@@ -1,7 +0,0 @@ | |||
fastNLP.component.bert\_tokenizer module | |||
======================================== | |||
.. automodule:: fastNLP.component.bert_tokenizer | |||
:members: | |||
:undoc-members: | |||
:show-inheritance: |
@@ -1,15 +0,0 @@ | |||
fastNLP.component package | |||
========================= | |||
.. automodule:: fastNLP.component | |||
:members: | |||
:undoc-members: | |||
:show-inheritance: | |||
Submodules | |||
---------- | |||
.. toctree:: | |||
fastNLP.component.bert_tokenizer | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.core.batch module | |||
========================= | |||
fastNLP.core.batch | |||
================== | |||
.. automodule:: fastNLP.core.batch | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.core.callback module | |||
============================ | |||
fastNLP.core.callback | |||
===================== | |||
.. automodule:: fastNLP.core.callback | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.core.const module | |||
========================= | |||
fastNLP.core.const | |||
================== | |||
.. automodule:: fastNLP.core.const | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.core.dataset module | |||
=========================== | |||
fastNLP.core.dataset | |||
==================== | |||
.. automodule:: fastNLP.core.dataset | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.core.field module | |||
========================= | |||
fastNLP.core.field | |||
================== | |||
.. automodule:: fastNLP.core.field | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.core.instance module | |||
============================ | |||
fastNLP.core.instance | |||
===================== | |||
.. automodule:: fastNLP.core.instance | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.core.losses module | |||
========================== | |||
fastNLP.core.losses | |||
=================== | |||
.. automodule:: fastNLP.core.losses | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.core.metrics module | |||
=========================== | |||
fastNLP.core.metrics | |||
==================== | |||
.. automodule:: fastNLP.core.metrics | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.core.optimizer module | |||
============================= | |||
fastNLP.core.optimizer | |||
====================== | |||
.. automodule:: fastNLP.core.optimizer | |||
:members: | |||
@@ -1,15 +1,16 @@ | |||
fastNLP.core package | |||
==================== | |||
fastNLP.core | |||
============ | |||
.. automodule:: fastNLP.core | |||
:members: | |||
:undoc-members: | |||
:show-inheritance: | |||
Submodules | |||
子模块 | |||
---------- | |||
.. toctree:: | |||
:titlesonly: | |||
fastNLP.core.batch | |||
fastNLP.core.callback | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.core.sampler module | |||
=========================== | |||
fastNLP.core.sampler | |||
==================== | |||
.. automodule:: fastNLP.core.sampler | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.core.tester module | |||
========================== | |||
fastNLP.core.tester | |||
=================== | |||
.. automodule:: fastNLP.core.tester | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.core.trainer module | |||
=========================== | |||
fastNLP.core.trainer | |||
==================== | |||
.. automodule:: fastNLP.core.trainer | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.core.utils module | |||
========================= | |||
fastNLP.core.utils | |||
================== | |||
.. automodule:: fastNLP.core.utils | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.core.vocabulary module | |||
============================== | |||
fastNLP.core.vocabulary | |||
======================= | |||
.. automodule:: fastNLP.core.vocabulary | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.io.base\_loader module | |||
============================== | |||
fastNLP.io.base\_loader | |||
======================= | |||
.. automodule:: fastNLP.io.base_loader | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.io.dataset\_loader module | |||
================================= | |||
fastNLP.io.dataset\_loader | |||
========================== | |||
.. automodule:: fastNLP.io.dataset_loader | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.io.embed\_loader module | |||
=============================== | |||
fastNLP.io.embed\_loader | |||
======================== | |||
.. automodule:: fastNLP.io.embed_loader | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.io.model\_io module | |||
=========================== | |||
fastNLP.io.model\_io | |||
==================== | |||
.. automodule:: fastNLP.io.model_io | |||
:members: | |||
@@ -1,15 +1,16 @@ | |||
fastNLP.io package | |||
================== | |||
fastNLP.io | |||
========== | |||
.. automodule:: fastNLP.io | |||
:members: | |||
:undoc-members: | |||
:show-inheritance: | |||
Submodules | |||
子模块 | |||
---------- | |||
.. toctree:: | |||
:titlesonly: | |||
fastNLP.io.base_loader | |||
fastNLP.io.dataset_loader | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.models.base\_model module | |||
================================= | |||
fastNLP.models.base\_model | |||
========================== | |||
.. automodule:: fastNLP.models.base_model | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.models.bert module | |||
========================== | |||
fastNLP.models.bert | |||
=================== | |||
.. automodule:: fastNLP.models.bert | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.models.biaffine\_parser module | |||
====================================== | |||
fastNLP.models.biaffine\_parser | |||
=============================== | |||
.. automodule:: fastNLP.models.biaffine_parser | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.models.cnn\_text\_classification module | |||
=============================================== | |||
fastNLP.models.cnn\_text\_classification | |||
======================================== | |||
.. automodule:: fastNLP.models.cnn_text_classification | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.models.enas\_controller module | |||
====================================== | |||
fastNLP.models.enas\_controller | |||
=============================== | |||
.. automodule:: fastNLP.models.enas_controller | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.models.enas\_model module | |||
================================= | |||
fastNLP.models.enas\_model | |||
========================== | |||
.. automodule:: fastNLP.models.enas_model | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.models.enas\_trainer module | |||
=================================== | |||
fastNLP.models.enas\_trainer | |||
============================ | |||
.. automodule:: fastNLP.models.enas_trainer | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.models.enas\_utils module | |||
================================= | |||
fastNLP.models.enas\_utils | |||
========================== | |||
.. automodule:: fastNLP.models.enas_utils | |||
:members: | |||
@@ -1,15 +1,16 @@ | |||
fastNLP.models package | |||
====================== | |||
fastNLP.models | |||
============== | |||
.. automodule:: fastNLP.models | |||
:members: | |||
:undoc-members: | |||
:show-inheritance: | |||
Submodules | |||
子模块 | |||
---------- | |||
.. toctree:: | |||
:titlesonly: | |||
fastNLP.models.base_model | |||
fastNLP.models.bert | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.models.sequence\_labeling module | |||
======================================== | |||
fastNLP.models.sequence\_labeling | |||
================================= | |||
.. automodule:: fastNLP.models.sequence_labeling | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.models.snli module | |||
========================== | |||
fastNLP.models.snli | |||
=================== | |||
.. automodule:: fastNLP.models.snli | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.models.star\_transformer module | |||
======================================= | |||
fastNLP.models.star\_transformer | |||
================================ | |||
.. automodule:: fastNLP.models.star_transformer | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.modules.aggregator.attention module | |||
=========================================== | |||
fastNLP.modules.aggregator.attention | |||
==================================== | |||
.. automodule:: fastNLP.modules.aggregator.attention | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.modules.aggregator.pooling module | |||
========================================= | |||
fastNLP.modules.aggregator.pooling | |||
