simba-torch

Name	simba-torch JSON
Version	0.0.5 JSON
	download
home_page	https://github.com/kyegomez/Simba
Summary	Paper - Pytorch
upload_time	2024-03-26 08:03:53
maintainer	None
docs_url	None
author	Kye Gomez
requires_python	<4.0,>=3.6
license	MIT
keywords	artificial intelligence deep learning optimizers prompt engineering
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            
# Simba
![graph](graph.png)
A simpler Pytorch + Zeta Implementation of the paper: "SiMBA: Simplified Mamba-based Architecture for Vision and Multivariate Time series"


## install
`$ pip install simba-torch`

## usage
```python

import torch 
from simba_torch.main import Simba

# Forward pass with images
img = torch.randn(1, 3, 224, 224)

# Create model
model = Simba(
    dim = 4,                # Dimension of the transformer
    dropout = 0.1,          # Dropout rate for regularization
    d_state=64,             # Dimension of the transformer state
    d_conv=64,              # Dimension of the convolutional layers
    num_classes=64,         # Number of output classes
    depth=8,                # Number of transformer layers
    patch_size=16,          # Size of the image patches
    image_size=224,         # Size of the input image
    channels=3,             # Number of input channels
    # use_pos_emb=True # If you want
)

# Forward pass
out = model(img)
print(out.shape)

```


# License
MIT

# Todo
- [ ] Add paper link
- [ ] Add citation bibtex
- [ ] cleanup
            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/kyegomez/Simba",
    "name": "simba-torch",
    "maintainer": null,
    "docs_url": null,
    "requires_python": "<4.0,>=3.6",
    "maintainer_email": null,
    "keywords": "artificial intelligence, deep learning, optimizers, Prompt Engineering",
    "author": "Kye Gomez",
    "author_email": "kye@apac.ai",
    "download_url": "https://files.pythonhosted.org/packages/b1/bc/7f22a7bdd4166d258bea69751d8d09dc150f1a6eb885fb0a3d96b1c938da/simba_torch-0.0.5.tar.gz",
    "platform": null,
    "description": "\n# Simba\n![graph](graph.png)\nA simpler Pytorch + Zeta Implementation of the paper: \"SiMBA: Simplified Mamba-based Architecture for Vision and Multivariate Time series\"\n\n\n## install\n`$ pip install simba-torch`\n\n## usage\n```python\n\nimport torch \nfrom simba_torch.main import Simba\n\n# Forward pass with images\nimg = torch.randn(1, 3, 224, 224)\n\n# Create model\nmodel = Simba(\n    dim = 4,                # Dimension of the transformer\n    dropout = 0.1,          # Dropout rate for regularization\n    d_state=64,             # Dimension of the transformer state\n    d_conv=64,              # Dimension of the convolutional layers\n    num_classes=64,         # Number of output classes\n    depth=8,                # Number of transformer layers\n    patch_size=16,          # Size of the image patches\n    image_size=224,         # Size of the input image\n    channels=3,             # Number of input channels\n    # use_pos_emb=True # If you want\n)\n\n# Forward pass\nout = model(img)\nprint(out.shape)\n\n```\n\n\n# License\nMIT\n\n# Todo\n- [ ] Add paper link\n- [ ] Add citation bibtex\n- [ ] cleanup",
    "bugtrack_url": null,
    "license": "MIT",
    "summary": "Paper - Pytorch",
    "version": "0.0.5",
    "project_urls": {
        "Documentation": "https://github.com/kyegomez/Simba",
        "Homepage": "https://github.com/kyegomez/Simba",
        "Repository": "https://github.com/kyegomez/Simba"
    },
    "split_keywords": [
        "artificial intelligence",
        " deep learning",
        " optimizers",
        " prompt engineering"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "686841bc77be42bf45adc262e91ab96eafeefa90a07a4b3d3d8aa9461a5e9df2",
                "md5": "a0d9b29578cf64d0e0877e8410d95648",
                "sha256": "46ac9b3296780b001b81ad79542bf14290683acbb600a99d130b756d4d470284"
            },
            "downloads": -1,
            "filename": "simba_torch-0.0.5-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "a0d9b29578cf64d0e0877e8410d95648",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": "<4.0,>=3.6",
            "size": 5998,
            "upload_time": "2024-03-26T08:03:50",
            "upload_time_iso_8601": "2024-03-26T08:03:50.327839Z",
            "url": "https://files.pythonhosted.org/packages/68/68/41bc77be42bf45adc262e91ab96eafeefa90a07a4b3d3d8aa9461a5e9df2/simba_torch-0.0.5-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "b1bc7f22a7bdd4166d258bea69751d8d09dc150f1a6eb885fb0a3d96b1c938da",
                "md5": "7ab0ecc9a82ed0ff8c11b82febd08308",
                "sha256": "e619f4defed636bfe3d7218ede72c1dba003a0558a8372dda3a0e0bbd94240a2"
            },
            "downloads": -1,
            "filename": "simba_torch-0.0.5.tar.gz",
            "has_sig": false,
            "md5_digest": "7ab0ecc9a82ed0ff8c11b82febd08308",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": "<4.0,>=3.6",
            "size": 5699,
            "upload_time": "2024-03-26T08:03:53",
            "upload_time_iso_8601": "2024-03-26T08:03:53.495233Z",
            "url": "https://files.pythonhosted.org/packages/b1/bc/7f22a7bdd4166d258bea69751d8d09dc150f1a6eb885fb0a3d96b1c938da/simba_torch-0.0.5.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-03-26 08:03:53",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "kyegomez",
    "github_project": "Simba",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "requirements": [],
    "lcname": "simba-torch"
}