From 720a264eb3035a2acf99a9a3d5ef096f16de75be Mon Sep 17 00:00:00 2001 From: FengZiYjun Date: Fri, 7 Dec 2018 14:53:27 +0800 Subject: [PATCH] * rename DataSet.get_fields() into get_all_fields() * add DataSet.get_field(), to fetch a FieldArray based on its name * remove old tutorials & add new tutorials --- fastNLP/api/processor.py | 4 +- fastNLP/core/batch.py | 2 +- fastNLP/core/dataset.py | 7 +- fastNLP/core/sampler.py | 2 +- fastNLP/models/cnn_text_classification.py | 6 +- test/core/test_dataset.py | 16 + .../tutorial_sample_dataset.csv | 41 +- tutorials/fastnlp_10min_tutorial_v2.ipynb | 911 ++++++++++++++++++ tutorials/fastnlp_10tmin_tutorial.ipynb | 860 +++++++++++++++++ tutorials/fastnlp_1_minute_tutorial.ipynb | 333 +++++++ ....ipynb => fastnlp_advanced_tutorial.ipynb} | 64 +- tutorials/fastnlp_tutorial_1203.ipynb | 526 ---------- tutorials/fastnlp_tutorial_1204.ipynb | 447 --------- 13 files changed, 2215 insertions(+), 1004 deletions(-) create mode 100644 tutorials/fastnlp_10min_tutorial_v2.ipynb create mode 100644 tutorials/fastnlp_10tmin_tutorial.ipynb create mode 100644 tutorials/fastnlp_1_minute_tutorial.ipynb rename tutorials/{fastnlp_in_six_lines.ipynb => fastnlp_advanced_tutorial.ipynb} (53%) delete mode 100644 tutorials/fastnlp_tutorial_1203.ipynb delete mode 100644 tutorials/fastnlp_tutorial_1204.ipynb diff --git a/fastNLP/api/processor.py b/fastNLP/api/processor.py index d6a68412..fcda3e7c 100644 --- a/fastNLP/api/processor.py +++ b/fastNLP/api/processor.py @@ -268,7 +268,7 @@ class SetTensorProcessor(Processor): self.default = default def process(self, dataset): - set_dict = {name: self.default for name in dataset.get_fields().keys()} + set_dict = {name: self.default for name in dataset.get_all_fields().keys()} set_dict.update(self.field_dict) dataset._set_need_tensor(**set_dict) return dataset @@ -282,7 +282,7 @@ class SetIsTargetProcessor(Processor): self.default = default def process(self, dataset): - set_dict = {name: self.default for name in dataset.get_fields().keys()} + set_dict = {name: self.default for name in dataset.get_all_fields().keys()} set_dict.update(self.field_dict) dataset.set_target(**set_dict) return dataset diff --git a/fastNLP/core/batch.py b/fastNLP/core/batch.py index 1e7d56fd..1bb26129 100644 --- a/fastNLP/core/batch.py +++ b/fastNLP/core/batch.py @@ -43,7 +43,7 @@ class Batch(object): indices = self.idx_list[self.curidx:endidx] - for field_name, field in self.dataset.get_fields().items(): + for field_name, field in self.dataset.get_all_fields().items(): if field.is_target or field.is_input: batch = field.get(indices) if not self.as_numpy: diff --git a/fastNLP/core/dataset.py b/fastNLP/core/dataset.py index f4963d0a..d4d285d7 100644 --- a/fastNLP/core/dataset.py +++ b/fastNLP/core/dataset.py @@ -157,7 +157,12 @@ class DataSet(object): """ self.field_arrays.pop(name) - def get_fields(self): + def get_field(self, field_name): + if field_name not in self.field_arrays: + raise KeyError("Field name {} not found in DataSet".format(field_name)) + return self.field_arrays[field_name] + + def get_all_fields(self): """Return all the fields with their names. :return dict field_arrays: the internal data structure of DataSet. diff --git a/fastNLP/core/sampler.py b/fastNLP/core/sampler.py index d568acf3..766d71a7 100644 --- a/fastNLP/core/sampler.py +++ b/fastNLP/core/sampler.py @@ -55,7 +55,7 @@ class BucketSampler(BaseSampler): def __call__(self, data_set): - seq_lens = data_set.get_fields()[self.seq_lens_field_name].content + seq_lens = data_set.get_all_fields()[self.seq_lens_field_name].content total_sample_num = len(seq_lens) bucket_indexes = [] diff --git a/fastNLP/models/cnn_text_classification.py b/fastNLP/models/cnn_text_classification.py index c8fe5181..f3898c00 100644 --- a/fastNLP/models/cnn_text_classification.py +++ b/fastNLP/models/cnn_text_classification.py @@ -44,7 +44,7 @@ class CNNText(torch.nn.Module): x = self.conv_pool(x) # [N,L,C] -> [N,C] x = self.dropout(x) x = self.fc(x) # [N,C] -> [N, N_class] - return {'output': x} + return {'pred': x} def predict(self, word_seq): """ @@ -53,5 +53,5 @@ class CNNText(torch.nn.Module): :return predict: dict of torch.LongTensor, [batch_size, seq_len] """ output = self(word_seq) - _, predict = output['output'].max(dim=1) - return {'predict': predict} + _, predict = output['pred'].max(dim=1) + return {'pred': predict} diff --git a/test/core/test_dataset.py b/test/core/test_dataset.py index 9527e8ee..74ad5958 100644 --- a/test/core/test_dataset.py +++ b/test/core/test_dataset.py @@ -2,6 +2,7 @@ import os import unittest from fastNLP.core.dataset import DataSet +from fastNLP.core.fieldarray import FieldArray from fastNLP.core.instance import Instance @@ -162,6 +163,21 @@ class TestDataSet(unittest.TestCase): ds_1 = DataSet.load("./my_ds.pkl") os.remove("my_ds.pkl") + def test_get_all_fields(self): + ds = DataSet({"x": [[1, 2, 3, 4]] * 10, "y": [[5, 6]] * 10}) + ans = ds.get_all_fields() + self.assertEqual(ans["x"].content, [[1, 2, 3, 4]] * 10) + self.assertEqual(ans["y"].content, [[5, 6]] * 10) + + def test_get_field(self): + ds = DataSet({"x": [[1, 2, 3, 4]] * 10, "y": [[5, 6]] * 10}) + ans = ds.get_field("x") + self.assertTrue(isinstance(ans, FieldArray)) + self.assertEqual(ans.content, [[1, 2, 3, 4]] * 10) + ans = ds.get_field("y") + self.assertTrue(isinstance(ans, FieldArray)) + self.assertEqual(ans.content, [[5, 6]] * 10) + class TestDataSetIter(unittest.TestCase): def test__repr__(self): diff --git a/test/data_for_tests/tutorial_sample_dataset.csv b/test/data_for_tests/tutorial_sample_dataset.csv index c3137854..e5c0a74f 100644 --- a/test/data_for_tests/tutorial_sample_dataset.csv +++ b/test/data_for_tests/tutorial_sample_dataset.csv @@ -35,4 +35,43 @@ There 's very little sense to what 's going on here , but the makers serve up th Cattaneo should have followed the runaway success of his first film , The Full Monty , with something different . 2 They 're the unnamed , easily substitutable forces that serve as whatever terror the heroes of horror movies try to avoid . 1 It almost feels as if the movie is more interested in entertaining itself than in amusing us . 1 -The movie 's progression into rambling incoherence gives new meaning to the phrase ` fatal script error . ' 0 \ No newline at end of file +The movie 's progression into rambling incoherence gives new meaning to the phrase ` fatal script error . ' 0 +I still like Moonlight Mile , better judgment be damned . 3 +A welcome relief from baseball movies that try too hard to be mythic , this one is a sweet and modest and ultimately winning story . 3 +a bilingual charmer , just like the woman who inspired it 3 +Like a less dizzily gorgeous companion to Mr. Wong 's In the Mood for Love -- very much a Hong Kong movie despite its mainland setting . 2 +As inept as big-screen remakes of The Avengers and The Wild Wild West . 1 +It 's everything you 'd expect -- but nothing more . 2 +Best indie of the year , so far . 4 +Hatfield and Hicks make the oddest of couples , and in this sense the movie becomes a study of the gambles of the publishing world , offering a case study that exists apart from all the movie 's political ramifications . 3 +It 's like going to a house party and watching the host defend himself against a frothing ex-girlfriend . 1 +That the Chuck Norris `` grenade gag '' occurs about 7 times during Windtalkers is a good indication of how serious-minded the film is . 2 +The plot is romantic comedy boilerplate from start to finish . 2 +It arrives with an impeccable pedigree , mongrel pep , and almost indecipherable plot complications . 2 +A film that clearly means to preach exclusively to the converted . 2 +I still like Moonlight Mile , better judgment be damned . 3 +A welcome relief from baseball movies that try too hard to be mythic , this one is a sweet and modest and ultimately winning story . 3 +a bilingual charmer , just like the woman who inspired it 3 +Like a less dizzily gorgeous companion to Mr. Wong 's In the Mood for Love -- very much a Hong Kong movie despite its mainland setting . 2 +As inept as big-screen remakes of The Avengers and The Wild Wild West . 1 +It 's everything you 'd expect -- but nothing more . 2 +Best indie of the year , so far . 