python - Keras w/Tensorflow 中间层批量提取
问题描述
我目前正在尝试利用我已经训练过的 DL 模型中的中间层作为给定输入的嵌入。下面的代码已经可以获取我想要的层,但是对于大量输入迭代地执行此操作非常慢。
model = load_model('model.h5')
inp = model.input
outputs = [layer.output for layer in model.layers]
functors = [K.function([inp]+ [K.learning_phase()], [out]) for out in outputs]
def text2tensor(text):
"""Convert string to tensor"""
tensor = tokenizer.texts_to_sequences([text])
tensor = pad_sequences(tensor, maxlen=10, padding='pre')
return tensor
def get_embedding(tensor, at_layer):
"""Get output at particular layer in network """
functors = [K.function([inp]+ [K.learning_phase()], [out]) for out in outputs][at_layer-1]
layer_outs = [func([tensor, 1.]) for func in [functors]]
return layer_outs[0][0]
texts = ['this is my first text',
'this is my second text',
'this is my third text',
.....nth text]
embeddings = np.empty((0,256))
for t in texts:
tensor = text2tensor(t)
embedding = get_embedding(tensor,at_layer=4)
embeddings = np.append(embeddings,[embedding[0]],axis=0)
我如何利用批处理,这样我就不必一一做这件事了?上面的实现非常慢,但它可以工作。
解决方案
除了我在评论中提到的一点,我建议您创建一个模型而不是后端函数:
input_tensor = Input(shape=(10,)) # assuming maxlen=10
new_model = Model(input_tensor, my_desired_layer.output)
然后,首先预处理您的文本数据以形成输入数组(即my_data
下面),然后使用predict
方法并将batch_size
参数传递给它以利用批处理:
out = new_model.predict(my_data) # the default batch size is 32