Add files via upload

models/DPCNN.py

@@ -0,0 +1,86 @@
+#coding: UTF-8
+import mindspore
+import mindspore.nn as nn
+import mindspore.ops as ops
+import numpy as np
+
+class Config(object):
+
+    """配置参数"""
+    def __init__(self, dataset, embedding):
+        self.model_name = 'DPCNN'
+        self.train_path = dataset + '/data/train.txt'                                # 训练集
+        self.dev_path = dataset + '/data/dev.txt'                                    # 验证集
+        self.test_path = dataset + '/data/test.txt'                                  # 测试集
+        self.class_list = [x.strip() for x in open(
+            dataset + '/data/class.txt', encoding='utf-8').readlines()]              # 类别名单
+        self.vocab_path = dataset + '/data/vocab.pkl'                                # 词表
+        self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt'        # 模型训练结果
+        self.log_path = dataset + '/log/' + self.model_name
+        self.embedding_pretrained = mindspore.Tensor(
+            np.load(dataset + '/data/' + embedding)["embeddings"].astype('float32'))\
+            if embedding != 'random' else None                                       # 预训练词向量
+
+        self.dropout = 0.5                                              # 随机失活
+        self.require_improvement = 1000                                 # 若超过1000batch效果还没提升，则提前结束训练
+        self.num_classes = len(self.class_list)                         # 类别数
+        self.n_vocab = 0                                                # 词表大小，在运行时赋值
+        self.num_epochs = 20                                            # epoch数
+        self.batch_size = 128                                           # mini-batch大小
+        self.pad_size = 32                                              # 每句话处理成的长度(短填长切)
+        self.learning_rate = 1e-3                                       # 学习率
+        self.embed = self.embedding_pretrained.size(1)\
+            if self.embedding_pretrained is not None else 300           # 字向量维度
+        self.num_filters = 250                                          # 卷积核数量(channels数)
+
+        '''Deep Pyramid Convolutional Neural Networks for Text Categorization'''
+
+
+class Model(nn.Cell):
+    def __init__(self, config):
+        super(Model, self).__init__()
+        if config.embedding_pretrained is not None:
+            self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False)
+        else:
+            self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1)
+        self.conv_region = nn.Conv2d(1, config.num_filters, (3, config.embed), stride=1, has_bias=True)
+        self.conv = nn.Conv2d(config.num_filters, config.num_filters, (3, 1), stride=1, has_bias=True)
+        self.max_pool = nn.MaxPool2d(kernel_size=(3, 1), stride=2)
+        self.padding1 = nn.ZeroPad2d((0, 0, 1, 1))  # top bottom
+        self.padding2 = nn.ZeroPad2d((0, 0, 0, 1))  # bottom
+        self.relu = nn.ReLU()
+        self.fc = nn.Dense(config.num_filters, config.num_classes)
+
+    def forward(self, x):
+        x = x[0]
+        x = self.embedding(x)
+        x = x.unsqueeze(1)  # [batch_size, 250, seq_len, 1]
+        x = self.conv_region(x)  # [batch_size, 250, seq_len-3+1, 1]
+
+        x = self.padding1(x)  # [batch_size, 250, seq_len, 1]
+        x = self.relu(x)
+        x = self.conv(x)  # [batch_size, 250, seq_len-3+1, 1]
+        x = self.padding1(x)  # [batch_size, 250, seq_len, 1]
+        x = self.relu(x)
+        x = self.conv(x)  # [batch_size, 250, seq_len-3+1, 1]
+        while x.size()[2] > 2:
+            x = self._block(x)
+        x = x.squeeze()  # [batch_size, num_filters(250)]
+        x = self.fc(x)
+        return x
+
+    def _block(self, x):
+        x = self.padding2(x)
+        px = self.max_pool(x)
+
+        x = self.padding1(px)
+        x = ops.relu(x)
+        x = self.conv(x)
+
+        x = self.padding1(x)
+        x = ops.relu(x)
+        x = self.conv(x)
+
+        # Short Cut
+        x = x + px
+        return x

