[英]Reduce output dimensions on LSTM keras
Below is my architecture of the model. 下面是我的模型架构。 The data is a time series which I need to predict only the last value, hence
return_sequences=False
. 数据是一个时间序列,我只需要预测最后一个值,因此
return_sequences=False
。
But this is exactly what creates the problem here. 但这正是在这里造成问题的原因。 I have been able to run the nnet using
sequences=True
, but it is not what I need to do. 我已经能够使用
sequences=True
运行nnet,但这不是我需要做的。
I need an input size (32,50,88) 我需要输入大小(32,50,88) =(batch_size,timesteps,features) and get output size of (32,88)
=(batch_size,timesteps,features)并获得(32,88)的输出大小 =(batch_size,labels) .
=(batch_size,labels)
Features and labels have the same size, but it is irrelevant. 特征和标签具有相同的大小,但无关紧要。
The error out of this code is: 此代码中的错误是:
ValueError: Error when checking target: expected dense_1 to have 2 dimensions, but got array with shape (32, 50, 88)
ValueError:检查目标时出错:预期density_1具有2维,但数组的形状为(32,50,88)
which is happening in the training phase (meaning, the architecture comes to be valid). 这是在培训阶段发生的(意思是该架构有效)。
The data comes in chunks of (32,50,88) from a generator, also the labels have the same size. 数据从生成器中以(32,50,88)的块形式输入,标签也具有相同的大小。 Since I use
keras
, I need to create the batches through the generator. 由于我使用
keras
,因此需要通过生成器创建批次。 I have tried to add a single (50,88) but simply it doesn't work. 我试图添加一个(50,88),但根本不起作用。
How could I have this kind of architecture, get the input of (32,50,88) but only get (32,88) as output? 我怎么有这种架构,获得(32,50,88)的输入,但仅获得(32,88)作为输出?
In short, I need the timestep+50 prediction...I think.. 简而言之,我需要timestep + 50预测...我认为..
def note_model():
visible = Input(shape=(50,88), batch_shape=(32,50,88))
hidden1 = Bidirectional(LSTM(200, stateful=False, return_sequences=False, kernel_regularizer=l1(10**(-4)), dropout=0.5))(visible)
#flat = Flatten()(hidden1)
output = Dense(88, activation='sigmoid')(hidden1)
model = Model(inputs=visible, outputs=output)
print(model.summary())
return model
def train_note_model(model):
checkpoint_path_notes = "1Layer-200units-loss=BCE-Model-{epoch:02d}-{val_acc:.2f}.hdf5"
model.compile(optimizer='SGD', loss='binary_crossentropy', metrics=['accuracy']) #mean_squared_error
monitor = EarlyStopping(monitor='val_loss', min_delta=1e-3, patience=10, verbose=0, mode='min')
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.3, patience=10, min_lr=0.001)
checkpoint = ModelCheckpoint(checkpoint_path_notes,monitor='val_loss', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)
model.fit_generator(training_generator(), steps_per_epoch=2,
callbacks=[monitor, reduce_lr, checkpoint],
validation_data= validation_generator(), validation_steps= 2,
verbose=1, epochs=10, shuffle=True)
model_try = note_model()
train_note_model(model_try)
Your model is correct, the issues is when checking the target which means that your training_generator
is returning wrong target shapes. 您的模型是正确的,问题出在检查目标时 ,这意味着您的
training_generator
返回了错误的目标形状。
Have a look at print(next(training_generator()))
and ensure that it returns a tuple with shapes (32, 50, 88), (32, 88)
. 看一下
print(next(training_generator()))
并确保它返回形状为(32, 50, 88), (32, 88)
的元组。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.