4 +Hatfield and Hicks make the oddest of couples , and in this sense the movie becomes a study of the gambles of the publishing world , offering a case study that exists apart from all the movie 's political ramifications . 3 +It 's like going to a house party and watching the host defend himself against a frothing ex-girlfriend . 1 +That the Chuck Norris `` grenade gag '' occurs about 7 times during Windtalkers is a good indication of how serious-minded the film is . 2 +The plot is romantic comedy boilerplate from start to finish . 2 +It arrives with an impeccable pedigree , mongrel pep , and almost indecipherable plot complications . 2 +A film that clearly means to preach exclusively to the converted . 2 +I still like Moonlight Mile , better judgment be damned . 3 +A welcome relief from baseball movies that try too hard to be mythic , this one is a sweet and modest and ultimately winning story . 3 +a bilingual charmer , just like the woman who inspired it 3 +Like a less dizzily gorgeous companion to Mr. Wong 's In the Mood for Love -- very much a Hong Kong movie despite its mainland setting . 2 +As inept as big-screen remakes of The Avengers and The Wild Wild West . 1 +It 's everything you 'd expect -- but nothing more . 2 +Best indie of the year , so far . 4 +Hatfield and Hicks make the oddest of couples , and in this sense the movie becomes a study of the gambles of the publishing world , offering a case study that exists apart from all the movie 's political ramifications . 3 +It 's like going to a house party and watching the host defend himself against a frothing ex-girlfriend . 1 +That the Chuck Norris `` grenade gag '' occurs about 7 times during Windtalkers is a good indication of how serious-minded the film is . 2 +The plot is romantic comedy boilerplate from start to finish . 2 +It arrives with an impeccable pedigree , mongrel pep , and almost indecipherable plot complications . 2 +A film that clearly means to preach exclusively to the converted . 2 \ No newline at end of file diff --git a/tutorials/fastnlp_10min_tutorial_v2.ipynb b/tutorials/fastnlp_10min_tutorial_v2.ipynb new file mode 100644 index 00000000..f86e5bf3 --- /dev/null +++ b/tutorials/fastnlp_10min_tutorial_v2.ipynb @@ -0,0 +1,911 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "fastNLP上手教程\n", + "-------\n", + "\n", + "fastNLP提供方便的数据预处理，训练和测试模型的功能" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "DataSet & Instance\n", + "------\n", + "\n", + "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。\n", + "\n", + "有一些read_*方法，可以轻松从文件读取数据，存成DataSet。" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "8529" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "from fastNLP import DataSet\n", + "from fastNLP import Instance\n", + "\n", + "# 从csv读取数据到DataSet\n", + "dataset = DataSet.read_csv('../sentence.csv', headers=('raw_sentence', 'label'), sep='\\t')\n", + "print(len(dataset))" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'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 .,\n'label': 1}" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "# 使用数字索引[k]，获取第k个样本\n", + "print(dataset[0])\n", + "\n", + "# 索引也可以是负数\n", + "print(dataset[-3])" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Instance\n", + "Instance表示一个样本，由一个或多个field（域，属性，特征）组成，每个field有名字和值。\n", + "\n", + "在初始化Instance时即可定义它包含的域，使用 \"field_name=field_value\"的写法。" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'raw_sentence': fake data,\n'label': 0}" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# DataSet.append(Instance)加入新数据\n", + "dataset.append(Instance(raw_sentence='fake data', label='0'))\n", + "dataset[-1]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## DataSet.apply方法\n", + "数据预处理利器" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'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 .,\n'label': 1}" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "# 将所有数字转为小写\n", + "dataset.apply(lambda x: x['raw_sentence'].lower(), new_field_name='raw_sentence')\n", + "print(dataset[0])" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'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 .,\n'label': 1}" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "# label转int\n", + "dataset.apply(lambda x: int(x['label']), new_field_name='label')\n", + "print(dataset[0])" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'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 .,\n'label': 1,\n'words': ['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', '.']}" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "# 使用空格分割句子\n", + "def split_sent(ins):\n", + " return ins['raw_sentence'].split()\n", + "dataset.apply(split_sent, new_field_name='words')\n", + "print(dataset[0])" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'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 .,\n'label': 1,\n'words': ['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', '.'],\n'seq_len': 37}" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "# 增加长度信息\n", + "dataset.apply(lambda x: len(x['words']), new_field_name='seq_len')\n", + "print(dataset[0])" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## DataSet.drop\n", + "筛选数据" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "8358" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "dataset.drop(lambda x: x['seq_len'] <= 3)\n", + "print(len(dataset))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 配置DataSet\n", + "1. 哪些域是特征，哪些域是标签\n", + "2. 切分训练集/验证集" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [], + "source": [ + "# 设置DataSet中，哪些field要转为tensor\n", + "\n", + "# set target，loss或evaluate中的golden，计算loss，模型评估时使用\n", + "dataset.set_target(\"label\")\n", + "# set input，模型forward时使用\n", + "dataset.set_input(\"words\")" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "5851" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "2507" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "# 分出测试集、训练集\n", + "\n", + "test_data, train_data = dataset.split(0.3)\n", + "print(len(test_data))\n", + "print(len(train_data))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Vocabulary\n", + "------\n", + "\n", + "fastNLP中的Vocabulary轻松构建词表，将词转成数字" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'raw_sentence': the project 's filmmakers forgot to include anything even halfway scary as they poorly rejigger fatal attraction into a high school setting .,\n'label': 0,\n'words': [4, 423, 9, 316, 1, 8, 1, 312, 72, 1478, 885, 14, 86, 725, 1, 1913, 1431, 53, 5, 455, 736, 1, 2],\n'seq_len': 23}" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "from fastNLP import Vocabulary\n", + "\n", + "# 构建词表, Vocabulary.add(word)\n", + "vocab = Vocabulary(min_freq=2)\n", + "train_data.apply(lambda x: [vocab.add(word) for word in x['words']])\n", + "vocab.build_vocab()\n", + "\n", + "# index句子, Vocabulary.to_index(word)\n", + "train_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='words')\n", + "test_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='words')\n", + "\n", + "\n", + "print(test_data[0])" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Model\n", + "定义一个PyTorch模型" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "CNNText(\n (embed): Embedding(\n (embed): Embedding(3459, 50, padding_idx=0)\n (dropout): Dropout(p=0.0)\n )\n (conv_pool): ConvMaxpool(\n (convs): ModuleList(\n (0): Conv1d(50, 3, kernel_size=(3,), stride=(1,), padding=(2,))\n (1): Conv1d(50, 4, kernel_size=(4,), stride=(1,), padding=(2,))\n (2): Conv1d(50, 5, kernel_size=(5,), stride=(1,), padding=(2,))\n )\n )\n (dropout): Dropout(p=0.1)\n (fc): Linear(\n (linear): Linear(in_features=12, out_features=5, bias=True)\n )\n)" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from fastNLP.models import CNNText\n", + "model = CNNText(embed_num=len(vocab), embed_dim=50, num_classes=5, padding=2, dropout=0.1)\n", + "model" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "这是上述模型的forward方法。如果你不知道什么是forward方法，请参考我们的PyTorch教程。\n", + "\n", + "注意两点：\n", + "1. forward参数名字叫**word_seq**，请记住。\n", + "2. forward的返回值是一个**dict**，其中有个key的名字叫**output**。