我試圖讓 LSTM 模型繼續運行，因為它的最后一次運行停止了。在我嘗試適應網絡之前，一切都可以正常編譯。然后它給出一個錯誤：ValueError：檢查目標時出錯：預期dense_29具有3維，但得到形狀為(672, 1)的數組我檢查了諸如this和this之類的各種文章， 但我沒有看到我的代碼有什么問題。from keras import Sequentialfrom keras.preprocessing.sequence import pad_sequencesfrom sklearn.model_selection import train_test_splitfrom keras.models import Sequential,Modelfrom keras.layers import LSTM, Dense, Bidirectional, Input,Dropout,BatchNormalizationfrom keras import backend as Kfrom keras.engine.topology import Layerfrom keras import initializers, regularizers, constraintsfrom keras.callbacks import ModelCheckpointfrom keras.models import load_modelimport os.pathimport osfilepath="Train-weights.best.hdf5"act = 'relu'model = Sequential()model.add(BatchNormalization(input_shape=(10, 128)))model.add(Bidirectional(LSTM(128, dropout=0.5, activation=act, return_sequences=True)))model.add(Dense(1,activation='sigmoid'))if (os.path.exists(filepath)): print("extending training of previous run") model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy']) with open('model_architecture.json', 'r') as f: model = model_from_json(f.read()) model.load_weights(filepath)else: print("First run") model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy']) model.fit(x_train, y_train, validation_data=(x_val, y_val), epochs=100, batch_size=32, callbacks=callbacks_list, verbose=2) model.save_weights(filepath) with open('model_architecture.json', 'w') as f: f.write(model.to_json()) checkpoint = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max') callbacks_list = [checkpoint] model.fit(x_train, y_train, validation_data=(x_val, y_val), epochs=100, batch_size=32, callbacks=callbacks_list, verbose=0)
1 回答
holdtom
TA貢獻1805條經驗 獲得超10個贊
嘗試一下model.summary()，您會看到網絡中最后一層（即 Dense 層）的輸出形狀是(None, 10, 1)。因此，您提供給模型的標簽（即y_train）也必須具有 形狀(num_samples, 10, 1)。
如果輸出形狀(None, 10, 1)不是您想要的（例如，您想要(None, 1)作為模型的輸出形狀），那么您需要修改您的模型定義。實現這一目標的一個簡單修改是return_sequences=True從 LSTM 層中刪除參數。
添加回答
舉報
0/150
提交
取消