================================== | |||
.. automodule:: fastNLP.modules.aggregator.pooling | |||
:members: | |||
@@ -1,15 +1,16 @@ | |||
fastNLP.modules.aggregator package | |||
================================== | |||
fastNLP.modules.aggregator | |||
========================== | |||
.. automodule:: fastNLP.modules.aggregator | |||
:members: | |||
:undoc-members: | |||
:show-inheritance: | |||
Submodules | |||
子模块 | |||
---------- | |||
.. toctree:: | |||
:titlesonly: | |||
fastNLP.modules.aggregator.attention | |||
fastNLP.modules.aggregator.pooling | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.modules.decoder.CRF module | |||
================================== | |||
fastNLP.modules.decoder.CRF | |||
=========================== | |||
.. automodule:: fastNLP.modules.decoder.CRF | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.modules.decoder.MLP module | |||
================================== | |||
fastNLP.modules.decoder.MLP | |||
=========================== | |||
.. automodule:: fastNLP.modules.decoder.MLP | |||
:members: | |||
@@ -1,15 +1,16 @@ | |||
fastNLP.modules.decoder package | |||
=============================== | |||
fastNLP.modules.decoder | |||
======================= | |||
.. automodule:: fastNLP.modules.decoder | |||
:members: | |||
:undoc-members: | |||
:show-inheritance: | |||
Submodules | |||
子模块 | |||
---------- | |||
.. toctree:: | |||
:titlesonly: | |||
fastNLP.modules.decoder.CRF | |||
fastNLP.modules.decoder.MLP | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.modules.decoder.utils module | |||
==================================== | |||
fastNLP.modules.decoder.utils | |||
============================= | |||
.. automodule:: fastNLP.modules.decoder.utils | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.modules.encoder.bert module | |||
=================================== | |||
fastNLP.modules.encoder.bert | |||
============================ | |||
.. automodule:: fastNLP.modules.encoder.bert | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.modules.encoder.char\_encoder module | |||
============================================ | |||
fastNLP.modules.encoder.char\_encoder | |||
===================================== | |||
.. automodule:: fastNLP.modules.encoder.char_encoder | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.modules.encoder.conv\_maxpool module | |||
============================================ | |||
fastNLP.modules.encoder.conv\_maxpool | |||
===================================== | |||
.. automodule:: fastNLP.modules.encoder.conv_maxpool | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.modules.encoder.embedding module | |||
======================================== | |||
fastNLP.modules.encoder.embedding | |||
================================= | |||
.. automodule:: fastNLP.modules.encoder.embedding | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.modules.encoder.lstm module | |||
=================================== | |||
fastNLP.modules.encoder.lstm | |||
============================ | |||
.. automodule:: fastNLP.modules.encoder.lstm | |||
:members: | |||
@@ -1,15 +1,16 @@ | |||
fastNLP.modules.encoder package | |||
=============================== | |||
fastNLP.modules.encoder | |||
======================= | |||
.. automodule:: fastNLP.modules.encoder | |||
:members: | |||
:undoc-members: | |||
:show-inheritance: | |||
Submodules | |||
子模块 | |||
---------- | |||
.. toctree:: | |||
:titlesonly: | |||
fastNLP.modules.encoder.bert | |||
fastNLP.modules.encoder.char_encoder | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.modules.encoder.star\_transformer module | |||
================================================ | |||
fastNLP.modules.encoder.star\_transformer | |||
========================================= | |||
.. automodule:: fastNLP.modules.encoder.star_transformer | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.modules.encoder.transformer module | |||
========================================== | |||
fastNLP.modules.encoder.transformer | |||
=================================== | |||
.. automodule:: fastNLP.modules.encoder.transformer | |||
:members: | |||
@@ -1,5 +1,5 @@ | |||
fastNLP.modules.encoder.variational\_rnn module | |||
=============================================== | |||
fastNLP.modules.encoder.variational\_rnn | |||
======================================== | |||
.. automodule:: fastNLP.modules.encoder.variational_rnn | |||
:members: | |||
@@ -1,15 +1,16 @@ | |||
fastNLP.modules package | |||
======================= | |||
fastNLP.modules | |||
=============== | |||
.. automodule:: fastNLP.modules | |||
:members: | |||
:undoc-members: | |||
:show-inheritance: | |||
Subpackages | |||
子模块 | |||
----------- | |||
.. toctree:: | |||
:titlesonly: | |||
fastNLP.modules.aggregator | |||
fastNLP.modules.decoder |
@@ -1,4 +1,4 @@ | |||
fastNLP package | |||
API 文档 | |||
=============== | |||
.. automodule:: fastNLP | |||
@@ -6,14 +6,15 @@ fastNLP package | |||
:undoc-members: | |||
:show-inheritance: | |||
Subpackages | |||
内部模块 | |||
----------- | |||
.. toctree:: | |||
:titlesonly: | |||
:maxdepth: 3 | |||
fastNLP.component | |||
fastNLP.core | |||
fastNLP.io | |||
fastNLP.models | |||
fastNLP.modules | |||
fastNLP.models | |||
@@ -12,19 +12,21 @@ fastNLP 是一款轻量级的 NLP 处理套件。你既可以使用它快速地 | |||
- 便捷且具有扩展性的训练器; 提供多种内置callback函数,方便实验记录、异常捕获等。 | |||
内置的模块 | |||
内置组件 | |||
------------ | |||
(TODO) | |||
大部分用于的 NLP 任务神经网络都可以看做由编码(encoder)、聚合(aggregator)、解码(decoder)三种模块组成。 | |||
.. image:: figures/text_classification.png | |||
主要包含了以下的三大模块: | |||
fastNLP 在 :mod:`~fastNLP.modules` 模块中内置了三种模块的诸多组件,可以帮助用户快速搭建自己所需的网络。 | |||
三种模块的功能和常见组件如下: | |||
+-----------------------+-----------------------+-----------------------+ | |||
| module type | functionality | example | | |||
+=======================+=======================+=======================+ | |||
| encoder | 将输入编码为具有具 | embedding, RNN, CNN, | | |||
| | 有表示能力的向量 | transformer | | |||
| | 有表示能力的向量 | transformer | | |||
+-----------------------+-----------------------+-----------------------+ | |||
| aggregator | 从多个向量中聚合信息 | self-attention, | | |||
| | | max-pooling | | |||
@@ -35,32 +37,24 @@ fastNLP 是一款轻量级的 NLP 处理套件。你既可以使用它快速地 | |||
+-----------------------+-----------------------+-----------------------+ | |||
For example: | |||
.. image:: figures/text_classification.png | |||
各个任务上的结果 | |||
----------------------- | |||
(TODO) | |||
快速入门 | |||
------------- | |||
内置模型 | |||
---------------- | |||
TODO | |||
fastNLP 在 :mod:`~fastNLP.models` 模块中内置了如 :class:`~fastNLP.models.CNNText` 、 | |||
:class:`~fastNLP.models.SeqLabeling` 等完整的模型,以供用户直接使用。 | |||
.. todo:: | |||
这些模型的介绍如下表所示:(模型名称 + 介绍 + 任务上的结果) | |||
用户手册 | |||
--------------- | |||
---------------- | |||
.. toctree:: | |||
:maxdepth: 1 | |||
安装指南 <user/installation> | |||
快速入门 <user/quickstart> | |||
详细指南 <user/tutorials> | |||
详细指南 <user/tutorial_one> | |||
科研向导 <user/with_fitlog> | |||
@@ -70,7 +64,7 @@ API 文档 | |||
除了用户手册之外,你还可以通过查阅 API 文档来找到你所需要的工具。 | |||
.. toctree:: | |||
:maxdepth: 2 | |||
:titlesonly: | |||
fastNLP | |||
@@ -2,6 +2,7 @@ fastNLP | |||
======= | |||
.. toctree:: | |||
:titlesonly: | |||
:maxdepth: 4 | |||
fastNLP |
@@ -1,376 +0,0 @@ | |||
fastNLP 10分钟上手教程 | |||
=============== | |||
教程原文见 https://github.com/fastnlp/fastNLP/blob/master/tutorials/fastnlp_10min_tutorial.ipynb | |||
fastNLP提供方便的数据预处理,训练和测试模型的功能 | |||
DataSet & Instance | |||
------------------ | |||
fastNLP用DataSet和Instance保存和处理数据。每个DataSet表示一个数据集,每个Instance表示一个数据样本。一个DataSet存有多个Instance,每个Instance可以自定义存哪些内容。 | |||
有一些read\_\*方法,可以轻松从文件读取数据,存成DataSet。 | |||
.. code:: ipython3 | |||
from fastNLP import DataSet | |||
from fastNLP import Instance | |||
# 从csv读取数据到DataSet | |||
win_path = "C:\\Users\zyfeng\Desktop\FudanNLP\\fastNLP\\test\\data_for_tests\\tutorial_sample_dataset.csv" | |||
dataset = DataSet.read_csv(win_path, headers=('raw_sentence', 'label'), sep='\t') | |||
print(dataset[0]) | |||
.. parsed-literal:: | |||
{'raw_sentence': A series of escapades demonstrating the adage that what is good for the goose is also good for the gander , some of which occasionally amuses but none of which amounts to much of a story ., | |||
'label': 1} | |||
.. code:: ipython3 | |||
# DataSet.append(Instance)加入新数据 | |||
dataset.append(Instance(raw_sentence='fake data', label='0')) | |||
dataset[-1] | |||
.. parsed-literal:: | |||
{'raw_sentence': fake data, | |||
'label': 0} | |||
.. code:: ipython3 | |||
# DataSet.apply(func, new_field_name)对数据预处理 | |||
# 将所有数字转为小写 | |||
dataset.apply(lambda x: x['raw_sentence'].lower(), new_field_name='raw_sentence') | |||