models/FastText.py

@@ -0,0 +1,67 @@
+#coding: UTF-8
+import mindspore
+import mindspore.nn as nn
+import mindspore.ops as ops
+import numpy as np
+
+class Config(object):
+
+    """配置参数"""
+    def __init__(self, dataset, embedding):
+        self.model_name = 'FastText'
+        self.train_path = dataset + '/data/train.txt'                                # 训练集
+        self.dev_path = dataset + '/data/dev.txt'                                    # 验证集
+        self.test_path = dataset + '/data/test.txt'                                  # 测试集
+        self.class_list = [x.strip() for x in open(
+            dataset + '/data/class.txt', encoding='utf-8').readlines()]              # 类别名单
+        self.vocab_path = dataset + '/data/vocab.pkl'                                # 词表
+        self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt'        # 模型训练结果
+        self.log_path = dataset + '/log/' + self.model_name
+        self.embedding_pretrained = mindspore.Tensor(
+            np.load(dataset + '/data/' + embedding)["embeddings"].astype('float32'))\
+            if embedding != 'random' else None                                       # 预训练词向量
+
+        self.dropout = 0.5                                              # 随机失活
+        self.require_improvement = 1000                                 # 若超过1000batch效果还没提升，则提前结束训练
+        self.num_classes = len(self.class_list)                         # 类别数
+        self.n_vocab = 0                                                # 词表大小，在运行时赋值
+        self.num_epochs = 20                                            # epoch数
+        self.batch_size = 128                                           # mini-batch大小
+        self.pad_size = 32                                              # 每句话处理成的长度(短填长切)
+        self.learning_rate = 1e-3                                       # 学习率
+        self.embed = self.embedding_pretrained.size(1)\
+            if self.embedding_pretrained is not None else 300           # 字向量维度
+        self.hidden_size = 256                                          # 隐藏层大小
+        self.n_gram_vocab = 250499
+
+
+'''Bag of Tricks for Efficient Text Classification'''
+
+
+class Model(nn.Cell):
+    def __init__(self, config):
+        super(Model, self).__init__()
+        if config.embedding_pretrained is not None:
+            self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False)
+        else:
+            self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1)
+        self.embedding_ngram2 = nn.Embedding(config.n_gram_vocab, config.embed)
+        self.embedding_ngram3 = nn.Embedding(config.n_gram_vocab, config.embed)
+        self.dropout = nn.Dropout(config.dropout)
+        self.fc1 = nn.Dense(config.embed * 3, config.hidden_size)
+        # self.dropout2 = nn.Dropout(config.dropout)
+        self.fc2 = nn.Dense(config.hidden_size, config.num_classes)
+
+    def forward(self, x):
+
+        out_word = self.embedding(x[0])
+        out_bigram = self.embedding_ngram2(x[2])
+        out_trigram = self.embedding_ngram3(x[3])
+        out = ops.cat((out_word, out_bigram, out_trigram), -1)
+
+        out = out.mean(dim=1)
+        out = self.dropout(out)
+        out = self.fc1(out)
+        out = ops.relu(out)
+        out = self.fc2(out)
+        return out

