Skip to main content

parallel neural network layer for binarization of ternarization - quantized layers from the beginning

Project description

plinear

Github for parrallel - linear layer

You can install PLinear using pip:

pip install plinear

Example usage

import torch
import torch.nn as nn
import plinear
import plinear.btnn as btnn

class SimpleNN(nn.Module):
    def __init__(self):
        super(SimpleNN, self).__init__()
        self.fc1 = btnn.linear(28*28, 128)
        self.fc2 = btnn.linear(128, 10)

    def forward(self, x):
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = self.fc2(x)
        return x

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

plinear-0.2.0.0.tar.gz (3.7 kB view details)

Uploaded Source

Built Distribution

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

plinear-0.2.0.0-py3-none-any.whl (5.4 kB view details)

Uploaded Python 3

File details

Details for the file plinear-0.2.0.0.tar.gz.

File metadata

  • Download URL: plinear-0.2.0.0.tar.gz
  • Upload date:
  • Size: 3.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.5 CPython/3.13.1 Darwin/23.6.0

File hashes

Hashes for plinear-0.2.0.0.tar.gz
Algorithm Hash digest
SHA256 b72349207aa7ccd7e97545cff3c84ad83e6aa3832fe9dce18d5d557121a54219
MD5 12156ffb6060e4488621203bd7ffda54
BLAKE2b-256 39ed952b96968a5842f6a4227abf19ed60ad369fa0fc1cce9096c282d80417ba

See more details on using hashes here.

File details

Details for the file plinear-0.2.0.0-py3-none-any.whl.

File metadata

  • Download URL: plinear-0.2.0.0-py3-none-any.whl
  • Upload date:
  • Size: 5.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.5 CPython/3.13.1 Darwin/23.6.0

File hashes

Hashes for plinear-0.2.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ca7273c7ddc720ba9250c4423d95d89f40590977b6e0d6ff4b73d55574f5c8f0
MD5 8de283797424a3a95d039f1a03b14d26
BLAKE2b-256 1a933a5e06e84d3cb117bafb0347d36a4339f1bd0a94c3b209b47a7be92e23d6

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