\n", + "\n", + "```Python\n", + " def forward(self, word_seq):\n", + " \"\"\"\n", + "\n", + " :param word_seq: torch.LongTensor, [batch_size, seq_len]\n", + " :return output: dict of torch.LongTensor, [batch_size, num_classes]\n", + " \"\"\"\n", + " x = self.embed(word_seq) # [N,L] -> [N,L,C]\n", + " x = self.conv_pool(x) # [N,L,C] -> [N,C]\n", + " x = self.dropout(x)\n", + " x = self.fc(x) # [N,C] -> [N, N_class]\n", + " return {'output': x}\n", + "```" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "这是上述模型的predict方法，是用来直接输出该任务的预测结果，与forward目的不同。\n", + "\n", + "注意两点：\n", + "1. predict参数名也叫**word_seq**。\n", + "2. predict的返回值是也一个**dict**，其中有个key的名字叫**predict**。\n", + "\n", + "```\n", + " def predict(self, word_seq):\n", + " \"\"\"\n", + "\n", + " :param word_seq: torch.LongTensor, [batch_size, seq_len]\n", + " :return predict: dict of torch.LongTensor, [batch_size, seq_len]\n", + " \"\"\"\n", + " output = self(word_seq)\n", + " _, predict = output['output'].max(dim=1)\n", + " return {'predict': predict}\n", + "```" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Trainer & Tester\n", + "------\n", + "\n", + "使用fastNLP的Trainer训练模型" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [], + "source": [ + "from fastNLP import Trainer\n", + "from copy import deepcopy\n", + "from fastNLP.core.losses import CrossEntropyLoss\n", + "from fastNLP.core.metrics import AccuracyMetric\n", + "\n", + "\n", + "# 更改DataSet中对应field的名称，与模型的forward的参数名一致\n", + "# 因为forward的参数叫word_seq, 所以要把原本叫words的field改名为word_seq\n", + "# 这里的演示是让你了解这种**命名规则**\n", + "train_data.rename_field('words', 'word_seq')\n", + "test_data.rename_field('words', 'word_seq')\n", + "\n", + "# 顺便把label换名为label_seq\n", + "train_data.rename_field('label', 'label_seq')\n", + "test_data.rename_field('label', 'label_seq')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### loss\n", + "训练模型需要提供一个损失函数\n", + "\n", + "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**。\n", + "\n", + "pred参数对应的是模型的forward返回的dict的一个key的名字，这里是\"output\"。\n", + "\n", + "target参数对应的是dataset作为标签的field的名字，这里是\"label_seq\"。" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "outputs": [], + "source": [ + "loss = CrossEntropyLoss(pred=\"output\", target=\"label_seq\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Metric\n", + "定义评价指标\n", + "\n", + "这里使用准确率。参数的“命名规则”跟上面类似。\n", + "\n", + "pred参数对应的是模型的predict方法返回的dict的一个key的名字，这里是\"predict\"。\n", + "\n", + "target参数对应的是dataset作为标签的field的名字，这里是\"label_seq\"。" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": {}, + "outputs": [], + "source": [ + "metric = AccuracyMetric(pred=\"predict\", target=\"label_seq\")" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "training epochs started 2018-12-07 14:11:31" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "data": { + "text/plain": [ + "HBox(children=(IntProgress(value=0, layout=Layout(flex='2'), max=915), HTML(value='')), layout=Layout(display=…" + ] + }, + "execution_count": 0, + "metadata": {}, + "output_type": "execute_result" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/5. Step:183/915. AccuracyMetric: acc=0.350367" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 2/5. Step:366/915. AccuracyMetric: acc=0.409332" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 3/5. Step:549/915. AccuracyMetric: acc=0.572552" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 4/5. Step:732/915. AccuracyMetric: acc=0.711331" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 5/5. Step:915/915. AccuracyMetric: acc=0.801572" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + } + ], + "source": [ + "# 实例化Trainer，传入模型和数据，进行训练\n", + "# 先在test_data拟合\n", + "copy_model = deepcopy(model)\n", + "overfit_trainer = Trainer(model=copy_model, train_data=test_data, dev_data=test_data,\n", + " loss=loss,\n", + " metrics=metric,\n", + " save_path=None,\n", + " batch_size=32,\n", + " n_epochs=5)\n", + "overfit_trainer.train()" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "training epochs started 2018-12-07 14:12:21" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "data": { + "text/plain": [ + "HBox(children=(IntProgress(value=0, layout=Layout(flex='2'), max=395), HTML(value='')), layout=Layout(display=…" + ] + }, + "execution_count": 0, + "metadata": {}, + "output_type": "execute_result" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/5. Step:79/395. AccuracyMetric: acc=0.250043" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 2/5. Step:158/395. AccuracyMetric: acc=0.280807" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 3/5. Step:237/395. AccuracyMetric: acc=0.280978" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 4/5. Step:316/395. AccuracyMetric: acc=0.285592" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 5/5. Step:395/395. AccuracyMetric: acc=0.278927" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + } + ], + "source": [ + "# 用train_data训练，在test_data验证\n", + "trainer = Trainer(model=model, train_data=train_data, dev_data=test_data,\n", + " loss=CrossEntropyLoss(pred=\"output\", target=\"label_seq\"),\n", + " metrics=AccuracyMetric(pred=\"predict\", target=\"label_seq\"),\n", + " save_path=None,\n", + " batch_size=32,\n", + " n_epochs=5)\n", + "trainer.train()\n", + "print('Train finished!')" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[tester] \nAccuracyMetric: acc=0.280636" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'AccuracyMetric': {'acc': 0.280636}}" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "# 调用Tester在test_data上评价效果\n", + "from fastNLP import Tester\n", + "\n", + "tester = Tester(data=test_data, model=model, metrics=AccuracyMetric(pred=\"predict\", target=\"label_seq\"),\n", + " batch_size=4)\n", + "acc = tester.test()\n", + "print(acc)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.7" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/tutorials/fastnlp_10tmin_tutorial.ipynb b/tutorials/fastnlp_10tmin_tutorial.ipynb new file mode 100644 index 00000000..bad29f55 --- /dev/null +++ b/tutorials/fastnlp_10tmin_tutorial.ipynb @@ -0,0 +1,860 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "fastNLP上手教程\n", + "-------\n", + "\n", + "fastNLP提供方便的数据预处理，训练和测试模型的功能" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "DataSet & Instance\n", + "------\n", + "\n", + "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。\n", + "\n", + "有一些read_*方法，可以轻松从文件读取数据，存成DataSet。" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'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 .,\n'label': 1}" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "from fastNLP import DataSet\n", + "from fastNLP import Instance\n", + "\n", + "# 从csv读取数据到DataSet\n", + "win_path = \"C:\\\\Users\\zyfeng\\Desktop\\FudanNLP\\\\fastNLP\\\\test\\\\data_for_tests\\\\tutorial_sample_dataset.csv\"\n", + "dataset = DataSet.read_csv(win_path, headers=('raw_sentence', 'label'), sep='\\t')\n", + "print(dataset[0])" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'raw_sentence': fake data,\n'label': 0}" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# DataSet.append(Instance)加入新数据\n", + "\n", + "dataset.append(Instance(raw_sentence='fake data', label='0'))\n", + "dataset[-1]" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "# DataSet.apply(func, new_field_name)对数据预处理\n", + "\n", + "# 将所有数字转为小写\n", + "dataset.apply(lambda x: x['raw_sentence'].lower(), new_field_name='raw_sentence')\n", + "# label转int\n", + "dataset.apply(lambda x: int(x['label']), new_field_name='label_seq', is_target=True)\n", + "# 使用空格分割句子\n", + "dataset.drop(lambda x: len(x['raw_sentence'].split()) == 0)\n", + "def split_sent(ins):\n", + " return ins['raw_sentence'].split()\n", + "dataset.apply(split_sent, new_field_name='words', is_input=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [], + "source": [ + "# DataSet.drop(func)筛除数据\n", + "# 删除低于某个长度的词语\n", + "dataset.drop(lambda x: len(x['words']) <= 3)" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Train size: " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + " " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "54" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Test size: " + ] + } + ], + "source": [ + "# 分出测试集、训练集\n", + "\n", + "test_data, train_data = dataset.split(0.3)\n", + "print(\"Train size: \", len(test_data))\n", + "print(\"Test size: \", len(train_data))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Vocabulary\n", + "------\n", + "\n", + "fastNLP中的Vocabulary轻松构建词表，将词转成数字" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'raw_sentence': the