Skip to main content

A simple tensorflow wrapper.

Project description

Zeras

A simple tensorflow wrapper

Description

from Zeras.data_parallelism import DataParallelism, get_files_with_ext
from Zeras.data_batcher import DataBatcher

from Zeras.model_settings_baseboard import ModelSettingsBaseboard
from Zeras.model_baseboard import ModelBaseboard, initialize_with_pretrained_ckpt

from Zeras.optim import linear_warmup_and_exp_decayed_lr
from Zeras.optim import linear_warmup_and_polynomial_decayed_lr
from Zeras.optim import adam_optimizer
from Zeras.optim import adam_wd_optimizer
from Zeras.optim import AdamWeightDecayOptimizer

import Zeras.zoo_nn as zrs_nn
import Zeras.zoo_layers as zrs_layers

from Zeras.vocab import Vocab

Installation

From PyPI distribution system:

pip install Zeras

Or from the code:

git clone https://github.com/Li-Ming-Fan/Zeras
cd Zeras
make clean install

Or just incorporate the directory Zeras/ to your project.

Usage

For usage of this package, please refer to the repositories:

https://github.com/Li-Ming-Fan/text_classification

https://github.com/Li-Ming-Fan/transformer-tensorflow

https://github.com/Li-Ming-Fan/pointer-generator-refactored


Acknowledgment

The name "Zeras" is a variant from Keras. We use "Z" because it makes the direcory Zeras/ always display in the last (or first) and do not intersect other directories.

Project details


Download files

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

Files for Zeras, version 0.4.3
Filename, size File type Python version Upload date Hashes
Filename, size Zeras-0.4.3.tar.gz (23.2 kB) File type Source Python version None Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page