one to many LSTM

Question

I have trained a one to many LSTM and I've used WandB. I have created the following code:

`X = list()
 Y = list()
 X = [x+3 for x in range(-2, 43, 3)]
 for i in X:
     output_vector = list()
     output_vector.append(i+1)
     output_vector.append(i+2)
     Y.append(output_vector)`

then reshape them in numpy array :

`X = np.array(X).reshape(15,1, 1)
 Y = np.array(Y)`

finally one to many lstm :

`model = Sequential()
 model.add(LSTM(50, activation='relu', input_shape=(1,1)))
 model.add(Dense(3))
 model.compile(optimizer='adam', loss='mse')
 wandb.init(project='simple-lstm')
 model.fit(X, Y, epochs=1000, validation_split=0.2, batch_size=3, 
 callbacks=[WandbCallback()])`

I want to convert the inputs and outputs to one-hot vectors, how can i implement it. what are the shapes of the inputs and outputs vectors?

one to many LSTM

0 Answers