models/TextCNN.py

@@ -0,0 +1,67 @@
+import mindspore
+import mindspore.nn as nn
+import mindspore.ops as ops
+import numpy as np
+from mindspore import Tensor, CSRTensor, COOTensor
+
+class Config(object):
+
+    """配置参数"""
+    def __init__(self, dataset, embedding):
+        self.model_name = 'TextCNN'
+        self.train_path = dataset + '/data/train.txt'                                # 训练集
+        self.dev_path = dataset + '/data/dev.txt'                                    # 验证集
+        self.test_path = dataset + '/data/test.txt'                                  # 测试集
+        self.class_list = [x.strip() for x in open(
+            dataset + '/data/class.txt', encoding='utf-8').readlines()]              # 类别名单
+        self.vocab_path = dataset + '/data/vocab.pkl'                                # 词表
+        self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt'        # 模型训练结果
+        self.log_path = dataset + '/log/' + self.model_name
+        self.embedding_pretrained = mindspore.Tensor(
+            np.load(dataset + '/data/' + embedding)["embeddings"].astype(Tensor.float32))\
+            if embedding != 'random' else None                                # 预训练词向量
+
+        self.dropout = 0.5                                              # 随机失活
+        self.require_improvement = 1000                                 # 若超过1000batch效果还没提升，则提前结束训练
+        self.num_classes = len(self.class_list)                         # 类别数
+        self.n_vocab = 0                                                # 词表大小，在运行时赋值
+        self.num_epochs = 20                                            # epoch数
+        self.batch_size = 128                                           # mini-batch大小
+        self.pad_size = 32                                              # 每句话处理成的长度(短填长切)
+        self.learning_rate = 1e-3                                       # 学习率
+        self.embed = self.embedding_pretrained.size(1)\
+            if self.embedding_pretrained is not None else 300           # 字向量维度
+        self.filter_sizes = (2, 3, 4)                                   # 卷积核尺寸
+        self.num_filters = 256                                          # 卷积核数量(channels数)
+
+
+'''Convolutional Neural Networks for Sentence Classification'''
+
+
+class Model(nn.Cell):
+    def __init__(self, config):
+        super(Model, self).__init__()        # 继承自nn.Cell类 创建一个模型类实例(self)
+        if config.embedding_pretrained is not None:
+            self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False)
+        else:
+            self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1)
+        self.convs = nn.CellList(
+            [nn.Conv2d(1, config.num_filters, (k, config.embed)) for k in config.filter_sizes], has_bias=True)
+        self.dropout = nn.Dropout(config.dropout)
+        self.fc = nn.Dense(config.num_filters * len(config.filter_sizes), config.num_classes)
+
+
+    def conv_and_pool(self, x, conv):
+        x = ops.relu(conv(x))                #relu:激活函数，它将所有负值变为零，并保持正值不变
+        x = ops.squeeze(x, axis = 3)         #squeeze:去掉维度,axis = 删除指定 axis 中大小为1的维度
+        x = ops.adaptive_max_pool1d(x, x.size(2))              #应用一维自适应最大池化操作
+        x = ops.squeeze(x, axis = 2)
+        return x
+
+    def forward(self, x):
+        out = self.embedding(x[0])
+        out = out.unsqueeze(1)
+        out = ops.cat([self.conv_and_pool(out, conv) for conv in self.convs], 1)      #拼接卷积核池化操作后的张量
+        out = self.dropout(out)
+        out = self.fc(out)
+        return out 

models/TextRCNN.py

@@ -0,0 +1,61 @@
+#coding: UTF-8
+import mindspore
+import mindspore.ops as ops
+import numpy as np
+import mindspore.nn as nn
+
+class Config(object):
+
+    """配置参数"""
+    def __init__(self, dataset, embedding):
+        self.model_name = 'TextRCNN'
+        self.train_path = dataset + '/data/train.txt'                                # 训练集
+        self.dev_path = dataset + '/data/dev.txt'                                    # 验证集
+        self.test_path = dataset + '/data/test.txt'                                  # 测试集
+        self.class_list = [x.strip() for x in open(
+            dataset + '/data/class.txt', encoding='utf-8').readlines()]              # 类别名单
+        self.vocab_path = dataset + '/data/vocab.pkl'                                # 词表
+        self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt'        # 模型训练结果
+        self.log_path = dataset + '/log/' + self.model_name
+        self.embedding_pretrained = mindspore.Tensor(
+            np.load(dataset + '/data/' + embedding)["embeddings"].astype('float32'))\
+            if embedding != 'random' else None                                       # 预训练词向量
+
+        self.dropout = 1.0                                              # 随机失活
+        self.require_improvement = 1000                                 # 若超过1000batch效果还没提升，则提前结束训练
+        self.num_classes = len(self.class_list)                         # 类别数
+        self.n_vocab = 0                                                # 词表大小，在运行时赋值
+        self.num_epochs = 10                                            # epoch数
+        self.batch_size = 128                                           # mini-batch大小
+        self.pad_size = 32                                              # 每句话处理成的长度(短填长切)
+        self.learning_rate = 1e-3                                       # 学习率
+        self.embed = self.embedding_pretrained.size(1)\
+            if self.embedding_pretrained is not None else 300           # 字向量维度, 若使用了预训练词向量，则维度统一
+        self.hidden_size = 256                                          # lstm隐藏层
+        self.num_layers = 1                                             # lstm层数
+
+'''Recurrent Convolutional Neural Networks for Text Classification'''
+
+
+class Model(nn.Cell):
+    def __init__(self, config):
+        super(Model, self).__init__()
+        if config.embedding_pretrained is not None:
+            self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False)
+        else:
+            self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1)
+        self.lstm = nn.LSTM(config.embed, config.hidden_size, config.num_layers,
+                            bidirectional=True, batch_first=True, dropout=config.dropout)
+        self.maxpool = nn.MaxPool1d(config.pad_size)
+        self.fc = nn.Dense(config.hidden_size * 2 + config.embed, config.num_classes)
+
+    def forward(self, x):
+        x, _ = x
+        embed = self.embedding(x)  # [batch_size, seq_len, embeding]=[64, 32, 64]
+        out, _ = self.lstm(embed)
+        out = ops.cat((embed, out), 2)
+        out = ops.relu(out)
+        out = out.permute(0, 2, 1)
+        out = self.maxpool(out).squeeze()
+        out = self.fc(out)
+        return out

