Troubleshooting Tensorflow Lite in Bangle

Hmm, the below code is copied from here and just slightly appended. When running it, Bangle restarts itself, when tf.invoke() is run.
What is amiss here, the code, or me?

Edit 1: While the code resets the physical watch, it runs fine in the emulator, both for Bangle 1 and 2
Edit 2: Tried to reset the watch by installing default apps, still same problem

var model=atob("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");

var x = 1;

var tf = require("tensorflow").create(2048, model);
print ("1");
tf.getInput()[0] = x;

print ("2");
tf.invoke();

print ("3");
print(tf.getOutput()[0]);

print ("4");