''TimeseriesGenerator' object has no attribute 'shape'
I have a LSTM model. which when I try to fit i get the error mentioned in the title.
I have an array of timeseries data with multiple features I'm feeding as input. The code that is causing the error is below.
TimeseriesGenerator(features, target, length=100, sampling_rate=1, batch_size=100)[0]
train_generator = TimeseriesGenerator(x_train,y_train,length=win_length,sampling_rate=1,batch_size=batch_size)
early_stopping=tf.keras.callbacks.EarlyStopping(monitor='val_loss',
patience=2,
mode='min')
model.compile(loss=tf.losses.MeanSquaredError(),
optimizer=tf.optimizers.Adam(),
metrics=[tf.metrics.MeanAbsoluteError()])
history=model.fit_generator(train_generator,epochs=50,
validation_data=test_generator,
shuffle=False,
callbacks=[early_stopping])
I've been losing my mind over this all day and any help would be appreciated.
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
Solution | Source |
---|