Skip to main content

ZenGrad Optimizer - Pytorch

Project description

Installation

To install ZenGrad, run the following command:

pip install zengrad-pytorch

Implementation

import torch
from zengrad_pytorch import ZenGrad  # Custom optimizer

# Define the model

# Instantiate the model
model = SimpleModel()

# Define loss function
criterion = nn.CrossEntropyLoss()

# Instantiate optimizer
optimizer = ZenGrad(model.parameters(), lr=0.01, weight_decay=1e-4, epsilon=1e-8) # <---- In This Way

# Model summary (optional)
print(model)

License

ZenGrad_pytorch is released under the Apache License 2.0.

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

zengrad_pytorch-0.0.1.tar.gz (2.5 kB view details)

Uploaded Source

Built Distribution

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

zengrad_pytorch-0.0.1-py3-none-any.whl (2.8 kB view details)

Uploaded Python 3

File details

Details for the file zengrad_pytorch-0.0.1.tar.gz.

File metadata

  • Download URL: zengrad_pytorch-0.0.1.tar.gz
  • Upload date:
  • Size: 2.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.4

File hashes

Hashes for zengrad_pytorch-0.0.1.tar.gz
Algorithm Hash digest
SHA256 2cd7c3a6ccf15a26b34b15540e3ea8e00dd7bbc330ed192ba116ca66b36b105f
MD5 68c6e057dc383890c604ee4818cb8ec7
BLAKE2b-256 8215d54b8ef0d268acc67b603b5b003b5cd952a38e57792a5f4cb3487d63a0a0

See more details on using hashes here.

File details

Details for the file zengrad_pytorch-0.0.1-py3-none-any.whl.

File metadata

File hashes

Hashes for zengrad_pytorch-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 d202175601d2fd52905e12cba900a8af7f9674901eadbea34708a0b8ebd99c21
MD5 8ed7745400fbf1795142db44e86c4849
BLAKE2b-256 71b9e2f2e3145ba62602853909ec36ecd36c512e53989284a08e63619368605a

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