# label转int | |||
dataset.apply(lambda x: int(x['label']), new_field_name='label_seq', is_target=True) | |||
# 使用空格分割句子 | |||
dataset.drop(lambda x: len(x['raw_sentence'].split()) == 0) | |||
def split_sent(ins): | |||
return ins['raw_sentence'].split() | |||
dataset.apply(split_sent, new_field_name='words', is_input=True) | |||
.. code:: ipython3 | |||
# DataSet.drop(func)筛除数据 | |||
# 删除低于某个长度的词语 | |||
dataset.drop(lambda x: len(x['words']) <= 3) | |||
.. code:: ipython3 | |||
# 分出测试集、训练集 | |||
test_data, train_data = dataset.split(0.3) | |||
print("Train size: ", len(test_data)) | |||
print("Test size: ", len(train_data)) | |||
.. parsed-literal:: | |||
Train size: 54 | |||
Test size: | |||
Vocabulary | |||
---------- | |||
fastNLP中的Vocabulary轻松构建词表,将词转成数字 | |||
.. code:: ipython3 | |||
from fastNLP import Vocabulary | |||
# 构建词表, Vocabulary.add(word) | |||
vocab = Vocabulary(min_freq=2) | |||
train_data.apply(lambda x: [vocab.add(word) for word in x['words']]) | |||
vocab.build_vocab() | |||
# index句子, Vocabulary.to_index(word) | |||
train_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='word_seq', is_input=True) | |||
test_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='word_seq', is_input=True) | |||
print(test_data[0]) | |||
.. parsed-literal:: | |||
{'raw_sentence': the plot is romantic comedy boilerplate from start to finish ., | |||
'label': 2, | |||
'label_seq': 2, | |||
'words': ['the', 'plot', 'is', 'romantic', 'comedy', 'boilerplate', 'from', 'start', 'to', 'finish', '.'], | |||
'word_seq': [2, 13, 9, 24, 25, 26, 15, 27, 11, 28, 3]} | |||
.. code:: ipython3 | |||
# 假设你们需要做强化学习或者gan之类的项目,也许你们可以使用这里的dataset | |||
from fastNLP.core.batch import Batch | |||
from fastNLP.core.sampler import RandomSampler | |||
batch_iterator = Batch(dataset=train_data, batch_size=2, sampler=RandomSampler()) | |||
for batch_x, batch_y in batch_iterator: | |||
print("batch_x has: ", batch_x) | |||
print("batch_y has: ", batch_y) | |||
break | |||
.. parsed-literal:: | |||
batch_x has: {'words': array([list(['this', 'kind', 'of', 'hands-on', 'storytelling', 'is', 'ultimately', 'what', 'makes', 'shanghai', 'ghetto', 'move', 'beyond', 'a', 'good', ',', 'dry', ',', 'reliable', 'textbook', 'and', 'what', 'allows', 'it', 'to', 'rank', 'with', 'its', 'worthy', 'predecessors', '.']), | |||
list(['the', 'entire', 'movie', 'is', 'filled', 'with', 'deja', 'vu', 'moments', '.'])], | |||
dtype=object), 'word_seq': tensor([[ 19, 184, 6, 1, 481, 9, 206, 50, 91, 1210, 1609, 1330, | |||
495, 5, 63, 4, 1269, 4, 1, 1184, 7, 50, 1050, 10, | |||
8, 1611, 16, 21, 1039, 1, 2], | |||
[ 3, 711, 22, 9, 1282, 16, 2482, 2483, 200, 2, 0, 0, | |||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, | |||
0, 0, 0, 0, 0, 0, 0]])} | |||
batch_y has: {'label_seq': tensor([3, 2])} | |||
Model | |||
----- | |||
.. code:: ipython3 | |||
# 定义一个简单的Pytorch模型 | |||
from fastNLP.models import CNNText | |||
model = CNNText(embed_num=len(vocab), embed_dim=50, num_classes=5, padding=2, dropout=0.1) | |||
model | |||
.. parsed-literal:: | |||
CNNText( | |||
(embed): Embedding( | |||
(embed): Embedding(77, 50, padding_idx=0) | |||
(dropout): Dropout(p=0.0) | |||
) | |||
(conv_pool): ConvMaxpool( | |||
(convs): ModuleList( | |||
(0): Conv1d(50, 3, kernel_size=(3,), stride=(1,), padding=(2,)) | |||
(1): Conv1d(50, 4, kernel_size=(4,), stride=(1,), padding=(2,)) | |||
(2): Conv1d(50, 5, kernel_size=(5,), stride=(1,), padding=(2,)) | |||
) | |||
) | |||
(dropout): Dropout(p=0.1) | |||
(fc): Linear( | |||
(linear): Linear(in_features=12, out_features=5, bias=True) | |||
) | |||
) | |||
Trainer & Tester | |||
---------------- | |||
使用fastNLP的Trainer训练模型 | |||
.. code:: ipython3 | |||
from fastNLP import Trainer | |||
from copy import deepcopy | |||
from fastNLP import CrossEntropyLoss | |||
from fastNLP import AccuracyMetric | |||
.. code:: ipython3 | |||
# 进行overfitting测试 | |||
copy_model = deepcopy(model) | |||
overfit_trainer = Trainer(model=copy_model, | |||
train_data=test_data, | |||
dev_data=test_data, | |||
loss=CrossEntropyLoss(pred="output", target="label_seq"), | |||
metrics=AccuracyMetric(), | |||
n_epochs=10, | |||
save_path=None) | |||
overfit_trainer.train() | |||
.. parsed-literal:: | |||
training epochs started 2018-12-07 14:07:20 | |||
.. parsed-literal:: | |||
HBox(children=(IntProgress(value=0, layout=Layout(flex='2'), max=20), HTML(value='')), layout=Layout(display='… | |||
.. parsed-literal:: | |||
Epoch 1/10. Step:2/20. AccuracyMetric: acc=0.037037 | |||
Epoch 2/10. Step:4/20. AccuracyMetric: acc=0.296296 | |||
Epoch 3/10. Step:6/20. AccuracyMetric: acc=0.333333 | |||
Epoch 4/10. Step:8/20. AccuracyMetric: acc=0.555556 | |||
Epoch 5/10. Step:10/20. AccuracyMetric: acc=0.611111 | |||
Epoch 6/10. Step:12/20. AccuracyMetric: acc=0.481481 | |||
Epoch 7/10. Step:14/20. AccuracyMetric: acc=0.62963 | |||
Epoch 8/10. Step:16/20. AccuracyMetric: acc=0.685185 | |||
Epoch 9/10. Step:18/20. AccuracyMetric: acc=0.722222 | |||
Epoch 10/10. Step:20/20. AccuracyMetric: acc=0.777778 | |||
.. code:: ipython3 | |||
# 实例化Trainer,传入模型和数据,进行训练 | |||
trainer = Trainer(model=model, | |||
train_data=train_data, | |||
dev_data=test_data, | |||
loss=CrossEntropyLoss(pred="output", target="label_seq"), | |||
metrics=AccuracyMetric(), | |||
n_epochs=5) | |||
trainer.train() | |||
print('Train finished!') | |||
.. parsed-literal:: | |||
training epochs started 2018-12-07 14:08:10 | |||
.. parsed-literal:: | |||
HBox(children=(IntProgress(value=0, layout=Layout(flex='2'), max=5), HTML(value='')), layout=Layout(display='i… | |||
.. parsed-literal:: | |||
Epoch 1/5. Step:1/5. AccuracyMetric: acc=0.037037 | |||
Epoch 2/5. Step:2/5. AccuracyMetric: acc=0.037037 | |||
Epoch 3/5. Step:3/5. AccuracyMetric: acc=0.037037 | |||
Epoch 4/5. Step:4/5. AccuracyMetric: acc=0.185185 | |||
Epoch 5/5. Step:5/5. AccuracyMetric: acc=0.240741 | |||
Train finished! | |||
.. code:: ipython3 | |||
from fastNLP import Tester | |||
tester = Tester(data=test_data, model=model, metrics=AccuracyMetric()) | |||
acc = tester.test() | |||
.. parsed-literal:: | |||
[tester] | |||
AccuracyMetric: acc=0.240741 | |||
In summary | |||
---------- | |||
fastNLP Trainer的伪代码逻辑 | |||
--------------------------- | |||
1. 准备DataSet,假设DataSet中共有如下的fields | |||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | |||
:: | |||
['raw_sentence', 'word_seq1', 'word_seq2', 'raw_label','label'] | |||
通过 | |||
DataSet.set_input('word_seq1', word_seq2', flag=True)将'word_seq1', 'word_seq2'设置为input | |||
通过 | |||
DataSet.set_target('label', flag=True)将'label'设置为target | |||
2. 初始化模型 | |||
~~~~~~~~~~~~~ | |||
:: | |||
class Model(nn.Module): | |||
def __init__(self): | |||
xxx | |||
def forward(self, word_seq1, word_seq2): | |||
# (1) 这里使用的形参名必须和DataSet中的input field的名称对应。因为我们是通过形参名, 进行赋值的 | |||
# (2) input field的数量可以多于这里的形参数量。但是不能少于。 | |||
xxxx | |||
# 输出必须是一个dict | |||
3. Trainer的训练过程 | |||
~~~~~~~~~~~~~~~~~~~~ | |||
:: | |||
(1) 从DataSet中按照batch_size取出一个batch,调用Model.forward | |||
(2) 将 Model.forward的结果 与 标记为target的field 传入Losser当中。 | |||
由于每个人写的Model.forward的output的dict可能key并不一样,比如有人是{'pred':xxx}, {'output': xxx}; | |||
另外每个人将target可能也会设置为不同的名称, 比如有人是label, 有人设置为target; | |||
为了解决以上的问题,我们的loss提供映射机制 | |||
比如CrossEntropyLosser的需要的输入是(prediction, target)。但是forward的output是{'output': xxx}; 'label'是target | |||
那么初始化losser的时候写为CrossEntropyLosser(prediction='output', target='label')即可 | |||
(3) 对于Metric是同理的 | |||
Metric计算也是从 forward的结果中取值 与 设置target的field中取值。 也是可以通过映射找到对应的值 | |||
一些问题. | |||
--------- | |||
1. DataSet中为什么需要设置input和target | |||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | |||
:: | |||
只有被设置为input或者target的数据才会在train的过程中被取出来 | |||
(1.1) 我们只会在设置为input的field中寻找传递给Model.forward的参数。 | |||
(1.2) 我们在传递值给losser或者metric的时候会使用来自: | |||
(a)Model.forward的output | |||
(b)被设置为target的field | |||
2. 我们是通过forwad中的形参名将DataSet中的field赋值给对应的参数 | |||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | |||
:: | |||
(1.1) 构建模型过程中, | |||
例如: | |||
DataSet中x,seq_lens是input,那么forward就应该是 | |||
def forward(self, x, seq_lens): | |||
pass | |||
我们是通过形参名称进行匹配的field的 | |||
1. 加载数据到DataSet | |||
~~~~~~~~~~~~~~~~~~~~ | |||
2. 使用apply操作对DataSet进行预处理 | |||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | |||
:: | |||
(2.1) 处理过程中将某些field设置为input,某些field设置为target | |||
3. 构建模型 | |||
~~~~~~~~~~~ | |||
:: | |||
(3.1) 构建模型过程中,需要注意forward函数的形参名需要和DataSet中设置为input的field名称是一致的。 | |||
例如: | |||
DataSet中x,seq_lens是input,那么forward就应该是 | |||
