NLP text processing toolkit for Deep Learning
Project description
FERN
Fern用于NLP的模型开发结构控制。通过它可以控制文本预处理、模型搭建、训练器:
- 文本预处理:数据下载、数据清洗、数据转换和数据分割
- 模型搭建:模型保存与加载、模型架构打印
- 模型训练:单步/epoch训练与评估、评估函数设置、损失函数设置、label权重设置
Fern的设计目的主要为了解决不同NLP工程中重复代码过多问题,减少流程性代码,从而避免数据交互过程中的随机bug出现
安装
-
从
pypi
安装$ pip install Fern2
-
从源码安装
$ pip install -e git+https://github.com/Jasonsey/Fern.git
使用教程
建议查看源码中函数的使用说明
变量命名规则
为了方便定义,对容易分歧变量命名做如下约定:
-
对于数据变量,同类型变量书写规则:
data_train
,data_val
label_train
,label_val
-
对于指标变量,同类型变量书写规则:
val_loss
,val_acc
,val_binary_acc
train_loss
,train_acc
-
对于其他变量,按照
首先它属于a, 其次它属于b
规则命名变量名:a_b
path_dataset
TODO
- BERT预训练模型直接调用
- BERT重现训练代码直接调用
版本变更日志
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Fern2-1.2.0.tar.gz
(26.7 kB
view details)
Built Distribution
Fern2-1.2.0-py3-none-any.whl
(32.7 kB
view details)
File details
Details for the file Fern2-1.2.0.tar.gz
.
File metadata
- Download URL: Fern2-1.2.0.tar.gz
- Upload date:
- Size: 26.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | eae00c38138a7993c1ecb14ac94aa93b8d8cbe15bfee74913c900e8de2dd7fea |
|
MD5 | bae3eb17ca392392884324273f930540 |
|
BLAKE2b-256 | 7ef8dd97b9af82a2bff329d39f67ad68364fb06092b360981c907357a1856d1f |
File details
Details for the file Fern2-1.2.0-py3-none-any.whl
.
File metadata
- Download URL: Fern2-1.2.0-py3-none-any.whl
- Upload date:
- Size: 32.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 675078e39b91685e3ba3dd2922cef06309baaa07af883294f86b32ade31aaba4 |
|
MD5 | 2c39c0fa25c08ca843a6b93e1f61360c |
|
BLAKE2b-256 | 86ec47eb61e376656b466d46d33aa9a9968256cbbfa9703c9fe92c76dd7a0634 |