Operating Machine-Learning Models on Different Platforms

A non-transitory computer-readable storage medium storing instructions that, when executed by an electronic device, cause the electronic device to determine whether a machine-learning model is operating within predefined limits, by carrying out one or more operations that comprise:

• receiving, from another electronic device, instructions for the machine-learning model, a reference input and a predetermined output of the machine-learning model for the reference input, wherein the instructions including an architecture of the machine-learning model, weights associated with the machine-learning model and a set of pre-processing transformations for use when executing the machine-learning model on images;
• configuring the machine-learning model based on the instructions;
• calculating an output of the machine-learning model for the reference input;
• and
• determining whether the machine-learning model is operating within the predefined limits based on the output and the predetermined output.

A method for determining whether a machine-learning model is operating within predefined limits, the method comprising:

• receiving, from another electronic device, instructions for the machine-learning model, a reference input and a predetermined output of the machine-learning model for the reference input, wherein the instructions including an architecture of the machine-learning model, weights associated with the machine-learning model and a set of pre-processing transformations for use when executing the machine-learning model on images;
• configuring the machine-learning model based on the instructions;
• calculating an output of the machine-learning model for the reference input;
• and
• determining whether the machine-learning model is operating within the predefined limits based on the output and the predetermined output.