def forward(self, x, seq_lens): | |||
pass | |||
我们是通过形参名称进行匹配的field的 | |||
(3.2) 模型的forward的output需要是dict类型的。 | |||
建议将输出设置为{"pred": xx}. | |||
@@ -1,113 +0,0 @@ | |||
FastNLP 1分钟上手教程 | |||
===================== | |||
教程原文见 https://github.com/fastnlp/fastNLP/blob/master/tutorials/fastnlp_1min_tutorial.ipynb | |||
step 1 | |||
------ | |||
读取数据集 | |||
.. code:: ipython3 | |||
from fastNLP import DataSet | |||
# linux_path = "../test/data_for_tests/tutorial_sample_dataset.csv" | |||
win_path = "C:\\Users\zyfeng\Desktop\FudanNLP\\fastNLP\\test\\data_for_tests\\tutorial_sample_dataset.csv" | |||
ds = DataSet.read_csv(win_path, headers=('raw_sentence', 'label'), sep='\t') | |||
step 2 | |||
------ | |||
数据预处理 1. 类型转换 2. 切分验证集 3. 构建词典 | |||
.. code:: ipython3 | |||
# 将所有数字转为小写 | |||
ds.apply(lambda x: x['raw_sentence'].lower(), new_field_name='raw_sentence') | |||
# label转int | |||
ds.apply(lambda x: int(x['label']), new_field_name='label_seq', is_target=True) | |||
def split_sent(ins): | |||
return ins['raw_sentence'].split() | |||
ds.apply(split_sent, new_field_name='words', is_input=True) | |||
.. code:: ipython3 | |||
# 分割训练集/验证集 | |||
train_data, dev_data = ds.split(0.3) | |||
print("Train size: ", len(train_data)) | |||
print("Test size: ", len(dev_data)) | |||
.. parsed-literal:: | |||
Train size: 54 | |||
Test size: 23 | |||
.. code:: ipython3 | |||
from fastNLP import Vocabulary | |||
vocab = Vocabulary(min_freq=2) | |||
train_data.apply(lambda x: [vocab.add(word) for word in x['words']]) | |||
# index句子, Vocabulary.to_index(word) | |||
train_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='word_seq', is_input=True) | |||
dev_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='word_seq', is_input=True) | |||
step 3 | |||
------ | |||
定义模型 | |||
.. code:: ipython3 | |||
from fastNLP.models import CNNText | |||
model = CNNText(embed_num=len(vocab), embed_dim=50, num_classes=5, padding=2, dropout=0.1) | |||
step 4 | |||
------ | |||
开始训练 | |||
.. code:: ipython3 | |||
from fastNLP import Trainer, CrossEntropyLoss, AccuracyMetric | |||
trainer = Trainer(model=model, | |||
train_data=train_data, | |||
dev_data=dev_data, | |||
loss=CrossEntropyLoss(), | |||
metrics=AccuracyMetric() | |||
) | |||
trainer.train() | |||
print('Train finished!') | |||
.. parsed-literal:: | |||
training epochs started 2018-12-07 14:03:41 | |||
.. parsed-literal:: | |||
HBox(children=(IntProgress(value=0, layout=Layout(flex='2'), max=6), HTML(value='')), layout=Layout(display='i… | |||
.. parsed-literal:: | |||
Epoch 1/3. Step:2/6. AccuracyMetric: acc=0.26087 | |||
Epoch 2/3. Step:4/6. AccuracyMetric: acc=0.347826 | |||
Epoch 3/3. Step:6/6. AccuracyMetric: acc=0.608696 | |||
Train finished! | |||
本教程结束。更多操作请参考进阶教程。 | |||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ |
@@ -1,5 +0,0 @@ | |||
fastNLP 进阶教程 | |||
=============== | |||
教程原文见 https://github.com/fastnlp/fastNLP/blob/master/tutorials/fastnlp_advanced_tutorial/advance_tutorial.ipynb | |||
@@ -1,5 +0,0 @@ | |||
fastNLP 开发者指南 | |||
=============== | |||
原文见 https://github.com/fastnlp/fastNLP/blob/master/tutorials/tutorial_for_developer.md | |||
@@ -121,4 +121,4 @@ | |||
In Epoch:6/Step:12, got best dev performance:AccuracyMetric: acc=0.8 | |||
Reloaded the best model. | |||
这份教程只是简单地介绍了使用 fastNLP 工作的流程,具体的细节分析见 :doc:`/user/tutorials` | |||
这份教程只是简单地介绍了使用 fastNLP 工作的流程,具体的细节分析见 :doc:`/user/tutorial_one` |
@@ -1,3 +0,0 @@ | |||
===================== | |||
用 fastNLP 分类 | |||
===================== |
@@ -1,3 +0,0 @@ | |||
===================== | |||
用 fastNLP 分词 | |||
===================== |
@@ -0,0 +1,371 @@ | |||
=============== | |||
详细指南 | |||
=============== | |||
我们使用和 :doc:`/user/quickstart` 中一样的任务来进行详细的介绍。给出一段文字,预测它的标签是0~4中的哪一个 | |||
(数据来源 `kaggle <https://www.kaggle.com/c/sentiment-analysis-on-movie-reviews>`_ )。 | |||
-------------- | |||
数据处理 | |||
-------------- | |||
数据读入 | |||
我们可以使用 fastNLP :mod:`fastNLP.io` 模块中的 :class:`~fastNLP.io.CSVLoader` 类,轻松地从 csv 文件读取我们的数据。 | |||
这里的 dataset 是 fastNLP 中 :class:`~fastNLP.DataSet` 类的对象 | |||
.. code-block:: python | |||
from fastNLP.io import CSVLoader | |||
loader = CSVLoader(headers=('raw_sentence', 'label'), sep='\t') | |||
dataset = loader.load("./sample_data/tutorial_sample_dataset.csv") | |||
除了读取数据外,fastNLP 还提供了读取其它文件类型的 Loader 类、读取 Embedding的 Loader 等。详见 :doc:`/fastNLP.io` 。 | |||
Instance 和 DataSet | |||
fastNLP 中的 :class:`~fastNLP.DataSet` 类对象类似于二维表格,它的每一列是一个 :mod:`~fastNLP.core.field` | |||
每一行是一个 :mod:`~fastNLP.core.instance` 。我们可以手动向数据集中添加 :class:`~fastNLP.Instance` 类的对象 | |||
.. code-block:: python | |||
from fastNLP import Instance | |||
dataset.append(Instance(raw_sentence='fake data', label='0')) | |||
此时的 ``dataset[-1]`` 的值如下,可以看到,数据集中的每个数据包含 ``raw_sentence`` 和 ``label`` 两个 | |||
:mod:`~fastNLP.core.field` ,他们的类型都是 ``str`` :: | |||
{'raw_sentence': fake data type=str, 'label': 0 type=str} | |||
field 的修改 | |||
我们使用 :class:`~fastNLP.DataSet` 类的 :meth:`~fastNLP.DataSet.apply` 方法将 ``raw_sentence`` 中字母变成小写,并将句子分词。 | |||
同时也将 ``label`` :mod:`~fastNLP.core.field` 转化为整数并改名为 ``target`` | |||
.. code-block:: python | |||
dataset.apply(lambda x: x['raw_sentence'].lower(), new_field_name='sentence') | |||
dataset.apply_field(lambda x: x.split(), field_name='sentence', new_field_name='words') | |||
dataset.apply(lambda x: int(x['label']), new_field_name='target') | |||
``words`` 和 ``target`` 已经足够用于 :class:`~fastNLP.models.CNNText` 的训练了,但我们从其文档 | |||
:class:`~fastNLP.models.CNNText` 中看到,在 :meth:`~fastNLP.models.CNNText.forward` 的时候,还可以传入可选参数 ``seq_len`` 。 | |||
所以,我们再使用 :meth:`~fastNLP.DataSet.apply_field` 方法增加一个名为 ``seq_len`` 的 :mod:`~fastNLP.core.field` 。 | |||
.. code-block:: python | |||
dataset.apply_field(lambda x: len(x), field_name='words', new_field_name='seq_len') | |||
观察可知: :meth:`~fastNLP.DataSet.apply_field` 与 :meth:`~fastNLP.DataSet.apply` 类似, | |||
但所传入的 `lambda` 函数是针对一个 :class:`~fastNLP.Instance` 中的一个 :mod:`~fastNLP.core.field` 的; | |||
而 :meth:`~fastNLP.DataSet.apply` 所传入的 `lambda` 函数是针对整个 :class:`~fastNLP.Instance` 的。 | |||
.. note:: | |||
`lambda` 函数即匿名函数,是 Python 的重要特性。 ``lambda x: len(x)`` 和下面的这个函数的作用相同:: | |||
def func_lambda(x): | |||
return len(x) | |||
你也可以编写复杂的函数做为 :meth:`~fastNLP.DataSet.apply_field` 与 :meth:`~fastNLP.DataSet.apply` 的参数 | |||
Vocabulary 的使用 | |||
我们再用 :class:`~fastNLP.Vocabulary` 类来统计数据中出现的单词,并使用 :meth:`~fastNLP.Vocabularyindex_dataset` | |||
将单词序列转化为训练可用的数字序列。 | |||
.. code-block:: python | |||
from fastNLP import Vocabulary | |||
vocab = Vocabulary(min_freq=2).from_dataset(dataset, field_name='words') | |||
vocab.index_dataset(dataset, field_name='words',new_field_name='words') | |||
数据集分割 | |||
除了修改 :mod:`~fastNLP.core.field` 之外,我们还可以对 :class:`~fastNLP.DataSet` 进行分割,以供训练、开发和测试使用。 | |||
下面这段代码展示了 :meth:`~fastNLP.DataSet.split` 的使用方法(但实际应该放在后面两段改名和设置输入的代码之后) | |||
.. code-block:: python | |||
train_dev_data, test_data = dataset.split(0.1) | |||
train_data, dev_data = train_dev_data.split(0.1) | |||
len(train_data), len(dev_data), len(test_data) | |||
--------------------- | |||
使用内置模型训练 | |||
--------------------- | |||
内置模型的输入输出命名 | |||
fastNLP内置了一些完整的神经网络模型,详见 :doc:`/fastNLP.models` , 我们使用其中的 :class:`~fastNLP.models.CNNText` 模型进行训练。 | |||
为了使用内置的 :class:`~fastNLP.models.CNNText`,我们必须修改 :class:`~fastNLP.DataSet` 中 :mod:`~fastNLP.core.field` 的名称。 | |||
在这个例子中模型输入 (forward方法的参数) 为 ``words`` 和 ``seq_len`` ; 预测输出为 ``pred`` ;标准答案为 ``target`` 。 | |||
具体的命名规范可以参考 :doc:`/fastNLP.core.const` 。 | |||
如果不想查看文档,您也可以使用 :class:`~fastNLP.Const` 类进行命名。下面的代码展示了给 :class:`~fastNLP.DataSet` 中 | |||
:mod:`~fastNLP.core.field` 改名的 :meth:`~fastNLP.DataSet.rename_field` 方法,以及 :class:`~fastNLP.Const` 类的使用方法。 | |||
.. code-block:: python | |||
from fastNLP import Const | |||
dataset.rename_field('words', Const.INPUT) | |||
dataset.rename_field('seq_len', Const.INPUT_LEN) | |||
dataset.rename_field('target', Const.TARGET) | |||
在给 :class:`~fastNLP.DataSet` 中 :mod:`~fastNLP.core.field` 改名后,我们还需要设置训练所需的输入和目标,这里使用的是 | |||
:meth:`~fastNLP.DataSet.set_input` 和 :meth:`~fastNLP.DataSet.set_target` 两个函数。 | |||
.. code-block:: python | |||
dataset.set_input(Const.INPUT, Const.INPUT_LEN) | |||
dataset.set_target(Const.TARGET) | |||
快速训练 | |||
现在我们可以导入 fastNLP 内置的文本分类模型 :class:`~fastNLP.models.CNNText` ,并使用 :class:`~fastNLP.Trainer` 进行训练了 | |||
(其中 ``loss`` 和 ``metrics`` 的定义,我们将在后续两段代码中给出)。 | |||
.. code-block:: python | |||
from fastNLP.models import CNNText | |||
from fastNLP import Trainer | |||
model = CNNText((len(vocab),50), num_classes=5, padding=2, dropout=0.1) | |||
