I am trying to create an AI that will predict a person’s weight from their height. Everything seems to work without any compiler errors. Here’s my code:

import numpy as np
from random import randint
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense


input_dim=1
output_dim = 1
x_train,y_train = [65,68,70,72,67,69,71,66,73,64],[150,160,175,180,155,165,170,148,185,142]
model = Sequential()
model.add(Dense(64, input_shape=(input_dim,), activation='relu'))
model.add(Dense(32, activation='relu'))
model.add(Dense(output_dim, activation='linear'))
model.compile(optimizer='adam', loss='mean_squared_error', metrics=['accuracy'])
model.fit(np.array(x_train), np.array(y_train), epochs=10, batch_size=32)

while True:
  height = float(input("Enter height:"))
  new_height = np.array([[height]])
  print("Weight:",model.predict(new_height))

In my training data, x_train represents heights in inches, while y_train represents weight in pounds.

However, whenever I enter a height to predict the weight, I get strange numbers that don’t correlate to my data:

Enter height:70

Weight: [[-2.168133]]

I would have expected something around 175 instead.

Why is this happening? Is this because my data set is too small?