💎一站式轻松地调用各大LLM模型接口,支持GPT4、智谱、星火、月之暗面及文生图 广告
# keras 的 skip-gram 模型 使用 Keras 的嵌入模型的流程与 TensorFlow 保持一致。 * 在 Keras 函数式或顺序模型中创建网络体系结构 * 将目标和上下文单词的真假对提供给网络 * 查找目标和上下文单词的单词向量 * 执行单词向量的点积以获得相似性得分 * 将相似性得分通过 sigmoid 层以将输出作为真或假对 现在让我们使用 Keras 函数式 API 实现这些步骤: 1. 导入所需的库: ```py from keras.models import Model from keras.layers.embeddings import Embedding from keras.preprocessing import sequence from keras.preprocessing.sequence import skipgrams from keras.layers import Input, Dense, Reshape, Dot, merge import keras ``` 重置图,以便清除以前在 Jupyter Notebook 中运行的任何后续效果: ```py # reset the jupyter buffers tf.reset_default_graph() keras.backend.clear_session() ``` 1. 创建一个验证集,我们将用它来打印我们的模型在训练结束时找到的相似单词: ```py valid_size = 8 x_valid = np.random.choice(valid_size * 10, valid_size, replace=False) print('valid: ',x_valid) ``` 1. 定义所需的超参数: ```py batch_size = 1024 embedding_size = 512 n_negative_samples = 64 ptb.skip_window=2 ``` 1. 使用`keras.preprocessing.sequence`中的`make_sampling_table()`函数创建一个大小等于词汇长度的样本表。接下来,使用`keras.preprocessing.sequence`中的函数`skipgrams()`生成上下文和目标词对以及表示它们是真对还是假对的标签。 ```py sample_table = sequence.make_sampling_table(ptb.vocab_len) pairs, labels= sequence.skipgrams(ptb.part['train'], ptb.vocab_len,window_size=ptb.skip_window, sampling_table=sample_table) ``` 1. 让我们打印一些使用以下代码生成的伪造和真实对: ```py print('The skip-gram pairs : target,context') for i in range(5 * ptb.skip_window): print(['{} {}'.format(id,ptb.id2word[id]) \ for id in pairs[i]],':',labels[i]) ``` 对配对如下: ```py The skip-gram pairs : target,context ['547 trying', '5 to'] : 1 ['4845 bargain', '2 <eos>'] : 1 ['1705 election', '198 during'] : 1 ['4704 flows', '8117 gun'] : 0 ['13 is', '37 company'] : 1 ['625 above', '132 three'] : 1 ['5768 pessimistic', '1934 immediate'] : 0 ['637 china', '2 <eos>'] : 1 ['258 five', '1345 pence'] : 1 ['1956 chrysler', '8928 exercises'] : 0 ``` 1. 从上面生成的对中拆分目标和上下文单词,以便将它们输入模型。将目标和上下文单词转换为二维数组。 ```py x,y=zip(*pairs) x=np.array(x,dtype=np.int32) x=dsu.to2d(x,unit_axis=1) y=np.array(y,dtype=np.int32) y=dsu.to2d(y,unit_axis=1) labels=np.array(labels,dtype=np.int32) labels=dsu.to2d(labels,unit_axis=1) ``` 1. 定义网络的体系结构。正如我们所讨论的,必须将目标和上下文单词输入网络,并且需要从嵌入层中查找它们的向量。因此,首先我们分别为目标和上下文单词定义输入,嵌入和重塑层: ```py # build the target word model target_in = Input(shape=(1,),name='target_in') target = Embedding(ptb.vocab_len,embedding_size,input_length=1, name='target_em')(target_in) target = Reshape((embedding_size,1),name='target_re')(target) # build the context word model context_in = Input((1,),name='context_in') context = Embedding(ptb.vocab_len,embedding_size,input_length=1, name='context_em')(context_in) context = Reshape((embedding_size,1),name='context_re')(context) ``` 1. 接下来,构建这两个模型的点积,将其输入 sigmoid 层以生成输出标签: ```py # merge the models with the dot product to check for # similarity and add sigmoid layer output = Dot(axes=1,name='output_dot')([target,context]) output = Reshape((1,),name='output_re')(output) output = Dense(1, activation='sigmoid',name='output_sig')(output) ``` 1. 从我们刚刚创建的输入和输出模型构建函数式模型: ```py # create the functional model for finding word vectors model = Model(inputs=[target_in,context_in],outputs=output) model.compile(loss='binary_crossentropy', optimizer='adam') ``` 1. 