trainer = Trainer(model=model_cnn, train_data=train_data, dev_data=dev_data, | |||
loss=loss, metrics=metrics) | |||
trainer.train() | |||
训练过程的输出如下:: | |||
input fields after batch(if batch size is 2): | |||
words: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 26]) | |||
target fields after batch(if batch size is 2): | |||
target: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2]) | |||
training epochs started 2019-05-09-10-59-39 | |||
Evaluation at Epoch 1/10. Step:2/20. AccuracyMetric: acc=0.333333 | |||
Evaluation at Epoch 2/10. Step:4/20. AccuracyMetric: acc=0.533333 | |||
Evaluation at Epoch 3/10. Step:6/20. AccuracyMetric: acc=0.533333 | |||
Evaluation at Epoch 4/10. Step:8/20. AccuracyMetric: acc=0.533333 | |||
Evaluation at Epoch 5/10. Step:10/20. AccuracyMetric: acc=0.6 | |||
Evaluation at Epoch 6/10. Step:12/20. AccuracyMetric: acc=0.8 | |||
Evaluation at Epoch 7/10. Step:14/20. AccuracyMetric: acc=0.8 | |||
Evaluation at Epoch 8/10. Step:16/20. AccuracyMetric: acc=0.733333 | |||
Evaluation at Epoch 9/10. Step:18/20. AccuracyMetric: acc=0.733333 | |||
Evaluation at Epoch 10/10. Step:20/20. AccuracyMetric: acc=0.733333 | |||
In Epoch:6/Step:12, got best dev performance:AccuracyMetric: acc=0.8 | |||
Reloaded the best model. | |||
损失函数 | |||
训练模型需要提供一个损失函数, 下面提供了一个在分类问题中常用的交叉熵损失。注意它的 **初始化参数** 。 | |||
``pred`` 参数对应的是模型的 forward 方法返回的 dict 中的一个 key 的名字。 | |||
``target`` 参数对应的是 :class:`~fastNLP.DataSet` 中作为标签的 :mod:`~fastNLP.core.field` 的名字。 | |||
这里我们用 :class:`~fastNLP.Const` 来辅助命名,如果你自己编写模型中 forward 方法的返回值或 | |||
数据集中 :mod:`~fastNLP.core.field` 的名字与本例不同, 你可以把 ``pred`` 参数和 ``target`` 参数设定符合自己代码的值。 | |||
.. code-block:: python | |||
from fastNLP import CrossEntropyLoss | |||
# loss = CrossEntropyLoss() 在本例中与下面这行代码等价 | |||
loss = CrossEntropyLoss(pred=Const.OUTPUT, target=Const.TARGET) | |||
评价指标 | |||
训练模型需要提供一个评价指标。这里使用准确率做为评价指标。参数的 `命名规则` 跟上面类似。 | |||
``pred`` 参数对应的是模型的 forward 方法返回的 dict 中的一个 key 的名字。 | |||
``target`` 参数对应的是 :class:`~fastNLP.DataSet` 中作为标签的 :mod:`~fastNLP.core.field` 的名字。 | |||
.. code-block:: python | |||
from fastNLP import AccuracyMetric | |||
# metrics=AccuracyMetric() 在本例中与下面这行代码等价 | |||
metrics=AccuracyMetric(pred=Const.OUTPUT, target=Const.TARGET) | |||
快速测试 | |||
与 :class:`~fastNLP.Trainer` 对应,fastNLP 也提供了 :class:`~fastNLP.Tester` 用于快速测试,用法如下 | |||
.. code-block:: python | |||
from fastNLP import Tester | |||
tester = Tester(test_data, model_cnn, metrics=AccuracyMetric()) | |||
tester.test() | |||
--------------------- | |||
编写自己的模型 | |||
--------------------- | |||
因为 fastNLP 是基于 `PyTorch <https://pytorch.org/>`_ 开发的框架,所以我们可以基于 PyTorch 模型编写自己的神经网络模型。 | |||
与标准的 PyTorch 模型不同,fastNLP 模型中 forward 方法返回的是一个字典,字典中至少需要包含 "pred" 这个字段。 | |||
而 forward 方法的参数名称必须与 :class:`~fastNLP.DataSet` 中用 :meth:`~fastNLP.DataSet.set_input` 设定的名称一致。 | |||
模型定义的代码如下: | |||
.. code-block:: python | |||
import torch | |||
import torch.nn as nn | |||
class LSTMText(nn.Module): | |||
def __init__(self, vocab_size, embedding_dim, output_dim, hidden_dim=64, num_layers=2, dropout=0.5): | |||
super().__init__() | |||
self.embedding = nn.Embedding(vocab_size, embedding_dim) | |||
self.lstm = nn.LSTM(embedding_dim, hidden_dim, num_layers=num_layers, bidirectional=True, dropout=dropout) | |||
self.fc = nn.Linear(hidden_dim * 2, output_dim) | |||
self.dropout = nn.Dropout(dropout) | |||
def forward(self, words): | |||
# (input) words : (batch_size, seq_len) | |||
words = words.permute(1,0) | |||
# words : (seq_len, batch_size) | |||
embedded = self.dropout(self.embedding(words)) | |||
# embedded : (seq_len, batch_size, embedding_dim) | |||
output, (hidden, cell) = self.lstm(embedded) | |||
# output: (seq_len, batch_size, hidden_dim * 2) | |||
# hidden: (num_layers * 2, batch_size, hidden_dim) | |||
# cell: (num_layers * 2, batch_size, hidden_dim) | |||
hidden = torch.cat((hidden[-2, :, :], hidden[-1, :, :]), dim=1) | |||
hidden = self.dropout(hidden) | |||
# hidden: (batch_size, hidden_dim * 2) | |||
pred = self.fc(hidden.squeeze(0)) | |||
# result: (batch_size, output_dim) | |||
return {"pred":pred} | |||
模型的使用方法与内置模型 :class:`~fastNLP.models.CNNText` 一致 | |||
.. code-block:: python | |||
model_lstm = LSTMText(len(vocab),50,5) | |||
trainer = Trainer(model=model_lstm, train_data=train_data, dev_data=dev_data, | |||
loss=loss, metrics=metrics) | |||
trainer.train() | |||
tester = Tester(test_data, model_lstm, metrics=AccuracyMetric()) | |||
tester.test() | |||
.. todo:: | |||
使用 :doc:`/fastNLP.modules` 编写模型 | |||
-------------------------- | |||
自己编写训练过程 | |||
-------------------------- | |||
如果你想用类似 PyTorch 的使用方法,自己编写训练过程,你可以参考下面这段代码。其中使用了 fastNLP 提供的 :class:`~fastNLP.Batch` | |||
来获得小批量训练的小批量数据,使用 :class:`~fastNLP.BucketSampler` 做为 :class:`~fastNLP.Batch` 的参数来选择采样的方式。 | |||
这段代码中使用了 PyTorch 的 `torch.optim.Adam` 优化器 和 `torch.nn.CrossEntropyLoss` 损失函数,并自己计算了正确率 | |||
.. code-block:: python | |||
from fastNLP import BucketSampler | |||
from fastNLP import Batch | |||
import torch | |||
import time | |||
model = CNNText((len(vocab),50), num_classes=5, padding=2, dropout=0.1) | |||
def train(epoch, data): | |||
optim = torch.optim.Adam(model.parameters(), lr=0.001) | |||
lossfunc = torch.nn.CrossEntropyLoss() | |||
batch_size = 32 | |||
train_sampler = BucketSampler(batch_size=batch_size, seq_len_field_name='seq_len') | |||
train_batch = Batch(batch_size=batch_size, dataset=data, sampler=train_sampler) | |||
start_time = time.time() | |||
for i in range(epoch): | |||
loss_list = [] | |||
for batch_x, batch_y in train_batch: | |||
optim.zero_grad() | |||
output = model(batch_x['words']) | |||
loss = lossfunc(output['pred'], batch_y['target']) | |||
loss.backward() | |||
optim.step() | |||
loss_list.append(loss.item()) | |||
print('Epoch {:d} Avg Loss: {:.2f}'.format(i, sum(loss_list) / len(loss_list)),end=" ") | |||
print('{:d}ms'.format(round((time.time()-start_time)*1000))) | |||
loss_list.clear() | |||
train(10, train_data) | |||
tester = Tester(test_data, model, metrics=AccuracyMetric()) | |||
tester.test() | |||
这段代码的输出如下:: | |||
Epoch 0 Avg Loss: 2.76 17ms | |||
Epoch 1 Avg Loss: 2.55 29ms | |||
Epoch 2 Avg Loss: 2.37 41ms | |||
Epoch 3 Avg Loss: 2.30 53ms | |||
Epoch 4 Avg Loss: 2.12 65ms | |||
Epoch 5 Avg Loss: 2.16 76ms | |||
Epoch 6 Avg Loss: 1.88 88ms | |||
Epoch 7 Avg Loss: 1.84 99ms | |||
Epoch 8 Avg Loss: 1.71 111ms | |||
Epoch 9 Avg Loss: 1.62 122ms | |||
[tester] | |||
AccuracyMetric: acc=0.142857 | |||
---------------------------------- | |||
使用 Callback 增强 Trainer | |||
---------------------------------- | |||
如果你不想自己实现繁琐的训练过程,只希望在训练过程中实现一些自己的功能(比如:输出从训练开始到当前 batch 结束的总时间), | |||
你可以使用 fastNLP 提供的 :class:`~fastNLP.Callback` 类。下面的例子中,我们继承 :class:`~fastNLP.Callback` 类实现了这个功能。 | |||
.. code-block:: python | |||
from fastNLP import Callback | |||
start_time = time.time() | |||
class MyCallback(Callback): | |||
def on_epoch_end(self): | |||
print('Sum Time: {:d}ms\n\n'.format(round((time.time()-start_time)*1000))) | |||
model = CNNText((len(vocab),50), num_classes=5, padding=2, dropout=0.1) | |||
trainer = Trainer(model=model, train_data=train_data, dev_data=dev_data, | |||
loss=CrossEntropyLoss(), metrics=AccuracyMetric(), callbacks=[MyCallback()]) | |||
trainer.train() | |||
训练输出如下:: | |||
input fields after batch(if batch size is 2): | |||
words: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 16]) | |||
seq_len: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2]) | |||
target fields after batch(if batch size is 2): | |||
target: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2]) | |||
training epochs started 2019-05-12-21-38-40 | |||
Evaluation at Epoch 1/10. Step:2/20. AccuracyMetric: acc=0.285714 | |||
Sum Time: 51ms | |||
………………………… | |||
Evaluation at Epoch 10/10. Step:20/20. AccuracyMetric: acc=0.857143 | |||
Sum Time: 212ms | |||
In Epoch:10/Step:20, got best dev performance:AccuracyMetric: acc=0.857143 | |||
Reloaded the best model. | |||
这个例子只是介绍了 :class:`~fastNLP.Callback` 类的使用方法。实际应用(比如:负采样、Learning Rate Decay、Early Stop 等)中 | |||
很多功能已经被 fastNLP 实现了。你可以直接 import 它们使用,详细请查看文档 :doc:`/fastNLP.core.callback` 。 |
@@ -0,0 +1,5 @@ | |||
================= | |||
科研向导 | |||
================= | |||
本文介绍使用 fastNLP 和 fitlog 进行科学研究的方法 |
@@ -1,12 +1,11 @@ | |||
""" | |||
fastNLP 由 :mod:`~fastNLP.core` 、 :mod:`~fastNLP.io` 、:mod:`~fastNLP.modules`、:mod:`~fastNLP.models` | |||
和 :mod:`~fastNLP.component` 等子模块组成。 | |||
等子模块组成,你可以点进去查看每个模块的文档。 | |||
- :mod:`~fastNLP.core` fastNLP 的核心模块,包括 DataSet、 Trainer、 Tester 等组件 | |||