plot is romantic comedy boilerplate from start to finish .,\n'label': 2,\n'label_seq': 2,\n'words': ['the', 'plot', 'is', 'romantic', 'comedy', 'boilerplate', 'from', 'start', 'to', 'finish', '.'],\n'word_seq': [2, 13, 9, 24, 25, 26, 15, 27, 11, 28, 3]}" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "from fastNLP import Vocabulary\n", + "\n", + "# 构建词表, Vocabulary.add(word)\n", + "vocab = Vocabulary(min_freq=2)\n", + "train_data.apply(lambda x: [vocab.add(word) for word in x['words']])\n", + "vocab.build_vocab()\n", + "\n", + "# index句子, Vocabulary.to_index(word)\n", + "train_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='word_seq', is_input=True)\n", + "test_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='word_seq', is_input=True)\n", + "\n", + "\n", + "print(test_data[0])" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "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', '.']),\n", + " list(['the', 'entire', 'movie', 'is', 'filled', 'with', 'deja', 'vu', 'moments', '.'])],\n", + " dtype=object), 'word_seq': tensor([[ 19, 184, 6, 1, 481, 9, 206, 50, 91, 1210, 1609, 1330,\n", + " 495, 5, 63, 4, 1269, 4, 1, 1184, 7, 50, 1050, 10,\n", + " 8, 1611, 16, 21, 1039, 1, 2],\n", + " [ 3, 711, 22, 9, 1282, 16, 2482, 2483, 200, 2, 0, 0,\n", + " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", + " 0, 0, 0, 0, 0, 0, 0]])}\n", + "batch_y has: {'label_seq': tensor([3, 2])}\n" + ] + } + ], + "source": [ + "# 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\n", + "from fastNLP.core.batch import Batch\n", + "from fastNLP.core.sampler import RandomSampler\n", + "\n", + "batch_iterator = Batch(dataset=train_data, batch_size=2, sampler=RandomSampler())\n", + "for batch_x, batch_y in batch_iterator:\n", + " print(\"batch_x has: \", batch_x)\n", + " print(\"batch_y has: \", batch_y)\n", + " break" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Model\n" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "CNNText(\n (embed): Embedding(\n (embed): Embedding(77, 50, padding_idx=0)\n (dropout): Dropout(p=0.0)\n )\n (conv_pool): ConvMaxpool(\n (convs): ModuleList(\n (0): Conv1d(50, 3, kernel_size=(3,), stride=(1,), padding=(2,))\n (1): Conv1d(50, 4, kernel_size=(4,), stride=(1,), padding=(2,))\n (2): Conv1d(50, 5, kernel_size=(5,), stride=(1,), padding=(2,))\n )\n )\n (dropout): Dropout(p=0.1)\n (fc): Linear(\n (linear): Linear(in_features=12, out_features=5, bias=True)\n )\n)" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 定义一个简单的Pytorch模型\n", + "\n", + "from fastNLP.models import CNNText\n", + "model = CNNText(embed_num=len(vocab), embed_dim=50, num_classes=5, padding=2, dropout=0.1)\n", + "model" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Trainer & Tester\n", + "------\n", + "\n", + "使用fastNLP的Trainer训练模型" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [], + "source": [ + "from fastNLP import Trainer\n", + "from copy import deepcopy\n", + "from fastNLP import CrossEntropyLoss\n", + "from fastNLP import AccuracyMetric" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "training epochs started 2018-12-07 14:07:20" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "data": { + "text/plain": [ + "HBox(children=(IntProgress(value=0, layout=Layout(flex='2'), max=20), HTML(value='')), layout=Layout(display='…" + ] + }, + "execution_count": 0, + "metadata": {}, + "output_type": "execute_result" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/10. Step:2/20. AccuracyMetric: acc=0.037037" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 2/10. Step:4/20. AccuracyMetric: acc=0.296296" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 3/10. Step:6/20. AccuracyMetric: acc=0.333333" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 4/10. Step:8/20. AccuracyMetric: acc=0.555556" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 5/10. Step:10/20. AccuracyMetric: acc=0.611111" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 6/10. Step:12/20. AccuracyMetric: acc=0.481481" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 7/10. Step:14/20. AccuracyMetric: acc=0.62963" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 8/10. Step:16/20. AccuracyMetric: acc=0.685185" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 9/10. Step:18/20. AccuracyMetric: acc=0.722222" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 10/10. Step:20/20. AccuracyMetric: acc=0.777778" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + } + ], + "source": [ + "# 进行overfitting测试\n", + "copy_model = deepcopy(model)\n", + "overfit_trainer = Trainer(model=copy_model, \n", + " train_data=test_data, \n", + " dev_data=test_data,\n", + " loss=CrossEntropyLoss(pred=\"output\", target=\"label_seq\"),\n", + " metrics=AccuracyMetric(),\n", + " n_epochs=10,\n", + " save_path=None)\n", + "overfit_trainer.train()" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "training epochs started 2018-12-07 14:08:10" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "data": { + "text/plain": [ + "HBox(children=(IntProgress(value=0, layout=Layout(flex='2'), max=5), HTML(value='')), layout=Layout(display='i…" + ] + }, + "execution_count": 0, + "metadata": {}, + "output_type": "execute_result" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/5. Step:1/5. AccuracyMetric: acc=0.037037" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 2/5. Step:2/5. AccuracyMetric: acc=0.037037" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 3/5. Step:3/5. AccuracyMetric: acc=0.037037" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 4/5. Step:4/5. AccuracyMetric: acc=0.185185" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 5/5. Step:5/5. AccuracyMetric: acc=0.240741" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Train finished!" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "# 实例化Trainer，传入模型和数据，进行训练\n", + "trainer = Trainer(model=model, \n", + " train_data=train_data, \n", + " dev_data=test_data,\n", + " loss=CrossEntropyLoss(pred=\"output\", target=\"label_seq\"),\n", + " metrics=AccuracyMetric(),\n", + " n_epochs=5)\n", + "trainer.train()\n", + "print('Train finished!')" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[tester] \nAccuracyMetric: acc=0.240741" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "from fastNLP import Tester\n", + "\n", + "tester = Tester(data=test_data, model=model, metrics=AccuracyMetric())\n", + "acc = tester.test()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# In summary\n", + "\n", + "## fastNLP Trainer的伪代码逻辑\n", + "### 1. 准备DataSet，假设DataSet中共有如下的fields\n", + " ['raw_sentence', 'word_seq1', 'word_seq2', 'raw_label','label']\n", + " 通过\n", + " DataSet.set_input('word_seq1', word_seq2', flag=True)将'word_seq1', 'word_seq2'设置为input\n", + " 通过\n", + " DataSet.set_target('label', flag=True)将'label'设置为target\n", + "### 2. 初始化模型\n", + " class Model(nn.Module):\n", + " def __init__(self):\n", + " xxx\n", + " def forward(self, word_seq1, word_seq2):\n", + " # (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\n", + " # (2) input field的数量可以多于这里的形参数量。但是不能少于。\n", + " xxxx\n", + " # 输出必须是一个dict\n", + "### 3. Trainer的训练过程\n", + " (1) 从DataSet中按照batch_size取出一个batch，调用Model.forward\n", + " (2) 将 Model.forward的结果 与 标记为target的field 传入Losser当中。\n", + " 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}; \n", + " 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；\n", + " 为了解决以上的问题，我们的loss提供映射机制\n", + " 比如CrossEntropyLosser的需要的输入是(prediction, target)。但是forward的output是{'output': xxx}; 'label'是target\n", + " 那么初始化losser的时候写为CrossEntropyLosser(prediction='output', target='label')即可\n", + " (3) 对于Metric是同理的\n", + " 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 \n", + " \n", + " \n", + "\n", + "## 一些问题.\n", + "### 1. DataSet中为什么需要设置input和target\n", + " 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\n", + " (1.1) 我们只会在设置为input的field中寻找传递给Model.forward的参数。\n", + " (1.2) 我们在传递值给losser或者metric的时候会使用来自: \n", + " (a)Model.forward的output\n", + " (b)被设置为target的field\n", + " \n", + "\n", + "### 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\n", + " (1.1) 构建模型过程中，\n", + " 例如:\n", + " DataSet中x，seq_lens是input，那么forward就应该是\n", + " def forward(self, x, seq_lens):\n", + " pass\n", + " 我们是通过形参名称进行匹配的field的\n", + " \n", + "\n", + "\n", + "### 1. 