Skip to main content

Something between Tinygrad and Micrograd

Project description

Robingrad


Maintenance stability-wip

Something between Tinygrad and Micrograd.

Installation

To install the current release,

pip install robingrad==0.1.0

From source

git clone https://github.com/marcosalvalaggio/robingrad.git
cd robingrad
./build.sh

Examples

  • In the examples folder, you can find examples of models trained using the Robingrad library.
  • A declaration example of an MLP net using Robingrad:
from robingrad import Tensor, draw_dot
import robingrad.nn as nn

class RobinNet:
    def __init__(self):
        self.l1 = nn.Linear(5,16)
        self.l2 = nn.Linear(16,1)
    def __call__(self, x):
        x = self.l1(x)
        x = x.relu()
        x = self.l2(x)
        return x
        
model = RobinNet()
res = model(X_train[0].reshape((1,5)))
draw_dot(res)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

robingrad-0.1.0.tar.gz (10.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

robingrad-0.1.0-py3-none-any.whl (10.3 kB view details)

Uploaded Python 3

File details

Details for the file robingrad-0.1.0.tar.gz.

File metadata

  • Download URL: robingrad-0.1.0.tar.gz
  • Upload date:
  • Size: 10.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.12

File hashes

Hashes for robingrad-0.1.0.tar.gz
Algorithm Hash digest
SHA256 95681ee940d6fb1f32a45f785c5eeb60936b170e3e1d53cf18f474042a178ab4
MD5 effcf5c4da446639e57c37dfc86beef0
BLAKE2b-256 9891f1974082093ba7694ffa118f78cf6342f69d6c9f0f378d982ab8bedb3550

See more details on using hashes here.

File details

Details for the file robingrad-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: robingrad-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 10.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.12

File hashes

Hashes for robingrad-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ba2c932e0c300a73ad4cb05367793503361d7acda5e4adb4ba757d268fa36966
MD5 62558525d89eb2602301b60651123082
BLAKE2b-256 f1a46c5f6062dc461efb4e54f8a6e4dd31410d867b7874917d8dbba9d27d8c63

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page