Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

句向量特征提取的最佳实践 #160

Open
RingoD opened this issue Mar 26, 2021 · 0 comments
Open

句向量特征提取的最佳实践 #160

RingoD opened this issue Mar 26, 2021 · 0 comments

Comments

@RingoD
Copy link

RingoD commented Mar 26, 2021

我想通过 albert_chinese_tiny 对一句话进行特征提取,再用提取的向量做我自己的训练。
由于 albert_chinese_tiny 的输出是 (none, 512, 21148),因此我对其进行了 max pooling,输出为 (none, 512)
想请教这样的实践是否正确

if __name__ == '__main__':
    import keras_albert_model
    import keras_bert
    import numpy as np
    from tensorflow import keras
    model = keras_albert_model.load_brightmart_albert_zh_checkpoint('./albert_tiny_489k/')
    tokenizer = keras_bert.Tokenizer(keras_bert.load_vocabulary('./albert_tiny_489k/vocab.txt'))

    outputs = keras.layers.GlobalMaxPool1D(name='MaxPooling', data_format='channels_first')(model.outputs[0])

    model = keras.models.Model(inputs=model.inputs, outputs=outputs)
    model.summary()
    token, segment = tokenizer.encode('I like it', max_len=512)
    prediction = model.predict([np.array([token]), np.array([segment])])[0]
    print(prediction, prediction.shape)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant