What is RNN LSTM input shape supposed to be?

Question

I'm confused about how LSTM input sizes work.

I have a scenario where im trying to predict the weight of a person based on weight and height, both in time series.

I can't seem to figure out where I'm going wrong in terms of dimensions:

from datetime import datetime
import numpy as np
import pandas as pd
import math
from keras.layers import Dense, Activation, LSTM, Input, concatenate
from keras.models import Model

def create_dataset(dataset, window_length=1):
    dataX, dataY = [], []
    for i in range(len(dataset)-window_length-1):
        # print("dataX from {} to {}".format(i, i+window_length))
        # print("dataY from {}".format(i+window_length))
        dataX.append(dataset[i:(i+window_length)])
        dataY.append(dataset[(i + window_length):])


    return np.array(dataX), np.array(dataY)

def buildModel(dataLength, labelLength):

    weight = Input(shape=(dataLength, 1), name="weight")
    height = Input(shape=(dataLength, 1), name="height")

    weightLayers = LSTM(64, return_sequences=False)(weight)
    heightLayers = LSTM(64, return_sequences=False)(height)

    output = concatenate([ weightLayers, heightLayers ])

    output = Dense(labelLength, activation="linear", name="weightedAverage_output")(output)

    model = Model(
        inputs=[weight, height],
        outputs=[output]
        )

    model.compile(optimizer="rmsprop", loss="mse")

    return model

bogus = {
    "weight": range(100,200),
    "height": range(150,250)
}

dataset = pd.DataFrame(bogus)



train_size      = int(len(dataset) * 0.90)
test_size       = len(dataset) - train_size
train, test     = dataset[:train_size], dataset[-test_size:]

# print("*" * 30)
# print(train.head())
# print(train.tail())
# print("==> {}".format(len(train)))
# print("*" * 30)
# print(test.head())
# print(test.tail())
# print("==> {}".format(len(test)))
# input(">")

height_train = np.array(train["height"].values.tolist()).reshape((-1, 1)).astype('float32')
weight_train = np.array(train["weight"].values.tolist()).reshape((-1, 1)).astype('float32')

height_test = np.array(test["height"].values.tolist()).reshape((-1, 1)).astype('float32')
weight_test = np.array(test["weight"].values.tolist()).reshape((-1, 1)).astype('float32')

x_train_height, y_train_height  = create_dataset(height_train, 60)
x_train_weight, y_train_weight  = create_dataset(weight_train, 60)

x_test_height, y_test_height  = create_dataset(height_test, 60)
x_test_weight, y_test_weight  = create_dataset(weight_test, 60)



model = buildModel(60,4)
model.fit(
    [ 
        x_train_weight,
        x_train_height,
    ],

    [ 
        y_train_weight
    ],

    validation_data=(
        [
            x_test_weight,
            x_test_height,
        ],
        [
            y_test_weight
        ],
    ),

    epochs=1,
    batch_size=3000,
    callbacks=[
        # board.createTensorboardConfig("log/graph"),
    ]
)

I get this error:

ValueError: Error when checking target: expected weightedAverage_output to have shape (None, 4) but got array with shape (29, 1)

Pretty sure i'm going wrong somewhere in input and output dimensions.

Any ideas?

Answer 1

First you need to change the dimension of your final output layer:

output = Dense(1, activation="linear", name="weightedAverage_output")(output)

Secondly, you need to change the input dimensions to include timesteps:

timesteps = 1
weight = Input(shape=(dataLength,timesteps,1), name="weight")
height = Input(shape=(dataLength,timesteps,1), name="height")

Timesteps can range between (0,inf).

You can refer this post for further knowledge on timesteps: https://machinelearningmastery.com/use-timesteps-lstm-networks-time-series-forecasting/