[](https://discord.gg/qUtxnK2NMf)
# Video Vit
Open source implementation of a vision transformer that can understand Videos using max vit as a foundation. This uses max vit as the backbone vit and then packs the video tensor into a 4d tensor which is the input to the maxvit model. Implementing this because the new McVit came out and I need more practice. This is fully ready to train and I believe would perform amazingly.
## Installation
`$ pip install video-vit`
## Usage
```python
import torch
from video_vit.main import VideoViT
# Instantiate the VideoViT model with the specified parameters
model = VideoViT(
num_classes=10, # Number of output classes
dim=64, # Dimension of the token embeddings
depth=(2, 2, 2), # Depth of each stage in the model
dim_head=32, # Dimension of the attention head
window_size=7, # Size of the attention window
mbconv_expansion_rate=4, # Expansion rate of the Mobile Inverted Bottleneck block
mbconv_shrinkage_rate=0.25, # Shrinkage rate of the Mobile Inverted Bottleneck block
dropout=0.1, # Dropout rate
channels=3, # Number of input channels
)
# Create a random tensor with shape (batch_size, channels, frames, height, width)
x = torch.randn(1, 3, 10, 224, 224)
# Perform a forward pass through the model
output = model(x)
# Print the shape of the output tensor
print(output.shape)
```
# License
MIT
Raw data
{
"_id": null,
"home_page": "https://github.com/kyegomez/VideoVIT",
"name": "video-vit",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6.1,<4.0.0",
"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/16/ef/2dd8b31e1629d6ca1d716c14322d03bd108637f6d82b0fea3fb5933e1321/video_vit-0.0.4.tar.gz",
"platform": null,
"description": "[](https://discord.gg/qUtxnK2NMf)\n\n# Video Vit\nOpen source implementation of a vision transformer that can understand Videos using max vit as a foundation. This uses max vit as the backbone vit and then packs the video tensor into a 4d tensor which is the input to the maxvit model. Implementing this because the new McVit came out and I need more practice. This is fully ready to train and I believe would perform amazingly.\n\n## Installation\n`$ pip install video-vit`\n\n## Usage\n```python\nimport torch\nfrom video_vit.main import VideoViT\n\n# Instantiate the VideoViT model with the specified parameters\nmodel = VideoViT(\n num_classes=10, # Number of output classes\n dim=64, # Dimension of the token embeddings\n depth=(2, 2, 2), # Depth of each stage in the model\n dim_head=32, # Dimension of the attention head\n window_size=7, # Size of the attention window\n mbconv_expansion_rate=4, # Expansion rate of the Mobile Inverted Bottleneck block\n mbconv_shrinkage_rate=0.25, # Shrinkage rate of the Mobile Inverted Bottleneck block\n dropout=0.1, # Dropout rate\n channels=3, # Number of input channels\n)\n\n# Create a random tensor with shape (batch_size, channels, frames, height, width)\nx = torch.randn(1, 3, 10, 224, 224)\n\n# Perform a forward pass through the model\noutput = model(x)\n\n# Print the shape of the output tensor\nprint(output.shape)\n\n\n```\n\n\n# License\nMIT\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Paper - Pytorch",
"version": "0.0.4",
"project_urls": {
"Homepage": "https://github.com/kyegomez/VideoVIT",
"Repository": "https://github.com/kyegomez/VideoVIT"
},
"split_keywords": [
"artificial intelligence",
"deep learning",
"optimizers",
"prompt engineering"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "fd018fc5570c1429f9f8c91bdb93cc435c452d4019aa2741c0d1b47145ba5d99",
"md5": "5dcc6ce561f5b7625a68f4d0b3c8273c",
"sha256": "84966886036bb6e4d81f14db3b42283004699ab274b91849b070470be5d2943a"
},
"downloads": -1,
"filename": "video_vit-0.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "5dcc6ce561f5b7625a68f4d0b3c8273c",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6.1,<4.0.0",
"size": 7189,
"upload_time": "2024-02-09T18:14:02",
"upload_time_iso_8601": "2024-02-09T18:14:02.888662Z",
"url": "https://files.pythonhosted.org/packages/fd/01/8fc5570c1429f9f8c91bdb93cc435c452d4019aa2741c0d1b47145ba5d99/video_vit-0.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "16ef2dd8b31e1629d6ca1d716c14322d03bd108637f6d82b0fea3fb5933e1321",
"md5": "58af345faf8453ffcfb3b3c2c7456050",
"sha256": "c4f031328fc1e856ca095bc7c2d392a0908d4733b5b93682971ffc78edd25f7c"
},
"downloads": -1,
"filename": "video_vit-0.0.4.tar.gz",
"has_sig": false,
"md5_digest": "58af345faf8453ffcfb3b3c2c7456050",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6.1,<4.0.0",
"size": 7068,
"upload_time": "2024-02-09T18:14:04",
"upload_time_iso_8601": "2024-02-09T18:14:04.480580Z",
"url": "https://files.pythonhosted.org/packages/16/ef/2dd8b31e1629d6ca1d716c14322d03bd108637f6d82b0fea3fb5933e1321/video_vit-0.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-09 18:14:04",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "kyegomez",
"github_project": "VideoVIT",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "video-vit"
}
JSON
