<div align="center"><a href="[https://i.ibb.co/cTyQysp/netwk-back-modified.png](https://i.ibb.co/cTyQysp/netwk-back-modified.png)"><img src="https://i.ibb.co/cTyQysp/netwk-back-modified.png" alt="flowa" border="0" width="430"></a></div>
# [netkw - Neural Network Toolkit](https://pypi.org/project/netwk)
[](https://github.com/flowa-ai/netwk/blob/master/LICENSE)
[](https://www.python.org/downloads/)
```
netwk: (V2.12.5)
Create fast, optimized, and easy-to-use neural networks.
```
## Installing
```shell
# Linux/macOS
python3 pip install -U netwk
# Windows
py -3 -m pip install -U netwk
```
### FastFix:
```diff
+ Made it so for hidden layers, you can have just one layer, in or not in a list/tuple.
```
# Usage
```python
import netwk as nk
nk.Seed(52) # Optional, used for testing purposes.
x = nk.Array([[0, 0], [0, 1], [1, 0], [1, 1]])
y = nk.Array([[0], [1], [1], [0]])
```
```python
network = nk.Network(
nk.Input(2),
(
nk.Hidden(3, nk.Tanh),
nk.Hidden(2, nk.Sigmoid)
),
nk.Output(1)
)
```
```python
network.train(x, y, epoch=500)
print(network.predict(x)
```
```javascript
/* Output (800ms Average):
>>> Epoch: 0, Error: 0.4984800733120248
>>> Epoch: 50, Error: 0.49632395442760113
>>> Epoch: 100, Error: 0.4781823668945816
>>> Epoch: 150, Error: 0.35665153383154413
>>> Epoch: 200, Error: 0.1874969659672475
>>> Epoch: 250, Error: 0.12789399797698137
>>> Epoch: 300, Error: 0.10069853802998781
>>> Epoch: 350, Error: 0.08495289503359527
>>> Epoch: 400, Error: 0.07452557528756484
>>> Epoch: 450, Error: 0.06702276126613768
[[0.10447174]
[0.94106133]
[0.94096653]
[0.02281434]]
*/
```
# All activations:
```javascript
/*
"Sigmoid",
"Tanh",
"ReLU",
"LeakyReLU",
"ELU",
"Swish",
"Gaussion",
"Identity",
"BinaryStep",
"PReLU",
"Exponential",
"Softplus",
"Softsign",
"BentIdentity",
"ArcTan",
"SiLU",
"Mish",
"HardSigmoid",
"HardTanh",
"SoftExponential",
"ISRU",
"Sine",
"Cosine",
"SQNL",
"SoftClipping",
"BentIdentity2",
"LogLog",
"GELU",
"Softmin",
*/
```
# Make your own!
```python
import netwk as nk
class MyModule(nk.Module):
def __init__(self, *args, **kwargs):
super().__init__("MyModule", *args, **kwargs)
def forward(self, x):
return x
def backward(self, x, y, outputs):
return nk.np.ones_like(x)
```
# Seeing used modules + seed.
```python
import netwk as nk
...Defining A Neural Network Here...
print(nk.modules())
```
```javascript
/* Example:
{'Input': Input(size: 2), 'Hidden': Hidden(size: 2), 'Output': Output(size: 1), 'Network': Network(
Input Layer:
1 Input(size: 2)
Hidden Layers:
1 Hidden(size: 3)
2 Hidden(size: 2)
Output Layer:
1 Output(size: 1)
)}
*/
```
```python
print(nk.seed())
# print(nk.seed(34))
```
```javascript
/* Example:
0
# 34
*/
```
Raw data
{
"_id": null,
"home_page": "https://github.com/flowa-ai/netwk",
"name": "netwk",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": "",
"keywords": "network,machine learning,ai,neural network",
"author": "flowa.ai",
"author_email": "flowa.dev@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/b5/68/1d390f04cc6c474c374e3a50e12e201a49cce94eaecec4fffed96b65d849/netwk-2.12.5.tar.gz",
"platform": null,
"description": "<div align=\"center\"><a href=\"[https://i.ibb.co/cTyQysp/netwk-back-modified.png](https://i.ibb.co/cTyQysp/netwk-back-modified.png)\"><img src=\"https://i.ibb.co/cTyQysp/netwk-back-modified.png\" alt=\"flowa\" border=\"0\" width=\"430\"></a></div>\n\n# [netkw - Neural Network Toolkit](https://pypi.org/project/netwk)\n[](https://github.com/flowa-ai/netwk/blob/master/LICENSE)\n[](https://www.python.org/downloads/)\n\n```\nnetwk: (V2.12.5)\n\nCreate fast, optimized, and easy-to-use neural networks.\n```\n\n## Installing\n```shell\n# Linux/macOS\npython3 pip install -U netwk\n\n# Windows\npy -3 -m pip install -U netwk\n```\n\n### FastFix:\n```diff\n+ Made it so for hidden layers, you can have just one layer, in or not in a list/tuple.\n```\n\n# Usage\n```python\nimport netwk as nk\n\nnk.Seed(52) # Optional, used for testing purposes.