Tarsus
 | Haec est pagina discretiva alias paginas eiusdem fere nominis indicans. |
|---|
Tarsus, urbs Turciae praeclara
Tarsus sive Tarsia, modestior Turciae urbs ad flumen Sangarium iacens
Tarsus, os
LSTM sequence prediction: 3d input to 2d output
1
$begingroup$
I have this LSTM model model = Sequential() model.add(Masking(mask_value=0, input_shape=(timesteps, features))) model.add(LSTM(100, dropout=0.2, recurrent_dropout=0.2, return_sequences=False)) model.add(Dense(features, activation='softmax')) model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) and shapes X_train (21, 11, 5), y_train (21, 5) . Each timestep is represented by 5 features and return_sequences is set to False because I want to predict one 5D array (the next timestep) for each input sequence of 11 timesteps. I get the error ValueError: y_true and y_pred have different number of output (5!=1) If I reshape the data as X_train (21, 11, 5), y_train (21, 1, 5) instead I get the error ValueError: Inva...