此外,在给定输入目标词的情况下,构建一个模型,用于预测与所有单词的相似性: ```py # merge the models and create model to check for cosine similarity similarity = Dot(axes=0,normalize=True, name='sim_dot')([target,context]) similarity_model = Model(inputs=[target_in,context_in], outputs=similarity) ``` 让我们打印模型摘要: ```py __________________________________________________________________________ Layer (type) Output Shape Param # Connected to ========================================================================== target_in (InputLayer) (None, 1) 0 __________________________________________________________________________ context_in (InputLayer) (None, 1) 0 __________________________________________________________________________ target_em (Embedding) (None, 1, 512) 5120000 target_in[0][0] __________________________________________________________________________ context_em (Embedding) (None, 1, 512) 5120000 context_in[0][0] __________________________________________________________________________ target_re (Reshape) (None, 512, 1) 0 target_em[0][0] __________________________________________________________________________ context_re (Reshape) (None, 512, 1) 0 context_em[0][0] __________________________________________________________________________ output_dot (Dot) (None, 1, 1) 0 target_re[0][0] context_re[0][0] __________________________________________________________________________ output_re (Reshape) (None, 1) 0 output_dot[0][0] __________________________________________________________________________ output_sig (Dense) (None, 1) 2 output_re[0][0] ========================================================================== Total params: 10,240,002 Trainable params: 10,240,002 Non-trainable params: 0 __________________________________________________________________________ ``` 1. 接下来,训练模型。我们只训练了 5 个周期,但你应该尝试更多的周期,至少 1000 或 10,000 个周期。 请记住,这将需要几个小时,因为这不是最优化的代码。 欢迎您使用本书和其他来源的提示和技巧进一步优化代码。 ```py n_epochs = 5 batch_size = 1024 model.fit([x,y],labels,batch_size=batch_size, epochs=n_epochs) ``` 让我们根据这个模型发现的单词向量打印单词的相似度: ```py # print closest words to validation set at end of training top_k = 5 y_val = np.arange(ptb.vocab_len, dtype=np.int32) y_val = dsu.to2d(y_val,unit_axis=1) for i in range(valid_size): x_val = np.full(shape=(ptb.vocab_len,1),fill_value=x_valid[i], dtype=np.int32) similarity_scores = similarity_model.predict([x_val,y_val]) similarity_scores=similarity_scores.flatten() similar_words = (-similarity_scores).argsort()[1:top_k + 1] similar_str = 'Similar to {0:}:'.format(ptb.id2word[x_valid[i]]) for k in range(top_k): similar_str = '{0:} {1:},'.format(similar_str, ptb.id2word[similar_words[k]]) print(similar_str) ``` 我们得到以下输出: ```py Similar to we: rake, kia, sim, ssangyong, memotec, Similar to been: nahb, sim, rake, punts, rubens, Similar to also: photography, snack-food, rubens, nahb, ssangyong, Similar to of: isi, rake, memotec, kia, mlx, Similar to last: rubens, punts, memotec, sim, photography, Similar to u.s.: mlx, memotec, punts, rubens, kia, Similar to an: memotec, isi, ssangyong, rake, sim, Similar to trading: rake, rubens, swapo, mlx, nahb, ``` 到目前为止,我们已经看到了如何使用 TensorFlow 及其高级库 Keras 创建单词向量或嵌入。现在让我们看看如何使用 TensorFlow 和 Keras 来学习模型并将模型应用于一些与 NLP 相关的任务的预测。