[![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)
# NaViT
My implementation of "Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution"
[Paper Link](https://arxiv.org/pdf/2307.06304.pdf)
# Appreciation
* Lucidrains
* Agorians
# Install
`pip install navit-torch`
# Usage
```pytorch
import torch
from navit.main import NaViT
n = NaViT(
image_size = 256,
patch_size = 32,
num_classes = 1000,
dim = 1024,
heads = 16,
mlp_dim=2048,
dropout=0.1,
emb_dropout=0.1,
token_dropout_prob=0.1
)
images = [
[torch.randn(3, 256, 256), torch.randn(3, 128, 128)],
[torch.randn(3, 256, 256), torch.randn(3, 256, 128)],
[torch.randn(3, 64, 256)]
]
preds = n(images)
```
# Architecture
# Todo
# License
MIT
# Citations
```
@misc{2307.06304,
Author = {Mostafa Dehghani and Basil Mustafa and Josip Djolonga and Jonathan Heek and Matthias Minderer and Mathilde Caron and Andreas Steiner and Joan Puigcerver and Robert Geirhos and Ibrahim Alabdulmohsin and Avital Oliver and Piotr Padlewski and Alexey Gritsenko and Mario Lučić and Neil Houlsby},
Title = {Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution},
Year = {2023},
Eprint = {arXiv:2307.06304},
}
```
Raw data
{
"_id": null,
"home_page": "https://github.com/kyegomez/navit",
"name": "navit-torch",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6,<4.0",
"maintainer_email": "",
"keywords": "artificial intelligence,deep learning,optimizers,Prompt Engineering",
"author": "Kye Gomez",
"author_email": "kye@apac.ai",
"download_url": "https://files.pythonhosted.org/packages/de/01/bf58c110f056923f9c2434340abb62605c5541c120eeef6a795416d545a3/navit_torch-0.0.8.tar.gz",
"platform": null,
"description": "[![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)\n\n# NaViT\nMy implementation of \"Patch n\u2019 Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution\"\n\n[Paper Link](https://arxiv.org/pdf/2307.06304.pdf)\n\n# Appreciation\n* Lucidrains\n* Agorians\n\n# Install\n`pip install navit-torch`\n\n# Usage\n```pytorch\nimport torch\nfrom navit.main import NaViT\n\n\nn = NaViT(\n image_size = 256,\n patch_size = 32,\n num_classes = 1000,\n dim = 1024,\n heads = 16,\n mlp_dim=2048,\n dropout=0.1,\n emb_dropout=0.1,\n token_dropout_prob=0.1\n)\n\nimages = [\n [torch.randn(3, 256, 256), torch.randn(3, 128, 128)],\n [torch.randn(3, 256, 256), torch.randn(3, 256, 128)],\n [torch.randn(3, 64, 256)]\n]\n\npreds = n(images)\n```\n\n# Architecture\n\n# Todo\n\n\n# License\nMIT\n\n# Citations\n```\n@misc{2307.06304,\nAuthor = {Mostafa Dehghani and Basil Mustafa and Josip Djolonga and Jonathan Heek and Matthias Minderer and Mathilde Caron and Andreas Steiner and Joan Puigcerver and Robert Geirhos and Ibrahim Alabdulmohsin and Avital Oliver and Piotr Padlewski and Alexey Gritsenko and Mario Lu\u010di\u0107 and Neil Houlsby},\nTitle = {Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution},\nYear = {2023},\nEprint = {arXiv:2307.06304},\n}\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "navit - Pytorch",
"version": "0.0.8",
"project_urls": {
"Homepage": "https://github.com/kyegomez/navit",
"Repository": "https://github.com/kyegomez/navit"
},
"split_keywords": [
"artificial intelligence",
"deep learning",
"optimizers",
"prompt engineering"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "29050d3a13e9677b534e620f1365287d881475218e9309b0f42579bb44feb068",
"md5": "bbaf9173c2c3ae136ffe485e15db42f9",
"sha256": "224fed285128e10554d0e1e165c18894370a75769f1900ecf98558803bd2ae3c"
},
"downloads": -1,
"filename": "navit_torch-0.0.8-py3-none-any.whl",
"has_sig": false,
"md5_digest": "bbaf9173c2c3ae136ffe485e15db42f9",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6,<4.0",
"size": 6457,
"upload_time": "2023-09-28T23:23:42",
"upload_time_iso_8601": "2023-09-28T23:23:42.860996Z",
"url": "https://files.pythonhosted.org/packages/29/05/0d3a13e9677b534e620f1365287d881475218e9309b0f42579bb44feb068/navit_torch-0.0.8-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "de01bf58c110f056923f9c2434340abb62605c5541c120eeef6a795416d545a3",
"md5": "2e170d40aca33065f793a47ee33982ea",
"sha256": "8404b64e330060e1c9770d1942b722881cce0c3ac0c6896fa825b1b9bebe67f8"
},
"downloads": -1,
"filename": "navit_torch-0.0.8.tar.gz",
"has_sig": false,
"md5_digest": "2e170d40aca33065f793a47ee33982ea",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6,<4.0",
"size": 6569,
"upload_time": "2023-09-28T23:23:44",
"upload_time_iso_8601": "2023-09-28T23:23:44.406156Z",
"url": "https://files.pythonhosted.org/packages/de/01/bf58c110f056923f9c2434340abb62605c5541c120eeef6a795416d545a3/navit_torch-0.0.8.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-09-28 23:23:44",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "kyegomez",
"github_project": "navit",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "navit-torch"
}