加载数据到DataSet\n", + "### 2. 使用apply操作对DataSet进行预处理\n", + " (2.1) 处理过程中将某些field设置为input，某些field设置为target\n", + "### 3. 构建模型\n", + " (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。\n", + " 例如:\n", + " DataSet中x，seq_lens是input，那么forward就应该是\n", + " def forward(self, x, seq_lens):\n", + " pass\n", + " 我们是通过形参名称进行匹配的field的\n", + " (3.2) 模型的forward的output需要是dict类型的。\n", + " 建议将输出设置为{\"pred\": xx}.\n", + " \n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.7" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/tutorials/fastnlp_1_minute_tutorial.ipynb b/tutorials/fastnlp_1_minute_tutorial.ipynb new file mode 100644 index 00000000..e584a405 --- /dev/null +++ b/tutorials/fastnlp_1_minute_tutorial.ipynb @@ -0,0 +1,333 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "collapsed": true + }, + "source": [ + "# FastNLP 1分钟上手教程" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## step 1\n", + "读取数据集" + ] + }, + { + "cell_type": "code", + "execution_count": 50, + "metadata": {}, + "outputs": [], + "source": [ + "from fastNLP import DataSet\n", + "# linux_path = \"../test/data_for_tests/tutorial_sample_dataset.csv\"\n", + "win_path = \"C:\\\\Users\\zyfeng\\Desktop\\FudanNLP\\\\fastNLP\\\\test\\\\data_for_tests\\\\tutorial_sample_dataset.csv\"\n", + "ds = DataSet.read_csv(win_path, headers=('raw_sentence', 'label'), sep='\\t')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## step 2\n", + "数据预处理\n", + "1. 类型转换\n", + "2. 切分验证集\n", + "3. 构建词典" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": {}, + "outputs": [], + "source": [ + "# 将所有数字转为小写\n", + "ds.apply(lambda x: x['raw_sentence'].lower(), new_field_name='raw_sentence')\n", + "# label转int\n", + "ds.apply(lambda x: int(x['label']), new_field_name='label_seq', is_target=True)\n", + "\n", + "def split_sent(ins):\n", + " return ins['raw_sentence'].split()\n", + "ds.apply(split_sent, new_field_name='words', is_input=True)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Train size: " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + " " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "54" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Test size: " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + " " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "23" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "# 分割训练集/验证集\n", + "train_data, dev_data = ds.split(0.3)\n", + "print(\"Train size: \", len(train_data))\n", + "print(\"Test size: \", len(dev_data))" + ] + }, + { + "cell_type": "code", + "execution_count": 61, + "metadata": {}, + "outputs": [], + "source": [ + "from fastNLP import Vocabulary\n", + "vocab = Vocabulary(min_freq=2)\n", + "train_data.apply(lambda x: [vocab.add(word) for word in x['words']])\n", + "\n", + "# index句子, Vocabulary.to_index(word)\n", + "train_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='word_seq', is_input=True)\n", + "dev_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='word_seq', is_input=True)\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## step 3\n", + " 定义模型" + ] + }, + { + "cell_type": "code", + "execution_count": 62, + "metadata": {}, + "outputs": [], + "source": [ + "from fastNLP.models import CNNText\n", + "model = CNNText(embed_num=len(vocab), embed_dim=50, num_classes=5, padding=2, dropout=0.1)\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## step 4\n", + "开始训练" + ] + }, + { + "cell_type": "code", + "execution_count": 63, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "training epochs started 2018-12-07 14:03:41" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "data": { + "text/plain": [ + "HBox(children=(IntProgress(value=0, layout=Layout(flex='2'), max=6), HTML(value='')), layout=Layout(display='i…" + ] + }, + "execution_count": 0, + "metadata": {}, + "output_type": "execute_result" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/3. Step:2/6. AccuracyMetric: acc=0.26087" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 2/3. Step:4/6. AccuracyMetric: acc=0.347826" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 3/3. Step:6/6. AccuracyMetric: acc=0.608696" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Train finished!" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n" + ] + } + ], + "source": [ + "from fastNLP import Trainer, CrossEntropyLoss, AccuracyMetric\n", + "trainer = Trainer(model=model, \n", + " train_data=train_data, \n", + " dev_data=dev_data,\n", + " loss=CrossEntropyLoss(),\n", + " metrics=AccuracyMetric()\n", + " )\n", + "trainer.train()\n", + "print('Train finished!')\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 本教程结束。更多操作请参考进阶教程。" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 2", + "language": "python", + "name": "python2" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.6" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} diff --git a/tutorials/fastnlp_in_six_lines.ipynb b/tutorials/fastnlp_advanced_tutorial.ipynb similarity index 53% rename from tutorials/fastnlp_in_six_lines.ipynb rename to tutorials/fastnlp_advanced_tutorial.ipynb index 2d8f40d7..c1322ab8 100644 --- a/tutorials/fastnlp_in_six_lines.ipynb +++ b/tutorials/fastnlp_advanced_tutorial.ipynb @@ -6,48 +6,68 @@ "collapsed": true }, "source": [ - "# 六行代码搞定FastNLP" + "## FastNLP 进阶教程\n", + "本教程阅读时间平均30分钟" ] }, { - "cell_type": "code", - "execution_count": null, + "cell_type": "markdown", "metadata": {}, - "outputs": [], "source": [ - "from fastNLP.core.dataset import DataSet\n", - "import fastNLP.io.dataset_loader" + "## 数据部分\n", + "### DataSet\n" ] }, { - "cell_type": "code", - "execution_count": null, + "cell_type": "markdown", "metadata": {}, - "outputs": [], "source": [ - "ds = DataSet.read_naive(\"../test/data_for_tests/tutorial_sample_dataset.csv\")" + "### Instance" ] }, { - "cell_type": "code", - "execution_count": null, + "cell_type": "markdown", "metadata": {}, - "outputs": [], - "source": [] + "source": [ + "### Vocabulary" + ] }, { - "cell_type": "code", - "execution_count": null, + "cell_type": "markdown", "metadata": {}, - "outputs": [], - "source": [] + "source": [ + "## 模型部分\n", + "### model" + ] }, { - "cell_type": "code", - "execution_count": null, + "cell_type": "markdown", "metadata": {}, - "outputs": [], - "source": [] + "source": [ + "## 训练测试部分\n", + "### Loss" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Metric" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Trainer" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Tester" + ] }, { "cell_type": "code", diff --git a/tutorials/fastnlp_tutorial_1203.ipynb b/tutorials/fastnlp_tutorial_1203.ipynb deleted file mode 100644 index cb8fa6a0..00000000 --- a/tutorials/fastnlp_tutorial_1203.ipynb +++ /dev/null @@ -1,526 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "fastNLP上手教程\n", - "-------\n", - "\n", - "fastNLP提供方便的数据预处理，训练和测试模型的功能" - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/Users/yh/miniconda2/envs/python3/lib/python3.6/site-packages/tqdm/autonotebook/__init__.py:14: TqdmExperimentalWarning: Using `tqdm.autonotebook.tqdm` in notebook mode. Use `tqdm.tqdm` instead to force console mode (e.g. in jupyter console)\n", - " \" (e.g. in jupyter console)\", TqdmExperimentalWarning)\n" - ] - } - ], - "source": [ - "import sys\n", - "sys.path.append('/Users/yh/Desktop/fastNLP/fastNLP/')\n", - "\n", - "import fastNLP as fnlp" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "DataSet & Instance\n", - "------\n", - "\n", - "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。\n", - "\n", - "有一些read_*方法，可以轻松从文件读取数据，存成DataSet。" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "{'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 .,\n", - "'label': 1}\n" - ] - } - ], - "source": [ - "from fastNLP import DataSet\n", - "from fastNLP import Instance\n", - "\n", - "# 从csv读取数据到DataSet\n", - "dataset = DataSet.read_csv('sentence.csv', headers=('raw_sentence', 'label'), sep='\\t')\n", - "print(dataset[0])" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "{'raw_sentence': fake data,\n", - "'label': 0}" - ] - }, - "execution_count": 3, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# DataSet.append(Instance)加入新数据\n", - "\n", - "dataset.append(Instance(raw_sentence='fake data', label='0'))\n", - "dataset[-1]" - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "metadata": {}, - "outputs": [], - "source": [ - "# DataSet.apply(func, new_field_name)对数据预处理\n", - "\n", - "# 将所有数字转为小写\n", - "dataset.apply(lambda x: x['raw_sentence'].lower(), new_field_name='raw_sentence')\n", - "# label转int\n", - "dataset.apply(lambda x: int(x['label']), new_field_name='label_seq', is_target=True)\n", - "# 使用空格分割句子\n", - "dataset.drop(lambda x:len(x['raw_sentence'].split())==0)\n", - "def split_sent(ins):\n", - " return ins['raw_sentence'].split()\n", - "dataset.apply(split_sent, new_field_name='words', is_input=True)" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "metadata": {}, - "outputs": [], - "source": [ - "# DataSet.drop(func)筛除数据\n", - "# 删除低于某个长度的词语\n", - "# dataset.drop(lambda x: len(x['words']) <= 3)" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Train size: 5971\n", - "Test size: 2558\n" - ] - } - ], - "source": [ - "# 分出测试集、训练集\n", - "\n", - "test_data, train_data = dataset.split(0.3)\n", - "print(\"Train size: \", len(test_data))\n", - "print(\"Test size: \", len(train_data))" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Vocabulary\n", - "------\n", - "\n", - "fastNLP中的Vocabulary轻松构建词表，将词转成数字" - ] - }, - { - "cell_type": "code", - "execution_count": 7, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "{'raw_sentence': gussied up with so many distracting special effects and visual party tricks that it 's not clear whether we 're supposed to shriek or laugh .,\n", - "'label': 1,\n", - "'label_seq': 1,\n", - "'words': ['gussied', 'up', 'with', 'so', 'many', 'distracting', 'special', 'effects', 'and', 'visual', 'party', 'tricks', 'that', 'it', \"'s\", 'not', 'clear', 'whether', 'we', \"'re\", 'supposed', 'to', 'shriek', 'or', 'laugh', '.'],\n", - "'word_seq': [1, 65, 16, 43, 108, 1, 329, 433, 7, 319, 1313, 1, 12, 10, 11, 27, 1428, 567, 86, 134, 1949, 8, 1, 49, 506, 2]}\n" - ] - } - ], - "source": [ - "from fastNLP import Vocabulary\n", - "\n", - "# 构建词表, Vocabulary.add(word)\n", - "vocab = Vocabulary(min_freq=2)\n", - "train_data.apply(lambda x: [vocab.add(word) for word in x['words']])\n", - "vocab.build_vocab()\n", - "\n", - "# index句子, Vocabulary.to_index(word)\n", - "train_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='word_seq', is_input=True)\n", - "test_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='word_seq', is_input=True)\n", - "\n", - "\n", - "print(test_data[0])" - ] - }, - { - "cell_type": "code", - "execution_count": 8, - "metadata": { - "scrolled": true - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "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', '.']),\n", - " list(['the', 'entire', 'movie', 'is', 'filled', 'with', 'deja', 'vu', 'moments', '.'])],\n", - " dtype=object), 'word_seq': tensor([[ 19, 184, 6, 1, 481, 9, 206, 50, 91, 1210, 1609, 1330,\n", - " 495, 5, 63, 4, 1269, 4, 1, 1184, 7, 50, 1050, 10,\n", - " 8, 1611, 16, 21, 1039, 1, 2],\n", - " [ 3, 711, 22, 9, 1282, 16, 2482, 2483, 200, 2, 0, 0,\n", - " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n", - " 0, 0, 0, 0, 0, 0, 0]])}\n", - "batch_y has: {'label_seq': tensor([3, 2])}\n" - ] - } - ], - "source": [ - "# 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\n", - "from fastNLP.core.batch import Batch\n", - "from fastNLP.core.sampler import RandomSampler\n", - "\n", - "batch_iterator = Batch(dataset=train_data, batch_size=2, sampler=RandomSampler())\n", - "for batch_x, batch_y in batch_iterator:\n", - " print(\"batch_x has: \", batch_x)\n", - " print(\"batch_y has: \", batch_y)\n", - " break" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "# Model\n" - ] - }, - { - "cell_type": "code", - "execution_count": 9, - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "CNNText(\n", - " (embed): Embedding(\n", - " (embed): Embedding(3470, 50, padding_idx=0)\n", - " (dropout): Dropout(p=0.0)\n", - " )\n", - " (conv_pool): ConvMaxpool(\n", - " (convs): ModuleList(\n", - " (0): Conv1d(50, 3, kernel_size=(3,), stride=(1,), padding=(2,))\n", - " (1): Conv1d(50, 4, kernel_size=(4,), stride=(1,), padding=(2,))\n", - " (2): Conv1d(50, 5, kernel_size=(5,), stride=(1,), padding=(2,))\n", - " )\n", - " )\n", - " (dropout): Dropout(p=0.1)\n", - " (fc): Linear(\n", - " (linear): Linear(in_features=12, out_features=5, bias=True)\n", - " )\n", - ")" - ] - }, - "execution_count": 9, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# 定义一个简单的Pytorch模型\n", - "\n", - "from fastNLP.models import CNNText\n", - "model = CNNText(embed_num=len(vocab), embed_dim=50, num_classes=5, padding=2, dropout=0.1)\n", - "model" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Trainer & Tester\n", - "------\n", - "\n", - "使用fastNLP的Trainer训练模型" - ] - }, - { - "cell_type": "code", - "execution_count": 10, - "metadata": {}, - "outputs": [], - "source": [ - "from fastNLP import Trainer\n", - "from copy import deepcopy\n", - "from fastNLP.core.losses import CrossEntropyLoss\n", - "from fastNLP.core.metrics import AccuracyMetric" - ] - }, - { - "cell_type": "code", - "execution_count": 11, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "training epochs started 2018-12-05 15:37:15\n" - ] - }, - { - "data": { - "text/plain": [ - "HBox(children=(IntProgress(value=0, layout=Layout(flex='2'), max=1870), HTML(value='')), layout=Layout(display…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 1/10. Step:187/1870. AccuracyMetric: acc=0.351365\n", - "Epoch 2/10. Step:374/1870. AccuracyMetric: acc=0.470943\n", - "Epoch 3/10. Step:561/1870. AccuracyMetric: acc=0.600402\n", - "Epoch 4/10. Step:748/1870. AccuracyMetric: acc=0.702227\n", - "Epoch 5/10. Step:935/1870. AccuracyMetric: acc=0.79099\n", - "Epoch 6/10. Step:1122/1870. AccuracyMetric: acc=0.846424\n", - "Epoch 7/10. Step:1309/1870. AccuracyMetric: acc=0.874058\n", - "Epoch 8/10. Step:1496/1870. AccuracyMetric: acc=0.898844\n", - "Epoch 9/10. Step:1683/1870. AccuracyMetric: acc=0.910568\n", - "Epoch 10/10. Step:1870/1870. AccuracyMetric: acc=0.921286\n", - "\r" - ] - } - ], - "source": [ - "# 进行overfitting测试\n", - "copy_model = deepcopy(model)\n", - "overfit_trainer = Trainer(model=copy_model, \n", - " train_data=test_data, \n", - " dev_data=test_data,\n", - " losser=CrossEntropyLoss(pred=\"output\", target=\"label_seq\"),\n", - " metrics=AccuracyMetric(),\n", - " n_epochs=10,\n", - " save_path=None)\n", - "overfit_trainer.train()" - ] - }, - { - "cell_type": "code", - "execution_count": 12, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "training epochs started 2018-12-05 15:37:41\n" - ] - }, - { - "data": { - "text/plain": [ - "HBox(children=(IntProgress(value=0, layout=Layout(flex='2'), max=400), HTML(value='')), layout=Layout(display=…" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r" - ] - }, - { - "ename": "AttributeError", - "evalue": "'NoneType' object has no attribute 'squeeze'", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 7\u001b[0m \u001b[0mn_epochs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m5\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 8\u001b[0m save_path='save/')\n\u001b[0;32m----> 9\u001b[0;31m \u001b[0mtrainer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 10\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Train finished!'