- :mod:`~fastNLP.io` fastNLP 的输入输出模块,实现了数据集的读取,模型的存取等功能 | |||
- :mod:`~fastNLP.modules` TODO 如何介绍 | |||
- :mod:`~fastNLP.models` 使用 fastNLP 实现的一些常见模型,具体参见 :doc:`fastNLP.models` | |||
- :mod:`~fastNLP.component` TODO | |||
- :mod:`~fastNLP.core` 是fastNLP 的核心模块,包括 DataSet、 Trainer、 Tester 等组件。详见文档 :doc:`/fastNLP.core` | |||
- :mod:`~fastNLP.io` 是实现输入输出的模块,包括了数据集的读取,模型的存取等功能。详见文档 :doc:`/fastNLP.io` | |||
- :mod:`~fastNLP.modules` 包含了用于搭建神经网络模型的诸多组件,可以帮助用户快速搭建自己所需的网络。详见文档 :doc:`/fastNLP.modules` | |||
- :mod:`~fastNLP.models` 包含了一些使用 fastNLP 实现的完整网络模型,包括CNNText、SeqLabeling等常见模型。详见文档 :doc:`/fastNLP.models` | |||
fastNLP 中最常用的组件可以直接从 fastNLP 包中 import ,他们的文档如下: | |||
""" | |||
@@ -33,7 +32,6 @@ __all__ = [ | |||
"EngChar2DPadder", | |||
"AccuracyMetric", | |||
"BMESF1PreRecMetric", | |||
"SpanFPreRecMetric", | |||
"SQuADMetric", | |||
@@ -1,5 +1,5 @@ | |||
""" | |||
core 模块里实现了 fastNLP 的核心框架,常用的组件都可以从 fastNLP 包中直接 import。当然你也同样可以从 core 模块的子模块中 import, | |||
core 模块里实现了 fastNLP 的核心框架,常用的功能都可以从 fastNLP 包中直接 import。当然你也同样可以从 core 模块的子模块中 import, | |||
例如 Batch 组件有两种 import 的方式:: | |||
# 直接从 fastNLP 中 import | |||
@@ -8,10 +8,11 @@ core 模块里实现了 fastNLP 的核心框架,常用的组件都可以从 fa | |||
# 从 core 模块的子模块 batch 中 import | |||
from fastNLP.core.batch import Batch | |||
对于常用的功能,你只需要在 :doc:`fastNLP` 中查看即可。如果想了解各个子模块的分工,您可以阅读以下文档: | |||
TODO 向导 | |||
对于常用的功能,你只需要在 :doc:`fastNLP` 中查看即可。如果想了解各个子模块的具体作用,您可以在下面找到每个子模块的具体文档。 | |||
.. todo:: | |||
介绍core 的子模块的分工,好像必要性不大 | |||
""" | |||
from .batch import Batch | |||
from .callback import Callback, GradientClipCallback, EarlyStopCallback, TensorboardCallback, LRScheduler, ControlC | |||
@@ -1,5 +1,10 @@ | |||
r""" | |||
callback模块实现了 fastNLP 中的许多 callback 类,用于增强 :class:`~fastNLP.Trainer` 类, | |||
callback模块实现了 fastNLP 中的许多 callback 类,用于增强 :class:`~fastNLP.Trainer` 类。 | |||
虽然Trainer本身已经集成了一些功能,但仍然不足以囊括训练过程中可能需要到的功能, | |||
比如负采样,learning rate decay, Early Stop等。 | |||
为了解决这个问题fastNLP引入了callback的机制,Callback 是一种在Trainer训练过程中特定阶段会运行的函数集合。 | |||
关于Trainer的详细文档,请参见 :doc:`trainer 模块<fastNLP.core.trainer>` | |||
我们将 :meth:`~fastNLP.Train.train` 这个函数内部分为以下的阶段,在对应阶段会触发相应的调用:: | |||
@@ -26,8 +31,6 @@ callback模块实现了 fastNLP 中的许多 callback 类,用于增强 :class: | |||
callback.on_train_end() # 训练结束 | |||
callback.on_exception() # 这是一个特殊的步骤,在训练过程中遭遇exception会跳转到这里 | |||
关于Trainer的详细文档,请参见 :doc:`trainer 模块<fastNLP.core.trainer>` | |||
如下面的例子所示,我们可以使用内置的 callback 类,或者继承 :class:`~fastNLP.core.callback.Callback` | |||
定义自己的 callback 类:: | |||
@@ -63,8 +66,9 @@ from ..io.model_io import ModelSaver, ModelLoader | |||
try: | |||
from tensorboardX import SummaryWriter | |||
tensorboardX_flag = True | |||
except: | |||
pass | |||
tensorboardX_flag = False | |||
class Callback(object): | |||
@@ -578,8 +582,11 @@ class TensorboardCallback(Callback): | |||
path = os.path.join("./", 'tensorboard_logs_{}'.format(self.trainer.start_time)) | |||
else: | |||
path = os.path.join(save_dir, 'tensorboard_logs_{}'.format(self.trainer.start_time)) | |||
self._summary_writer = SummaryWriter(path) | |||
if tensorboardX_flag: | |||
self._summary_writer = SummaryWriter(path) | |||
else: | |||
self._summary_writer = None | |||
def on_batch_begin(self, batch_x, batch_y, indices): | |||
if "model" in self.options and self.graph_added is False: | |||
# tesorboardX 这里有大bug,暂时没法画模型图 | |||
@@ -591,10 +598,10 @@ class TensorboardCallback(Callback): | |||
self.graph_added = True | |||
def on_backward_begin(self, loss): | |||
if "loss" in self.options: | |||
if "loss" in self.options and self._summary_writer: | |||
self._summary_writer.add_scalar("loss", loss.item(), global_step=self.trainer.step) | |||
if "model" in self.options: | |||
if "model" in self.options and self._summary_writer: | |||
for name, param in self.trainer.model.named_parameters(): | |||
if param.requires_grad: | |||
self._summary_writer.add_scalar(name + "_mean", param.mean(), global_step=self.trainer.step) | |||
@@ -603,15 +610,16 @@ class TensorboardCallback(Callback): | |||
global_step=self.trainer.step) | |||
def on_valid_end(self, eval_result, metric_key, optimizer, is_better_eval): | |||
if "metric" in self.options: | |||
if "metric" in self.options and self._summary_writer: | |||
for name, metric in eval_result.items(): | |||
for metric_key, metric_val in metric.items(): | |||
self._summary_writer.add_scalar("valid_{}_{}".format(name, metric_key), metric_val, | |||
global_step=self.trainer.step) | |||
def on_train_end(self): | |||
self._summary_writer.close() | |||
del self._summary_writer | |||
if self._summary_writer: | |||
self._summary_writer.close() | |||
del self._summary_writer | |||
def on_exception(self, exception): | |||
if hasattr(self, "_summary_writer"): | |||
@@ -1,5 +1,10 @@ | |||
class Const: | |||
"""fastNLP中field命名常量。 | |||
""" | |||
fastNLP中field命名常量。 | |||
.. todo:: | |||
把下面这段改成表格 | |||
具体列表:: | |||
INPUT 模型的序列输入 words(复数words1, words2) | |||
@@ -58,7 +58,10 @@ | |||
2 DataSet与预处理 | |||
常见的预处理有如下几种 | |||
2.1 从某个文本文件读取内容 # TODO 引用DataLoader | |||
2.1 从某个文本文件读取内容 # | |||
.. todo:: | |||
引用DataLoader | |||
Example:: | |||
@@ -209,39 +212,33 @@ | |||
target和input,这种情况下,fastNLP默认不进行pad。另外,当某个field已经被设置为了target或者input后,之后append的 | |||
instance对应的field必须要和前面已有的内容一致,否则会报错。 | |||
可以查看field的dtype | |||
Example:: | |||
可以查看field的dtype:: | |||
from fastNLP import DataSet | |||
from fastNLP import DataSet | |||
d = DataSet({'a': [0, 1, 3], 'b':[[1.0, 2.0], [0.1, 0.2], [3]]}) | |||
d.set_input('a', 'b') | |||
d.a.dtype | |||
>> numpy.int64 | |||
d.b.dtype | |||
>> numpy.float64 | |||
# 默认情况下'a'这个field将被转换为torch.LongTensor,但如果需要其为torch.FloatTensor可以手动修改dtype | |||
d.a.dtype = float # 请确保该field的确可以全部转换为float。 | |||
d = DataSet({'a': [0, 1, 3], 'b':[[1.0, 2.0], [0.1, 0.2], [3]]}) | |||
d.set_input('a', 'b') | |||
d.a.dtype | |||
>> numpy.int64 | |||
d.b.dtype | |||
>> numpy.float64 | |||
# 默认情况下'a'这个field将被转换为torch.LongTensor,但如果需要其为torch.FloatTensor可以手动修改dtype | |||
d.a.dtype = float # 请确保该field的确可以全部转换为float。 | |||
如果某个field中出现了多种类型混合(比如一部分为str,一部分为int)的情况,fastNLP无法判断该field的类型,会报如下的 | |||
错误: | |||
Example:: | |||
错误:: | |||
from fastNLP import DataSet | |||
d = DataSet({'data': [1, 'a']}) | |||
d.set_input('data') | |||
>> RuntimeError: Mixed data types in Field data: [<class 'str'>, <class 'int'>] | |||
from fastNLP import DataSet | |||
d = DataSet({'data': [1, 'a']}) | |||
d.set_input('data') | |||
>> RuntimeError: Mixed data types in Field data: [<class 'str'>, <class 'int'>] | |||
可以通过设置以忽略对该field进行类型检查 | |||
可以通过设置以忽略对该field进行类型检查:: | |||
Example:: | |||
from fastNLP import DataSet | |||
d = DataSet({'data': [1, 'a']}) | |||
d.set_ignore_type('data') | |||
d.set_input('data') | |||
from fastNLP import DataSet | |||
d = DataSet({'data': [1, 'a']}) | |||
d.set_ignore_type('data') | |||
d.set_input('data') | |||
当某个field被设置为忽略type之后,fastNLP将不对其进行pad。 | |||
@@ -221,8 +221,7 @@ class CrossEntropyLoss(LossBase): | |||
""" | |||
def __init__(self, pred=None, target=None, padding_idx=-100): | |||
# TODO 需要做一些检查,F.cross_entropy在计算时,如果pred是(16, 10 ,4), target的形状按道理应该是(16, 10), 但实际却需要 | |||
# TODO (16, 4) | |||
# TODO 需要做一些检查,F.cross_entropy在计算时,如果pred是(16, 10 ,4), target的形状按道理应该是(16, 10), 但实际需要(16,4) | |||
super(CrossEntropyLoss, self).__init__() | |||
self._init_param_map(pred=pred, target=target) | |||
self.padding_idx = padding_idx | |||
@@ -35,9 +35,7 @@ def cache_results(_cache_fp, _refresh=False, _verbose=1): | |||
""" | |||
别名::class:`fastNLP.cache_results` :class:`fastNLP.core.uitls.cache_results` | |||
cache_results是fastNLP中用于cache数据的装饰器。通过下面的例子看一下如何使用 | |||
Example:: | |||
cache_results是fastNLP中用于cache数据的装饰器。通过下面的例子看一下如何使用:: | |||
import time | |||
import numpy as np | |||
@@ -607,6 +605,7 @@ def seq_len_to_mask(seq_len): | |||
转变 1-d seq_len到2-d mask. | |||
Example:: | |||
>>> seq_len = torch.arange(2, 16) | |||
>>> mask = seq_len_to_mask(seq_len) | |||
>>> print(mask.size()) | |||
@@ -5,15 +5,10 @@ | |||
2. 用于读入数据的 :doc:`DataSetLoader <fastNLP.io.dataset_loader>` 类 | |||
3. 用于保存和载入模型的类, 参考 :doc:`Model-IO <fastNLP.io.model_io>` | |||
3. 用于保存和载入模型的类, 参考 :doc:`/fastNLP.io.model_io` | |||
这些类的使用方法可以在对应module的文档下查看. | |||
这些类的使用方法如下: | |||
""" | |||
from .embed_loader import EmbedLoader | |||
from .dataset_loader import DataSetLoader, CSVLoader, JsonLoader, ConllLoader, SNLILoader, SSTLoader, \ | |||
PeopleDailyCorpusLoader, Conll2003Loader | |||
from .model_io import ModelLoader as ModelLoader, ModelSaver as ModelSaver | |||
__all__ = [ | |||
'EmbedLoader', | |||
@@ -29,3 +24,7 @@ __all__ = [ | |||
'ModelLoader', | |||
