大家好。我正在尝试为匹配任务定制一个共注意力层。并且有一个错误让我很困惑。
model = Model(inputs=[ans_input, ques_input], outputs=output)我的程序在运行上述代码时关闭。然后它会抛出一个错误
AttributeError: 'Tensor' object has no attribute '_keras_history'这意味着我的模型不能成为一个完整的图，我猜。所以我尝试了很多我在StackOverflow和其他博客上找到的方法。但所有这些都无法工作。:(
我将在下面粘贴我的模型。谢谢你们帮助我 🙂
import timefrom keras.layers import Embedding, LSTM, TimeDistributed, Lambdafrom keras.layers.core import *from keras.layers.merge import concatenatefrom keras.layers.pooling import GlobalMaxPooling1Dfrom keras.models import *from keras.optimizers import *from dialog.keras_lstm.k_call import *from dialog.model.keras_himodel import ZeroMaskedEntries, loggerclass Co_AttLayer(Layer): def __init__(self, **kwargs): # self.input_spec = [InputSpec(ndim=3)] super(Co_AttLayer, self).__init__(**kwargs) def build(self, input_shape): assert len(input_shape) == 2 assert len(input_shape[0]) == len(input_shape[1]) super(Co_AttLayer, self).build(input_shape) def cosine_sim(self, x): ans_ss = K.sum(K.square(x[0]), axis=2, keepdims=True) ans_norm = K.sqrt(K.maximum(ans_ss, K.epsilon())) ques_ss = K.sum(K.square(x[1]), axis=2, keepdims=True) ques_norm = K.sqrt(K.maximum(ques_ss, K.epsilon())) tr_ques_norm = K.permute_dimensions(ques_norm, (0, 2, 1)) tr_ques = K.permute_dimensions(x[1], (0, 2, 1)) ss = K.batch_dot(x[0], tr_ques, axes=[2, 1]) den = K.batch_dot(ans_norm, tr_ques_norm, axes=[2, 1]) return ss / den def call(self, x, mask=None): cosine = Lambda(self.cosine_sim)(x) coqWij = K.softmax(cosine) print(x[1].shape, coqWij.shape) ai = K.dot(coqWij, x[1]) # (N A Q) (N Q L) coaWij = K.softmax(K.permute_dimensions(cosine, (0, 2, 1))) qj = K.dot(coaWij, x[0]) print(qj.shape, ai.shape) return concatenate([ai, qj], axis=2) def compute_output_shape(self, input_shape): return input_shapedef build_QAmatch_model(opts, vocab_size=0, maxlen=300, embedd_dim=50, init_mean_value=None): ans_input = Input(shape=(maxlen,), dtype='int32', name='ans_input') ques_input = Input(shape=(maxlen,), dtype='int32', name='ques_input') embedding = Embedding(output_dim=embedd_dim, input_dim=vocab_size, input_length=maxlen, mask_zero=True, name='embedding') dropout = Dropout(opts.dropout, name='dropout') lstm = LSTM(opts.lstm_units, return_sequences=True, name='lstm') hidden_layer = Dense(units=opts.hidden_units, name='hidden_layer') output_layer = Dense(units=1, name='output_layer') zme = ZeroMaskedEntries(name='maskedout') ans_maskedout = zme(embedding(ans_input)) ques_maskedout = zme(embedding(ques_input)) ans_lstm = lstm(dropout(ans_maskedout)) # (A V) ques_lstm = lstm(dropout(ques_maskedout)) # (Q V) co_att = Co_AttLayer()([ans_lstm, ques_lstm]) def slice(x, index): return x[:, :, index, :] ans_att = Lambda(slice, output_shape=(maxlen, embedd_dim), arguments={'index': 0})(co_att) ques_att = Lambda(slice, output_shape=(maxlen, embedd_dim), arguments={'index': 1})(co_att) merged_ques = concatenate([ques_lstm, ques_att, ques_maskedout], axis=2) merged_ans = concatenate([ans_lstm, ans_att, ans_maskedout], axis=2) ans_vec = GlobalMaxPooling1D(name='ans_pooling')(merged_ans) ques_vec = GlobalMaxPooling1D(name='ques_pooling')(merged_ques) ans_hid = hidden_layer(ans_vec) ques_hid = hidden_layer(ques_vec) merged_hid = concatenate([ans_hid, ques_hid], axis=-1) merged_all = concatenate([merged_hid, ans_hid + ques_hid, ans_hid - ques_hid, K.abs(ans_hid - ques_hid)], axis=-1) output = output_layer(merged_all) model = Model(inputs=[ans_input, ques_input], outputs=output) if init_mean_value: logger.info("Initialise output layer bias with log(y_mean/1-y_mean)") bias_value = (np.log(init_mean_value) - np.log(1 - init_mean_value)).astype(K.floatx()) model.layers[-1].b.set_value(bias_value) if verbose: model.summary() start_time = time.time() model.compile(loss='mse', optimizer='rmsprop') total_time = time.time() - start_time logger.info("Model compiled in %.4f s" % total_time) return model回答：
我无法重现你的代码，但我猜测错误发生在这里：
merged_all = concatenate([merged_hid, ans_hid + ques_hid, ans_hid - ques_hid, K.abs(ans_hid - ques_hid)], axis=-1)后端操作 +, - 和 K.abs 没有被包装在 Lambda 层中，因此生成的张量不是 Keras 张量，因此它们缺少一些属性，例如 _keras_history。你可以按以下方式包装它们：
l1 = Lambda(lambda x: x[0] + x[1])([ans_hid, ques_hid])l2 = Lambda(lambda x: x[0] - x[1])([ans_hid, ques_hid])l3 = Lambda(lambda x: K.abs(x[0] - x[1]))([ans_hid, ques_hid])merged_all = concatenate([merged_hid, l1, l2, l3], axis=-1)注意： 未经测试。