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/Desktop/fastNLP/fastNLP/fastNLP/core/trainer.py\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 163\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_summary_writer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mSummaryWriter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 164\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0muse_tqdm\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 165\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_tqdm_train\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 166\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 167\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_print_train\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/Desktop/fastNLP/fastNLP/fastNLP/core/trainer.py\u001b[0m in \u001b[0;36m_tqdm_train\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 206\u001b[0m \u001b[0mpbar\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0meval_str\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 207\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalidate_every\u001b[0m \u001b[0;34m<\u001b[0m \u001b[0;36m0\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdev_data\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 208\u001b[0;31m \u001b[0meval_res\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_do_validation\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 209\u001b[0m \u001b[0meval_str\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"Epoch {}/{}. Step:{}/{}. \"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mepoch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mn_epochs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtotal_steps\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m+\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m\\\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 210\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtester\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_format_eval_results\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0meval_res\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/Desktop/fastNLP/fastNLP/fastNLP/core/trainer.py\u001b[0m in \u001b[0;36m_do_validation\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 265\u001b[0m \u001b[0mres\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtester\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtest\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 266\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnum\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mres\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 267\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_summary_writer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd_scalar\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"valid_{}\"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnum\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mglobal_step\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 268\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_path\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_better_eval_result\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mres\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 269\u001b[0m \u001b[0mmetric_key\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmetric_key\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmetric_key\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0;34m\"None\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/miniconda2/envs/python3/lib/python3.6/site-packages/tensorboardX/writer.py\u001b[0m in \u001b[0;36madd_scalar\u001b[0;34m(self, tag, scalar_value, global_step, walltime)\u001b[0m\n\u001b[1;32m 332\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_check_caffe2\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mscalar_value\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 333\u001b[0m \u001b[0mscalar_value\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mworkspace\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mFetchBlob\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mscalar_value\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 334\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfile_writer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd_summary\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mscalar\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtag\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mscalar_value\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mglobal_step\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwalltime\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 335\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 336\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0madd_scalars\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmain_tag\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtag_scalar_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mglobal_step\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwalltime\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/miniconda2/envs/python3/lib/python3.6/site-packages/tensorboardX/summary.py\u001b[0m in \u001b[0;36mscalar\u001b[0;34m(name, scalar, collections)\u001b[0m\n\u001b[1;32m 115\u001b[0m \u001b[0mname\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_clean_tag\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 116\u001b[0m \u001b[0mscalar\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmake_np\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mscalar\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 117\u001b[0;31m \u001b[0;32massert\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mscalar\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msqueeze\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'scalar should be 0D'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 118\u001b[0m \u001b[0mscalar\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfloat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mscalar\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 119\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mSummary\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mSummary\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mValue\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtag\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msimple_value\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mscalar\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mAttributeError\u001b[0m: 'NoneType' object has no attribute 'squeeze'" - ], - "output_type": "error" - } - ], - "source": [ - "# 实例化Trainer，传入模型和数据，进行训练\n", - "trainer = Trainer(model=model, \n", - " train_data=train_data, \n", - " dev_data=test_data,\n", - " losser=CrossEntropyLoss(pred=\"output\", target=\"label_seq\"),\n", - " metrics=AccuracyMetric(),\n", - " n_epochs=5,\n", - " save_path='save/')\n", - "trainer.train()\n", - "print('Train finished!')" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "from fastNLP import Tester\n", - "\n", - "tester = Tester(data=test_data, model=model, metrics=AccuracyMetric())\n", - "acc = tester.test()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "# In summary\n", - "\n", - "## fastNLP Trainer的伪代码逻辑\n", - "### 1. 准备DataSet，假设DataSet中共有如下的fields\n", - " ['raw_sentence', 'word_seq1', 'word_seq2', 'raw_label','label']\n", - " 通过\n", - " DataSet.set_input('word_seq1', word_seq2', flag=True)将'word_seq1', 'word_seq2'设置为input\n", - " 通过\n", - " DataSet.set_target('label', flag=True)将'label'设置为target\n", - "### 2. 初始化模型\n", - " class Model(nn.Module):\n", - " def __init__(self):\n", - " xxx\n", - " def forward(self, word_seq1, word_seq2):\n", - " # (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\n", - " # (2) input field的数量可以多于这里的形参数量。但是不能少于。\n", - " xxxx\n", - " # 输出必须是一个dict\n", - "### 3. Trainer的训练过程\n", - " (1) 从DataSet中按照batch_size取出一个batch，调用Model.forward\n", - " (2) 将 Model.forward的结果 与 标记为target的field 传入Losser当中。\n", - " 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}; \n", - " 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；\n", - " 为了解决以上的问题，我们的loss提供映射机制\n", - " 比如CrossEntropyLosser的需要的输入是(prediction, target)。但是forward的output是{'output': xxx}; 'label'是target\n", - " 那么初始化losser的时候写为CrossEntropyLosser(prediction='output', target='label')即可\n", - " (3) 对于Metric是同理的\n", - " 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 \n", - " \n", - " \n", - "\n", - "## 一些问题.\n", - "### 1. DataSet中为什么需要设置input和target\n", - " 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\n", - " (1.1) 我们只会在设置为input的field中寻找传递给Model.forward的参数。\n", - " (1.2) 我们在传递值给losser或者metric的时候会使用来自: \n", - " (a)Model.forward的output\n", - " (b)被设置为target的field\n", - " \n", - "\n", - "### 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\n", - " (1.1) 构建模型过程中，\n", - " 例如:\n", - " DataSet中x，seq_lens是input，那么forward就应该是\n", - " def forward(self, x, seq_lens):\n", - " pass\n", - " 我们是通过形参名称进行匹配的field的\n", - " \n", - "\n", - "\n", - "### 1. 加载数据到DataSet\n", - "### 2. 使用apply操作对DataSet进行预处理\n", - " (2.1) 处理过程中将某些field设置为input，某些field设置为target\n", - "### 3. 构建模型\n", - " (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。