如何重塑文本数据以适合于Keras中的LSTM模型 [英] how to reshape text data to be suitable for LSTM model in keras
问题描述
更新1:
The code Im referring is exactly the code in the book which you can find it here.
唯一的事情是我不想在解码器部分使用embed_size.这就是为什么我认为根本不需要嵌入层的原因，因为如果我放置嵌入层，则需要在解码器部分中添加embed_size(如果我输入错误，请更正我).
The only thing is that I don't want to have embed_size in the decoder part. That's why I think I don't need to have embedding layer at all because If I put embedding layer, I need to have embed_size in the decoder part(please correct me if Im wrong).
总体而言，我试图在不使用嵌入层的情况下采用相同的代码，因为我需要o在解码器部分中包含vocab_size.
Overall, Im trying to adopt the same code without using the embedding layer, because I need o have vocab_size in the decoder part.
我认为评论中提供的建议可能是正确的(using one_hot_encoding)，无论我如何面对此错误:
I think the suggestion provided in the comment could be correct (using one_hot_encoding) how ever I faced with this error:
当我做one_hot_encoding时:
tf.keras.backend.one_hot(indices=sent_wids, classes=vocab_size)
我收到此错误:
in check_num_samples
you should specify the + steps_name + argument
ValueError: If your data is in the form of symbolic tensors, you should specify the steps_per_epoch argument (instead of the batch_size argument, because symbolic tensors are expected to produce batches of input data)
in check_num_samples
you should specify the + steps_name + argument
ValueError: If your data is in the form of symbolic tensors, you should specify the steps_per_epoch argument (instead of the batch_size argument, because symbolic tensors are expected to produce batches of input data)
我准备数据的方式是这样的:
The way that I have prepared data is like this:
形状是(87716, 200)，我想以可以将其输入LSTM的方式重塑它的形状.
这里的200代表sequence_lenght，而87716是我拥有的样本数.
shape of sent_lens is (87716, 200) and I want to reshape it in a way I can feed it into LSTM.
here 200 stands for the sequence_lenght and 87716 is number of samples I have.
下面是LSTM Autoencoder的代码:
inputs = Input(shape=(SEQUENCE_LEN,VOCAB_SIZE), name="input")
encoded = Bidirectional(LSTM(LATENT_SIZE), merge_mode="sum", name="encoder_lstm")(inputs)
decoded = RepeatVector(SEQUENCE_LEN, name="repeater")(encoded)
decoded = LSTM(VOCAB_SIZE, return_sequences=True)(decoded)
autoencoder = Model(inputs, decoded)
autoencoder.compile(optimizer="sgd", loss='mse')
autoencoder.summary()
history = autoencoder.fit(Xtrain, Xtrain,batch_size=BATCH_SIZE,
epochs=NUM_EPOCHS)
我仍然需要做些额外的事情吗?如果没有，为什么我无法使它正常工作?
Do I still need to do anything extra, if No, why I can not get this works?
请让我知道我要解释的部分不清楚.
Please let me know which part is not clear I will explain.
感谢您的帮助:)
推荐答案
因此，正如评论中所述，事实证明我只需要执行one_hot_encoding.
So as said in the comments it turns out I just needed to do one_hot_encoding.
当我使用tf.keras.backend进行one_hot编码时，会引发我在问题中更新的错误.
when I did one_hot encoding using the tf.keras.backend it throws the error that I have updated in my question.
然后我尝试了to_categorical(sent_wids, num_classes=VOCAB_SIZE)并修复了该问题(但是面对memory error:D却是另一回事)！
Then I tried to_categorical(sent_wids, num_classes=VOCAB_SIZE) and it fixed (however faced with memory error :D which is different story)!!!
我还应该提到我尝试了sparse_categorical_crossentropy而不是one_hot_encoding，尽管它不起作用！
I should also mention that I tried sparse_categorical_crossentropy instead of one_hot_encoding though it did not work!
感谢您的所有帮助:)
这篇关于如何重塑文本数据以适合于Keras中的LSTM模型的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