\n\nx = nk.Array([[0, 0], [0, 1], [1, 0], [1, 1]])\ny = nk.Array([[0], [1], [1], [0]])\n```\n```python\nnetwork = nk.Network(\n nk.Input(2),\n (\n nk.Hidden(3, nk.Tanh), \n nk.Hidden(2, nk.Sigmoid)\n ),\n nk.Output(1)\n)\n```\n```python\nnetwork.train(x, y, epoch=500)\nprint(network.predict(x)\n```\n```javascript\n/* Output (800ms Average):\n>>> Epoch: 0, Error: 0.4984800733120248\n>>> Epoch: 50, Error: 0.49632395442760113\n>>> Epoch: 100, Error: 0.4781823668945816\n>>> Epoch: 150, Error: 0.35665153383154413\n>>> Epoch: 200, Error: 0.1874969659672475\n>>> Epoch: 250, Error: 0.12789399797698137\n>>> Epoch: 300, Error: 0.10069853802998781\n>>> Epoch: 350, Error: 0.08495289503359527\n>>> Epoch: 400, Error: 0.07452557528756484\n>>> Epoch: 450, Error: 0.06702276126613768\n[[0.10447174]\n [0.94106133]\n [0.94096653]\n [0.02281434]]\n*/\n```\n\n# All activations:\n```javascript\n/*\n \"Sigmoid\",\n \"Tanh\",\n \"ReLU\",\n \"LeakyReLU\",\n \"ELU\",\n \"Swish\",\n \"Gaussion\",\n \"Identity\",\n \"BinaryStep\",\n \"PReLU\",\n \"Exponential\",\n \"Softplus\",\n \"Softsign\",\n \"BentIdentity\",\n \"ArcTan\",\n \"SiLU\",\n \"Mish\",\n \"HardSigmoid\",\n \"HardTanh\",\n \"SoftExponential\",\n \"ISRU\",\n \"Sine\",\n \"Cosine\",\n \"SQNL\",\n \"SoftClipping\",\n \"BentIdentity2\",\n \"LogLog\",\n \"GELU\",\n \"Softmin\",\n*/\n```\n\n# Make your own!\n```python\nimport netwk as nk\n\nclass MyModule(nk.Module):\n def __init__(self, *args, **kwargs):\n super().__init__(\"MyModule\", *args, **kwargs)\n\n def forward(self, x):\n return x\n\n def backward(self, x, y, outputs):\n return nk.np.ones_like(x)\n```\n\n# Seeing used modules + seed.\n```python\nimport netwk as nk\n\n...Defining A Neural Network Here...\n\nprint(nk.modules())\n```\n```javascript\n/* Example:\n{'Input': Input(size: 2), 'Hidden': Hidden(size: 2), 'Output': Output(size: 1), 'Network': Network(\n Input Layer:\n 1 Input(size: 2)\n\n Hidden Layers: \n 1 Hidden(size: 3)\n 2 Hidden(size: 2)\n\n Output Layer:\n 1 Output(size: 1)\n)}\n*/\n```\n```python\nprint(nk.seed())\n# print(nk.seed(34))\n```\n```javascript\n/* Example:\n0\n# 34\n*/\n```\n",
"bugtrack_url": null,
"license": "",
"summary": "Create fast, optimized, and easy-to-use neural networks.",
"version": "2.12.5",
"project_urls": {
"Homepage": "https://github.com/flowa-ai/netwk"
},
"split_keywords": [
"network",
"machine learning",
"ai",
"neural network"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "19d9c3e10977f7ca8fe5355c7207805a2ae3a29f3dacbd0f3a2f035b814a9441",
"md5": "ce5b2400e0c6e3f31143bb228f66cfe9",
"sha256": "2201b9cb9f632dd7754683cbcdc57a3e93a752f6117d6be21c422277489a5841"
},
"downloads": -1,
"filename": "netwk-2.12.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "ce5b2400e0c6e3f31143bb228f66cfe9",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 7323,
"upload_time": "2023-12-17T17:08:09",
"upload_time_iso_8601": "2023-12-17T17:08:09.899103Z",
"url": "https://files.pythonhosted.org/packages/19/d9/c3e10977f7ca8fe5355c7207805a2ae3a29f3dacbd0f3a2f035b814a9441/netwk-2.12.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "b5681d390f04cc6c474c374e3a50e12e201a49cce94eaecec4fffed96b65d849",
"md5": "d8810b030f05194b15668f1a1f3e6bcc",
"sha256": "2f0e9f146d00270290f1c6859f1f82003ae6c0fcc9e0e512ee01320014ab2466"
},
"downloads": -1,
"filename": "netwk-2.12.5.tar.gz",
"has_sig": false,
"md5_digest": "d8810b030f05194b15668f1a1f3e6bcc",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 6332,
"upload_time": "2023-12-17T17:08:11",
"upload_time_iso_8601": "2023-12-17T17:08:11.139652Z",
"url": "https://files.pythonhosted.org/packages/b5/68/1d390f04cc6c474c374e3a50e12e201a49cce94eaecec4fffed96b65d849/netwk-2.12.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-12-17 17:08:11",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "flowa-ai",
"github_project": "netwk",
"github_not_found": true,
"lcname": "netwk"
}
JSON