'ModelSaver', | |||
] | |||
from .embed_loader import EmbedLoader | |||
from .dataset_loader import DataSetLoader, CSVLoader, JsonLoader, ConllLoader, SNLILoader, SSTLoader, \ | |||
PeopleDailyCorpusLoader, Conll2003Loader | |||
from .model_io import ModelLoader as ModelLoader, ModelSaver as ModelSaver |
@@ -47,7 +47,6 @@ class BaseLoader(object): | |||
class DataLoaderRegister: | |||
# TODO 这个类使用在何处? | |||
_readers = {} | |||
@classmethod | |||
@@ -64,3 +63,5 @@ class DataLoaderRegister: | |||
if read_fn_name in cls._readers: | |||
return cls._readers[read_fn_name] | |||
raise AttributeError('no read function: {}'.format(read_fn_name)) | |||
# TODO 这个类使用在何处? |
@@ -1,8 +1,7 @@ | |||
""" | |||
dataset_loader模块实现了许多 DataSetLoader, 用于读取不同格式的数据, 并返回 `DataSet` , | |||
得到的 :class:`~fastNLP.DataSet` 对象可以直接传入 :class:`~fastNLP.Trainer`, :class:`~fastNLP.Tester`, 用于模型的训练和测试 | |||
Example:: | |||
得到的 :class:`~fastNLP.DataSet` 对象可以直接传入 :class:`~fastNLP.Trainer`, :class:`~fastNLP.Tester`, 用于模型的训练和测试。 | |||
以SNLI数据集为例:: | |||
loader = SNLILoader() | |||
train_ds = loader.load('path/to/train') | |||
@@ -1,8 +1,3 @@ | |||
""" | |||
.. _embed-loader: | |||
用于读取预训练的embedding, 读取结果可直接载入为模型参数 | |||
""" | |||
import os | |||
import numpy as np | |||
@@ -16,7 +11,7 @@ class EmbedLoader(BaseLoader): | |||
""" | |||
别名::class:`fastNLP.io.EmbedLoader` :class:`fastNLP.io.embed_loader.EmbedLoader` | |||
这个类用于从预训练的Embedding中load数据。 | |||
用于读取预训练的embedding, 读取结果可直接载入为模型参数。 | |||
""" | |||
def __init__(self): | |||
@@ -1,8 +1,13 @@ | |||
""" | |||
使用 fastNLP 实现的一系列常见模型,具体有: | |||
TODO 详细介绍的表格,与主页相对应 | |||
fastNLP 在 :mod:`~fastNLP.models` 模块中内置了如 :class:`~fastNLP.models.CNNText` 、 | |||
:class:`~fastNLP.models.SeqLabeling` 等完整的模型,以供用户直接使用。 | |||
.. todo:: | |||
这些模型的介绍(与主页一致) | |||
""" | |||
__all__ = ["CNNText", "SeqLabeling", "ESIM", "STSeqLabel", "AdvSeqLabel", "STNLICls", "STSeqCls"] | |||
from .base_model import BaseModel | |||
from .bert import BertForMultipleChoice, BertForQuestionAnswering, BertForSequenceClassification, \ | |||
BertForTokenClassification | |||
@@ -78,7 +78,7 @@ class ENASTrainer(Trainer): | |||
results['seconds'] = 0. | |||
return results | |||
try: | |||
if torch.cuda.is_available() and self.use_cuda: | |||
if torch.cuda.is_available() and "cuda" in self.device: | |||
self.model = self.model.cuda() | |||
self._model_device = self.model.parameters().__next__().device | |||
self._mode(self.model, is_test=False) | |||
@@ -337,7 +337,7 @@ class ENASTrainer(Trainer): | |||
# policy loss | |||
loss = -log_probs*utils.get_variable(adv, | |||
self.use_cuda, | |||
'cuda' in self.device, | |||
requires_grad=False) | |||
loss = loss.sum() # or loss.mean() | |||
@@ -1,10 +1,25 @@ | |||
""" | |||
modules 模块是 fastNLP 的重要组成部分,它实现了神经网络构建中常见的组件, | |||
具体包括 TODO | |||
大部分用于的 NLP 任务神经网络都可以看做由编码 :mod:`~fastNLP.modules.encoder` 、 | |||
聚合 :mod:`~fastNLP.modules.aggregator` 、解码 :mod:`~fastNLP.modules.decoder` 三种模块组成。 | |||
可以和 PyTorch 结合使用?TODO | |||
.. image:: figures/text_classification.png | |||
TODO __all__ 里面多暴露一些 | |||
:mod:`~fastNLP.modules` 中实现了 fastNLP 提供的诸多模块组件,可以帮助用户快速搭建自己所需的网络。 | |||
三种模块的功能和常见组件如下: | |||
+-----------------------+-----------------------+-----------------------+ | |||
| module type | functionality | example | | |||
+=======================+=======================+=======================+ | |||
| encoder | 将输入编码为具有具 | embedding, RNN, CNN, | | |||
| | 有表示能力的向量 | transformer | | |||
+-----------------------+-----------------------+-----------------------+ | |||
| aggregator | 从多个向量中聚合信息 | self-attention, | | |||
| | | max-pooling | | |||
+-----------------------+-----------------------+-----------------------+ | |||
| decoder | 将具有某种表示意义的 | MLP, CRF | | |||
| | 向量解码为需要的输出 | | | |||
| | 形式 | | | |||
+-----------------------+-----------------------+-----------------------+ | |||
""" | |||
from . import aggregator | |||
@@ -16,3 +31,20 @@ from .dropout import TimestepDropout | |||
from .encoder import * | |||
from .utils import get_embeddings | |||
__all__ = [ | |||
"LSTM", | |||
"Embedding", | |||
"ConvMaxpool", | |||
"BertModel", | |||
"MaxPool", | |||
"MaxPoolWithMask", | |||
"AvgPool", | |||
"MultiHeadAttention", | |||
"BiAttention", | |||
"MLP", | |||
"ConditionalRandomField", | |||
"viterbi_decode", | |||
"allowed_transitions", | |||
] |
@@ -1,7 +1,14 @@ | |||
__all__ = ["MaxPool", "MaxPoolWithMask", "AvgPool", "MultiHeadAttention", "BiAttention"] | |||
from .pooling import MaxPool | |||
from .pooling import MaxPoolWithMask | |||
from .pooling import AvgPool | |||
from .pooling import MeanPoolWithMask | |||
from .attention import MultiHeadAttention, BiAttention | |||
__all__ = [ | |||
"MaxPool", | |||
"MaxPoolWithMask", | |||
"AvgPool", | |||
"MultiHeadAttention", | |||
"BiAttention" | |||
] |
@@ -12,7 +12,8 @@ from ..utils import initial_parameter | |||
class DotAttention(nn.Module): | |||
""" | |||
TODO | |||
.. todo:: | |||
补上文档 | |||
""" | |||
def __init__(self, key_size, value_size, dropout=0): | |||
super(DotAttention, self).__init__() | |||
@@ -1,5 +1,11 @@ | |||
__all__ = ["MLP", "ConditionalRandomField", "viterbi_decode", "allowed_transitions"] | |||
from .CRF import ConditionalRandomField | |||
from .MLP import MLP | |||
from .utils import viterbi_decode | |||
from .CRF import allowed_transitions | |||
__all__ = [ | |||
"MLP", | |||
"ConditionalRandomField", | |||
"viterbi_decode", | |||
"allowed_transitions" | |||
] |
@@ -3,7 +3,9 @@ from .embedding import Embedding | |||
from .lstm import LSTM | |||
from .bert import BertModel | |||
__all__ = ["LSTM", | |||
"Embedding", | |||
"ConvMaxpool", | |||
"BertModel"] | |||
__all__ = [ | |||
"LSTM", | |||
"Embedding", | |||
"ConvMaxpool", | |||
"BertModel" | |||
] |
@@ -70,7 +70,10 @@ def initial_parameter(net, initial_method=None): | |||
def get_embeddings(init_embed): | |||
""" | |||
得到词嵌入 TODO | |||
得到词嵌入 | |||
.. todo:: | |||
补上文档 | |||
:param init_embed: 单词词典, 可以是 tuple, 包括(num_embedings, embedding_dim), 即 | |||
embedding的大小和每个词的维度. 也可以传入 nn.Embedding 对象, | |||
@@ -5,13 +5,13 @@ import torch | |||
warnings.filterwarnings('ignore') | |||
import os | |||
from ..core.dataset import DataSet | |||
from fastNLP.core.dataset import DataSet | |||
from .utils import load_url | |||
from .processor import ModelProcessor | |||
from ..io.dataset_loader import _cut_long_sentence, ConllLoader | |||
from ..core.instance import Instance | |||
from fastNLP.io.dataset_loader import _cut_long_sentence, ConllLoader | |||
from fastNLP.core.instance import Instance | |||
from ..api.pipeline import Pipeline | |||
from ..core.metrics import SpanFPreRecMetric | |||
from fastNLP.core.metrics import SpanFPreRecMetric | |||
from .processor import IndexerProcessor | |||
# TODO add pretrain urls |
@@ -3,10 +3,10 @@ from collections import defaultdict | |||
import torch | |||
from ..core.batch import Batch | |||
from ..core.dataset import DataSet | |||
from ..core.sampler import SequentialSampler | |||
from ..core.vocabulary import Vocabulary | |||
from fastNLP.core.batch import Batch | |||
from fastNLP.core.dataset import DataSet | |||
from fastNLP.core.sampler import SequentialSampler | |||
from fastNLP.core.vocabulary import Vocabulary | |||
class Processor(object): | |||
@@ -232,7 +232,7 @@ class SeqLenProcessor(Processor): | |||
return dataset | |||
from ..core.utils import _build_args | |||
from fastNLP.core.utils import _build_args | |||
class ModelProcessor(Processor): | |||
@@ -257,10 +257,7 @@ class ModelProcessor(Processor): | |||
data_iterator = Batch(dataset, batch_size=self.batch_size, sampler=SequentialSampler()) | |||
batch_output = defaultdict(list) | |||
if hasattr(self.model, "predict"): | |||
predict_func = self.model.predict | |||
else: | |||
predict_func = self.model.forward | |||
predict_func = self.model.forward | |||
with torch.no_grad(): | |||
for batch_x, _ in data_iterator: | |||
refined_batch_x = _build_args(predict_func, **batch_x) |
@@ -22,7 +22,7 @@ except ImportError: | |||
try: | |||
from tqdm.auto import tqdm | |||
except: | |||
from ..core.utils import _pseudo_tqdm as tqdm | |||
from fastNLP.core.utils import _pseudo_tqdm as tqdm | |||
# matches bfd8deac from resnet18-bfd8deac.pth | |||
HASH_REGEX = re.compile(r'-([a-f0-9]*)\.') |
@@ -11,15 +11,15 @@ import torch | |||
try: | |||
from tqdm.auto import tqdm | |||
except: | |||
from ..core.utils import _pseudo_tqdm as tqdm | |||
from fastNLP.core.utils import _pseudo_tqdm as tqdm | |||
from ..core.batch import Batch | |||
from ..core.callback import CallbackException | |||
