层顺序的 Keras Tuner 输入 0 与层不兼容：：预期 min_ndim=3，发现 ndim=2。收到的完整形状：（无，216）

Question

帮我解决错误

keras 输入尺寸错误

def model_builder(hp):
  model = keras.Sequential()
  model.add(keras.layers.Conv1D(256, 5,padding='same',input_shape=(215,1), activation='relu'))    
  model.add(keras.layers.Conv1D(128, 5,padding='same',activation='relu'))      
  model.add(keras.layers.Dropout(0.1))
  model.add(keras.layers.MaxPooling1D(pool_size=(32)))
  model.add(keras.layers.Conv1D(128, 5,padding='same',activation='relu'))
  model.add(keras.layers.Conv1D(128, 5,padding='same',activation='relu'))
  model.add(keras.layers.Conv1D(128, 5,padding='same',activation='relu'))
  model.add(keras.layers.Conv1D(128, 5,padding='same',activation='relu'))
  model.add(keras.layers.Dropout(0.2))
  model.add(keras.layers.Conv1D(128, 5,padding='same',activation='relu'))
  model.add(keras.layers.Flatten())
  model.add(keras.layers.Dense(5,kernel_regularizer='l1',activation='softmax'))
 
  opt = keras.optimizers.RMSprop(lr=0.00001, decay=1e-6)
  model.compile(loss='categorical_crossentropy', optimizer=opt,metrics=['accuracy'])
              
  return model

tuner = kt.Hyperband(model_builder,
                     objective='val_accuracy',
                     max_epochs=10,
                     factor=3,
                     directory='my_dir',
                     project_name='intro_to_kt')

stop_early = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=5)

tuner.search(X_train, y_train, epochs=50, validation_split=0.2, callbacks=[stop_early])

# Get the optimal hyperparameters
best_hps=tuner.get_best_hyperparameters(num_trials=215)[0]

print(f"""
The hyperparameter search is complete. The optimal number of units in the 
first densely-connected
layer is {best_hps.get('units')} 
optimal learning rate for the optimizer is {best_hps.get('learning_rate')}. """)

此处的错误照片

enter image description here

Answer 1

在您的输入层中，您只需添加一个维度

X_train[:,:,np.newaxis]