A learned model includes an input layer; intermediate layers connected to the input layer; and an output layer connected to the intermediate layer. The learned model causes a computer to function to perform machine learning based on first data indicating a result detected while a product is produced by an injection molding machine or a result of measuring the product after the product is produced, and ground truth information indicating whether a value included in a section is ground truth for each section obtained by dividing an amount relating to production of the product into sections, and output, from the output layer, a degree to which the value included in the section is the ground truth, when second data is input from the input layer, the second data indicating the result detected while the product is produced or the result of measuring the product after being produced.

An inspection apparatus includes an imaging device acquiring a polarization image of a molding product, and a determination unit determining quality of the molding product. The determination unit includes an image generating unit generating a pseudo image from an input image in accordance with a machine-learned learning model, and the determination unit inputs the polarization image or a calculation image obtained by calculation from the polarization image to the image generating unit as the input image and determines the quality of the molding product based on the input image and the pseudo image generated by the image generating unit.