from ..core.dataset import DataSet | |||
from ..core.utils import _move_dict_value_to_device | |||
from fastNLP.core.batch import Batch | |||
from fastNLP.core.callback import CallbackException | |||
from fastNLP.core.dataset import DataSet | |||
from fastNLP.core.utils import _move_dict_value_to_device | |||
import fastNLP | |||
from . import enas_utils as utils | |||
from ..core.utils import _build_args | |||
from fastNLP.core.utils import _build_args | |||
from torch.optim import Adam | |||
@@ -1,6 +0,0 @@ | |||
import unittest | |||
class TestPipeline(unittest.TestCase): | |||
def test_case(self): | |||
pass |
@@ -1,101 +0,0 @@ | |||
import random | |||
import unittest | |||
import numpy as np | |||
from fastNLP import Vocabulary, Instance | |||
from fastNLP.api.processor import FullSpaceToHalfSpaceProcessor, PreAppendProcessor, SliceProcessor, Num2TagProcessor, \ | |||
IndexerProcessor, VocabProcessor, SeqLenProcessor, ModelProcessor, Index2WordProcessor, SetTargetProcessor, \ | |||
SetInputProcessor, VocabIndexerProcessor | |||
from fastNLP.core.dataset import DataSet | |||
class TestProcessor(unittest.TestCase): | |||
def test_FullSpaceToHalfSpaceProcessor(self): | |||
ds = DataSet({"word": ["00, u1, u), (u2, u2"]}) | |||
proc = FullSpaceToHalfSpaceProcessor("word") | |||
ds = proc(ds) | |||
self.assertEqual(ds.field_arrays["word"].content, ["00, u1, u), (u2, u2"]) | |||
def test_PreAppendProcessor(self): | |||
ds = DataSet({"word": [["1234", "3456"], ["8789", "3464"]]}) | |||
proc = PreAppendProcessor(data="abc", field_name="word") | |||
ds = proc(ds) | |||
self.assertEqual(ds.field_arrays["word"].content, [["abc", "1234", "3456"], ["abc", "8789", "3464"]]) | |||
def test_SliceProcessor(self): | |||
ds = DataSet({"xx": [[random.randint(0, 10) for _ in range(30)]] * 40}) | |||
proc = SliceProcessor(10, 20, 2, "xx", new_added_field_name="yy") | |||
ds = proc(ds) | |||
self.assertEqual(len(ds.field_arrays["yy"].content[0]), 5) | |||
def test_Num2TagProcessor(self): | |||
ds = DataSet({"num": [["99.9982", "2134.0"], ["0.002", "234"]]}) | |||
proc = Num2TagProcessor("<num>", "num") | |||
ds = proc(ds) | |||
for data in ds.field_arrays["num"].content: | |||
for d in data: | |||
self.assertEqual(d, "<num>") | |||
def test_VocabProcessor_and_IndexerProcessor(self): | |||
ds = DataSet({"xx": [[str(random.randint(0, 10)) for _ in range(30)]] * 40}) | |||
vocab_proc = VocabProcessor("xx") | |||
vocab_proc(ds) | |||
vocab = vocab_proc.vocab | |||
self.assertTrue(isinstance(vocab, Vocabulary)) | |||
self.assertTrue(len(vocab) > 5) | |||
proc = IndexerProcessor(vocab, "xx", "yy") | |||
ds = proc(ds) | |||
for data in ds.field_arrays["yy"].content[0]: | |||
self.assertTrue(isinstance(data, int)) | |||
def test_SeqLenProcessor(self): | |||
ds = DataSet({"xx": [[str(random.randint(0, 10)) for _ in range(30)]] * 10}) | |||
proc = SeqLenProcessor("xx", "len") | |||
ds = proc(ds) | |||
for data in ds.field_arrays["len"].content: | |||
self.assertEqual(data, 30) | |||
def test_ModelProcessor(self): | |||
from fastNLP.models.cnn_text_classification import CNNText | |||
model = CNNText((100, 100), 5) | |||
ins_list = [] | |||
for _ in range(64): | |||
seq_len = np.random.randint(5, 30) | |||
ins_list.append(Instance(word_seq=[np.random.randint(0, 100) for _ in range(seq_len)], seq_lens=seq_len)) | |||
data_set = DataSet(ins_list) | |||
data_set.set_input("word_seq", "seq_lens") | |||
proc = ModelProcessor(model) | |||
data_set = proc(data_set) | |||
self.assertTrue("pred" in data_set) | |||
def test_Index2WordProcessor(self): | |||
vocab = Vocabulary() | |||
vocab.add_word_lst(["a", "b", "c", "d", "e"]) | |||
proc = Index2WordProcessor(vocab, "tag_id", "tag") | |||
data_set = DataSet([Instance(tag_id=[np.random.randint(0, 7) for _ in range(32)])]) | |||
data_set = proc(data_set) | |||
self.assertTrue("tag" in data_set) | |||
def test_SetTargetProcessor(self): | |||
proc = SetTargetProcessor("a", "b", "c") | |||
data_set = DataSet({"a": [1, 2, 3], "b": [1, 2, 3], "c": [1, 2, 3]}) | |||
data_set = proc(data_set) | |||
self.assertTrue(data_set["a"].is_target) | |||
self.assertTrue(data_set["b"].is_target) | |||
self.assertTrue(data_set["c"].is_target) | |||
def test_SetInputProcessor(self): | |||
proc = SetInputProcessor("a", "b", "c") | |||
data_set = DataSet({"a": [1, 2, 3], "b": [1, 2, 3], "c": [1, 2, 3]}) | |||
data_set = proc(data_set) | |||
self.assertTrue(data_set["a"].is_input) | |||
self.assertTrue(data_set["b"].is_input) | |||
self.assertTrue(data_set["c"].is_input) | |||
def test_VocabIndexerProcessor(self): | |||
proc = VocabIndexerProcessor("word_seq", "word_ids") | |||
data_set = DataSet([Instance(word_seq=["a", "b", "c", "d", "e"])]) | |||
data_set = proc(data_set) | |||
self.assertTrue("word_ids" in data_set) |
@@ -1,111 +0,0 @@ | |||
import unittest | |||
from fastNLP import DataSet | |||
from fastNLP import Instance | |||
from fastNLP import Vocabulary | |||
from fastNLP.core.losses import CrossEntropyLoss | |||
from fastNLP.core.metrics import AccuracyMetric | |||
class TestENAS(unittest.TestCase): | |||
def testENAS(self): | |||
# 从csv读取数据到DataSet | |||
sample_path = "tutorials/sample_data/tutorial_sample_dataset.csv" | |||
dataset = DataSet.read_csv(sample_path, headers=('raw_sentence', 'label'), | |||
sep='\t') | |||
print(len(dataset)) | |||
print(dataset[0]) | |||
print(dataset[-3]) | |||
dataset.append(Instance(raw_sentence='fake data', label='0')) | |||
# 将所有数字转为小写 | |||
dataset.apply(lambda x: x['raw_sentence'].lower(), new_field_name='raw_sentence') | |||
# label转int | |||
dataset.apply(lambda x: int(x['label']), new_field_name='label') | |||
# 使用空格分割句子 | |||
def split_sent(ins): | |||
return ins['raw_sentence'].split() | |||
dataset.apply(split_sent, new_field_name='words') | |||
# 增加长度信息 | |||
dataset.apply(lambda x: len(x['words']), new_field_name='seq_len') | |||
print(len(dataset)) | |||
print(dataset[0]) | |||
# DataSet.drop(func)筛除数据 | |||
dataset.drop(lambda x: x['seq_len'] <= 3, inplace=True) | |||
print(len(dataset)) | |||
# 设置DataSet中,哪些field要转为tensor | |||
# set target,loss或evaluate中的golden,计算loss,模型评估时使用 | |||
dataset.set_target("label") | |||
# set input,模型forward时使用 | |||
dataset.set_input("words", "seq_len") | |||
# 分出测试集、训练集 | |||
test_data, train_data = dataset.split(0.5) | |||
print(len(test_data)) | |||
print(len(train_data)) | |||
# 构建词表, Vocabulary.add(word) | |||
vocab = Vocabulary(min_freq=2) | |||
train_data.apply(lambda x: [vocab.add(word) for word in x['words']]) | |||
vocab.build_vocab() | |||
# index句子, Vocabulary.to_index(word) | |||
train_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='words') | |||
test_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='words') | |||
print(test_data[0]) | |||
# 如果你们需要做强化学习或者GAN之类的项目,你们也可以使用这些数据预处理的工具 | |||
from fastNLP.core.batch import Batch | |||
from fastNLP.core.sampler import RandomSampler | |||
batch_iterator = Batch(dataset=train_data, batch_size=2, sampler=RandomSampler()) | |||
for batch_x, batch_y in batch_iterator: | |||
print("batch_x has: ", batch_x) | |||
print("batch_y has: ", batch_y) | |||
break | |||
from fastNLP.automl.enas_model import ENASModel | |||
from fastNLP.automl.enas_controller import Controller | |||
model = ENASModel(embed_num=len(vocab), num_classes=5) | |||
controller = Controller() | |||
from fastNLP.automl.enas_trainer import ENASTrainer | |||
# 更改DataSet中对应field的名称,要以模型的forward等参数名一致 | |||
train_data.rename_field('words', 'word_seq') # input field 与 forward 参数一致 | |||
train_data.rename_field('label', 'label_seq') | |||
test_data.rename_field('words', 'word_seq') | |||
test_data.rename_field('label', 'label_seq') | |||
loss = CrossEntropyLoss(pred="output", target="label_seq") | |||
metric = AccuracyMetric(pred="predict", target="label_seq") | |||
trainer = ENASTrainer(model=model, controller=controller, train_data=train_data, dev_data=test_data, | |||
loss=CrossEntropyLoss(pred="output", target="label_seq"), | |||
metrics=AccuracyMetric(pred="predict", target="label_seq"), | |||
check_code_level=-1, | |||
save_path=None, | |||
batch_size=32, | |||
print_every=1, | |||
n_epochs=3, | |||
final_epochs=1) | |||
trainer.train() | |||
print('Train finished!') | |||
# 调用Tester在test_data上评价效果 | |||
from fastNLP import Tester | |||
tester = Tester(data=test_data, model=model, metrics=AccuracyMetric(pred="predict", target="label_seq"), | |||
batch_size=4) | |||
acc = tester.test() | |||
print(acc) | |||
if __name__ == '__main__': | |||
unittest.main() |