md5_digest": "174b60af391eecd5c48c165a0417ad60",
"packagetype": "bdist_wheel",
"python_version": "cp38",
"requires_python": null,
"size": 10512674,
"upload_time": "2023-04-05T06:18:17",
"upload_time_iso_8601": "2023-04-05T06:18:17.580877Z",
"url": "https://files.pythonhosted.org/packages/ef/9f/7082ad2d97aa6f8c2a5c605bb9ef7eef6b89c763d10ef11f7f46a14839cc/enot_autodl_yandex-3.2.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-04-05 06:18:17",
"github": false,
"gitlab": false,
"bitbucket": false,
"lcname": "enot-autodl-yandex"
}
JSON