[![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)
# LiquidNet
This is a simple implementation of the Liquid net official repo translated into pytorch for simplicity. [Find the original repo here:](https://github.com/raminmh/liquid_time_constant_networks)
## Install
`pip install liquidnet`
## Usage
```python
import torch
from liquidnet.main import LiquidNet
# Create an LiquidNet with a specified number of units
num_units = 64
ltc_cell = LiquidNet(num_units)
# Generate random input data with batch size 4 and input size 32
batch_size = 4
input_size = 32
inputs = torch.randn(batch_size, input_size)
# Initialize the cell state (hidden state)
initial_state = torch.zeros(batch_size, num_units)
# Forward pass through the LiquidNet
outputs, final_state = ltc_cell(inputs, initial_state)
# Print the shape of outputs and final_state
print("Outputs shape:", outputs.shape)
print("Final state shape:", final_state.shape)
```
## `VisionLiquidNet`
- Simple model with 2 convolutions with 2 max pools, alot of room for improvement
```python
import torch
from liquidnet.vision_liquidnet import VisionLiquidNet
# Random Input Image
x = torch.randn(4, 3, 32, 32)
# Create a VisionLiquidNet with a specified number of units
model = VisionLiquidNet(64, 10)
# Forward pass through the VisionLiquidNet
print(model(x).shape)
```
# Citation
```bibtex
@article{DBLP:journals/corr/abs-2006-04439,
author = {Ramin M. Hasani and
Mathias Lechner and
Alexander Amini and
Daniela Rus and
Radu Grosu},
title = {Liquid Time-constant Networks},
journal = {CoRR},
volume = {abs/2006.04439},
year = {2020},
url = {https://arxiv.org/abs/2006.04439},
eprinttype = {arXiv},
eprint = {2006.04439},
timestamp = {Fri, 12 Jun 2020 14:02:57 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-04439.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
```
# License
MIT
# Todo:
- [ ] Implement LiquidNet for vision and train on CIFAR
Raw data
{
"_id": null,
"home_page": "https://github.com/kyegomez/LiqudNet",
"name": "liquidnet",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.9,<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/9a/35/3b75c0e49bee70341fc2c43d61e4d5537c1084a36da78d2517d507317b7d/liquidnet-0.0.5.tar.gz",
"platform": null,
"description": "[![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)\n\n# LiquidNet\nThis is a simple implementation of the Liquid net official repo translated into pytorch for simplicity. [Find the original repo here:](https://github.com/raminmh/liquid_time_constant_networks)\n\n## Install\n`pip install liquidnet`\n\n## Usage\n```python\nimport torch\nfrom liquidnet.main import LiquidNet\n\n# Create an LiquidNet with a specified number of units\nnum_units = 64\nltc_cell = LiquidNet(num_units)\n\n# Generate random input data with batch size 4 and input size 32\nbatch_size = 4\ninput_size = 32\ninputs = torch.randn(batch_size, input_size)\n\n# Initialize the cell state (hidden state)\ninitial_state = torch.zeros(batch_size, num_units)\n\n# Forward pass through the LiquidNet\noutputs, final_state = ltc_cell(inputs, initial_state)\n\n# Print the shape of outputs and final_state\nprint(\"Outputs shape:\", outputs.shape)\nprint(\"Final state shape:\", final_state.shape)\n\n```\n\n## `VisionLiquidNet`\n- Simple model with 2 convolutions with 2 max pools, alot of room for improvement\n\n```python\nimport torch \nfrom liquidnet.vision_liquidnet import VisionLiquidNet\n\n# Random Input Image\nx = torch.randn(4, 3, 32, 32)\n\n# Create a VisionLiquidNet with a specified number of units\nmodel = VisionLiquidNet(64, 10)\n\n# Forward pass through the VisionLiquidNet\nprint(model(x).shape)\n\n\n```\n\n\n# Citation\n```bibtex\n@article{DBLP:journals/corr/abs-2006-04439,\n author = {Ramin M. Hasani and\n Mathias Lechner and\n Alexander Amini and\n Daniela Rus and\n Radu Grosu},\n title = {Liquid Time-constant Networks},\n journal = {CoRR},\n volume = {abs/2006.04439},\n year = {2020},\n url = {https://arxiv.org/abs/2006.04439},\n eprinttype = {arXiv},\n eprint = {2006.04439},\n timestamp = {Fri, 12 Jun 2020 14:02:57 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2006-04439.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n```\n\n\n# License\nMIT\n\n\n# Todo:\n- [ ] Implement LiquidNet for vision and train on CIFAR\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Liquid Net - Pytorch",
"version": "0.0.5",
"project_urls": {
"Homepage": "https://github.com/kyegomez/LiqudNet",
"Repository": "https://github.com/kyegomez/LiqudNet"
},
"split_keywords": [
"artificial intelligence",
"deep learning",
"optimizers",
"prompt engineering"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "8573a66f1bae5f1fb4efb84f40ef23cf018ae6d12cf62fafd400dc624defe84e",
"md5": "3592ae2d7f93dc06da6bb39e037325e6",
"sha256": "b74aeb3c3e3c2ec0ea8a37329fae1f5bf7acb17571a4e041c588cd874c0cdda2"
},
"downloads": -1,
"filename": "liquidnet-0.0.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "3592ae2d7f93dc06da6bb39e037325e6",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9,<4.0",
"size": 7076,
"upload_time": "2023-11-06T06:25:55",
"upload_time_iso_8601": "2023-11-06T06:25:55.051188Z",
"url": "https://files.pythonhosted.org/packages/85/73/a66f1bae5f1fb4efb84f40ef23cf018ae6d12cf62fafd400dc624defe84e/liquidnet-0.0.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "9a353b75c0e49bee70341fc2c43d61e4d5537c1084a36da78d2517d507317b7d",
"md5": "c0a0dd9aa20b114a2d81978e2fd175c8",
"sha256": "5163e3341c40a932025cba788dbc181517c4dd26b6e0ae1c63d4ca5a768625a3"
},
"downloads": -1,
"filename": "liquidnet-0.0.5.tar.gz",
"has_sig": false,
"md5_digest": "c0a0dd9aa20b114a2d81978e2fd175c8",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9,<4.0",
"size": 7175,
"upload_time": "2023-11-06T06:25:56",
"upload_time_iso_8601": "2023-11-06T06:25:56.702408Z",
"url": "https://files.pythonhosted.org/packages/9a/35/3b75c0e49bee70341fc2c43d61e4d5537c1084a36da78d2517d507317b7d/liquidnet-0.0.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-11-06 06:25:56",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "kyegomez",
"github_project": "LiqudNet",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "liquidnet"
}