\n", - " 例如:\n", - " DataSet中x，seq_lens是input，那么forward就应该是\n", - " def forward(self, x, seq_lens):\n", - " pass\n", - " 我们是通过形参名称进行匹配的field的\n", - " (3.2) 模型的forward的output需要是dict类型的。\n", - " 建议将输出设置为{\"pred\": xx}.\n", - " \n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.6.7" - } - }, - "nbformat": 4, - "nbformat_minor": 2 -} diff --git a/tutorials/fastnlp_tutorial_1204.ipynb b/tutorials/fastnlp_tutorial_1204.ipynb deleted file mode 100644 index 8d896bf2..00000000 --- a/tutorials/fastnlp_tutorial_1204.ipynb +++ /dev/null @@ -1,447 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "fastNLP上手教程\n", - "-------\n", - "\n", - "fastNLP提供方便的数据预处理，训练和测试模型的功能" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "import sys\n", - "sys.path.append('/Users/yh/Desktop/fastNLP/fastNLP/')" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "DataSet & Instance\n", - "------\n", - "\n", - "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。\n", - "\n", - "有一些read_*方法，可以轻松从文件读取数据，存成DataSet。" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "from fastNLP import DataSet\n", - "from fastNLP import Instance\n", - "\n", - "# 从csv读取数据到DataSet\n", - "dataset = DataSet.read_csv('../sentence.csv', headers=('raw_sentence', 'label'), sep='\\t')\n", - "print(len(dataset))" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 使用数字索引[k]，获取第k个样本\n", - "print(dataset[0])\n", - "\n", - "# 索引也可以是负数\n", - "print(dataset[-3])" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Instance\n", - "Instance表示一个样本，由一个或多个field（域，属性，特征）组成，每个field有名字和值。\n", - "\n", - "在初始化Instance时即可定义它包含的域，使用 \"field_name=field_value\"的写法。" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# DataSet.append(Instance)加入新数据\n", - "dataset.append(Instance(raw_sentence='fake data', label='0'))\n", - "dataset[-1]" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## DataSet.apply方法\n", - "数据预处理利器" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 将所有数字转为小写\n", - "dataset.apply(lambda x: x['raw_sentence'].lower(), new_field_name='raw_sentence')\n", - "print(dataset[0])" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# label转int\n", - "dataset.apply(lambda x: int(x['label']), new_field_name='label')\n", - "print(dataset[0])" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 使用空格分割句子\n", - "def split_sent(ins):\n", - " return ins['raw_sentence'].split()\n", - "dataset.apply(split_sent, new_field_name='words')\n", - "print(dataset[0])" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 增加长度信息\n", - "dataset.apply(lambda x: len(x['words']), new_field_name='seq_len')\n", - "print(dataset[0])" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## DataSet.drop\n", - "筛选数据" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "dataset.drop(lambda x: x['seq_len'] <= 3)\n", - "print(len(dataset))" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## 配置DataSet\n", - "1. 哪些域是特征，哪些域是标签\n", - "2. 切分训练集/验证集" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 设置DataSet中，哪些field要转为tensor\n", - "\n", - "# set target，loss或evaluate中的golden，计算loss，模型评估时使用\n", - "dataset.set_target(\"label\")\n", - "# set input，模型forward时使用\n", - "dataset.set_input(\"words\")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 分出测试集、训练集\n", - "\n", - "test_data, train_data = dataset.split(0.3)\n", - "print(len(test_data))\n", - "print(len(train_data))" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Vocabulary\n", - "------\n", - "\n", - "fastNLP中的Vocabulary轻松构建词表，将词转成数字" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "from fastNLP import Vocabulary\n", - "\n", - "# 构建词表, Vocabulary.add(word)\n", - "vocab = Vocabulary(min_freq=2)\n", - "train_data.apply(lambda x: [vocab.add(word) for word in x['words']])\n", - "vocab.build_vocab()\n", - "\n", - "# index句子, Vocabulary.to_index(word)\n", - "train_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='words')\n", - "test_data.apply(lambda x: [vocab.to_index(word) for word in x['words']], new_field_name='words')\n", - "\n", - "\n", - "print(test_data[0])" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "# Model\n", - "定义一个PyTorch模型" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "from fastNLP.models import CNNText\n", - "model = CNNText(embed_num=len(vocab), embed_dim=50, num_classes=5, padding=2, dropout=0.1)\n", - "model" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "这是上述模型的forward方法。如果你不知道什么是forward方法，请参考我们的PyTorch教程。\n", - "\n", - "注意两点：\n", - "1. forward参数名字叫**word_seq**，请记住。\n", - "2. forward的返回值是一个**dict**，其中有个key的名字叫**output**。\n", - "\n", - "```Python\n", - " def forward(self, word_seq):\n", - " \"\"\"\n", - "\n", - " :param word_seq: torch.LongTensor, [batch_size, seq_len]\n", - " :return output: dict of torch.LongTensor, [batch_size, num_classes]\n", - " \"\"\"\n", - " x = self.embed(word_seq) # [N,L] -> [N,L,C]\n", - " x = self.conv_pool(x) # [N,L,C] -> [N,C]\n", - " x = self.dropout(x)\n", - " x = self.fc(x) # [N,C] -> [N, N_class]\n", - " return {'output': x}\n", - "```" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "这是上述模型的predict方法，是用来直接输出该任务的预测结果，与forward目的不同。\n", - "\n", - "注意两点：\n", - "1. predict参数名也叫**word_seq**。\n", - "2. predict的返回值是也一个**dict**，其中有个key的名字叫**predict**。\n", - "\n", - "```\n", - " def predict(self, word_seq):\n", - " \"\"\"\n", - "\n", - " :param word_seq: torch.LongTensor, [batch_size, seq_len]\n", - " :return predict: dict of torch.LongTensor, [batch_size, seq_len]\n", - " \"\"\"\n", - " output = self(word_seq)\n", - " _, predict = output['output'].max(dim=1)\n", - " return {'predict': predict}\n", - "```" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Trainer & Tester\n", - "------\n", - "\n", - "使用fastNLP的Trainer训练模型" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "from fastNLP import Trainer\n", - "from copy import deepcopy\n", - "from fastNLP.core.losses import CrossEntropyLoss\n", - "from fastNLP.core.metrics import AccuracyMetric\n", - "\n", - "\n", - "# 更改DataSet中对应field的名称，与模型的forward的参数名一致\n", - "# 因为forward的参数叫word_seq, 所以要把原本叫words的field改名为word_seq\n", - "# 这里的演示是让你了解这种**命名规则**\n", - "train_data.rename_field('words', 'word_seq')\n", - "test_data.rename_field('words', 'word_seq')\n", - "\n", - "# 顺便把label换名为label_seq\n", - "train_data.rename_field('label', 'label_seq')\n", - "test_data.rename_field('label', 'label_seq')" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### loss\n", - "训练模型需要提供一个损失函数\n", - "\n", - "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**。\n", - "\n", - "pred参数对应的是模型的forward返回的dict的一个key的名字，这里是\"output\"。\n", - "\n", - "target参数对应的是dataset作为标签的field的名字，这里是\"label_seq\"。" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "loss = CrossEntropyLoss(pred=\"output\", target=\"label_seq\")" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Metric\n", - "定义评价指标\n", - "\n", - "这里使用准确率。参数的“命名规则”跟上面类似。\n", - "\n", - "pred参数对应的是模型的predict方法返回的dict的一个key的名字，这里是\"predict\"。\n", - "\n", - "target参数对应的是dataset作为标签的field的名字，这里是\"label_seq\"。" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "metric = AccuracyMetric(pred=\"predict\", target=\"label_seq\")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 实例化Trainer，传入模型和数据，进行训练\n", - "# 先在test_data拟合\n", - "copy_model = deepcopy(model)\n", - "overfit_trainer = Trainer(model=copy_model, train_data=test_data, dev_data=test_data,\n", - " losser=loss,\n", - " metrics=metric,\n", - " save_path=None,\n", - " batch_size=32,\n", - " n_epochs=5)\n", - "overfit_trainer.train()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 用train_data训练，在test_data验证\n", - "trainer = Trainer(model=model, train_data=train_data, dev_data=test_data,\n", - " losser=CrossEntropyLoss(pred=\"output\", target=\"label_seq\"),\n", - " metrics=AccuracyMetric(pred=\"predict\", target=\"label_seq\"),\n", - " save_path=None,\n", - " batch_size=32,\n", - " n_epochs=5)\n", - "trainer.train()\n", - "print('Train finished!')" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# 调用Tester在test_data上评价效果\n", - "from fastNLP import Tester\n", - "\n", - "tester = Tester(data=test_data, model=model, metrics=AccuracyMetric(pred=\"predict\", target=\"label_seq\"),\n", - " batch_size=4)\n", - "acc = tester.test()\n", - "print(acc)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.6.7" - } - }, - "nbformat": 4, - "nbformat_minor": 2 -}