models/TextRNN.py

@@ -0,0 +1,57 @@
+#coding: UTF-8
+import mindspore
+import mindspore.nn as nn
+import numpy as np
+
+
+class Config(object):
+
+    """配置参数"""
+    def __init__(self, dataset, embedding):
+        self.model_name = 'TextRNN'
+        self.train_path = dataset + '/data/train.txt'                                # 训练集
+        self.dev_path = dataset + '/data/dev.txt'                                    # 验证集
+        self.test_path = dataset + '/data/test.txt'                                  # 测试集
+        self.class_list = [x.strip() for x in open(
+            dataset + '/data/class.txt', encoding='utf-8').readlines()]              # 类别名单
+        self.vocab_path = dataset + '/data/vocab.pkl'                                # 词表
+        self.save_path = dataset + '/saved_dict/' + self.model_name + '.ckpt'        # 模型训练结果
+        self.log_path = dataset + '/log/' + self.model_name
+        self.embedding_pretrained = mindspore.Tensor(
+            np.load(dataset + '/data/' + embedding)["embeddings"].astype('float32'))\
+            if embedding != 'random' else None                                       # 预训练词向量
+
+        self.dropout = 0.5                                              # 随机失活
+        self.require_improvement = 1000                                 # 若超过1000batch效果还没提升，则提前结束训练
+        self.num_classes = len(self.class_list)                         # 类别数
+        self.n_vocab = 0                                                # 词表大小，在运行时赋值
+        self.num_epochs = 10                                            # epoch数
+        self.batch_size = 128                                           # mini-batch大小
+        self.pad_size = 32                                              # 每句话处理成的长度(短填长切)
+        self.learning_rate = 1e-3                                       # 学习率
+        self.embed = self.embedding_pretrained.size(1)\
+            if self.embedding_pretrained is not None else 300           # 字向量维度, 若使用了预训练词向量，则维度统一
+        self.hidden_size = 128                                          # lstm隐藏层
+        self.num_layers = 2                                             # lstm层数
+
+
+'''Recurrent Neural Network for Text Classification with Multi-Task Learning'''
+
+
+class Model(nn.Cell):
+    def __init__(self, config):
+        super(Model, self).__init__()
+        if config.embedding_pretrained is not None:
+            self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False)
+        else:
+            self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1)
+        self.lstm = nn.LSTM(config.embed, config.hidden_size, config.num_layers,
+                            bidirectional=True, batch_first=True, dropout=config.dropout)
+        self.fc = nn.Dense(config.hidden_size * 2, config.num_classes)
+
+    def forward(self, x):
+        x, _ = x
+        out = self.embedding(x)  # [batch_size, seq_len, embeding]=[128, 32, 300]
+        out, _ = self.lstm(out)
+        out = self.fc(out[:, -1, :])  # 句子最后时刻的 hidden state
+        return out