Multi-scale autoencoder generation method, electronic device and readable storage medium

An electronic device comprising:

• a storage device;
• at least one processor;
• and
• the storage device storing one or more programs, which when executed by the at least one processor, cause the at least one processor to:
• acquire a plurality of product images and acquire an annotation of each of the plurality of product images, an image size of each of the plurality of product images being the same and the plurality of product images comprising a plurality of non-defective images;
• construct latent spaces of a plurality of scales;
• construct a plurality of autoencoders according to the plurality of latent spaces and the image size of each of the plurality of product images;
• obtain a plurality of learners by training each of the plurality of autoencoders based on the plurality of non-defective images;
• input the plurality of product images into each of the plurality of learners and obtain a plurality of reconstructed images reconstructed by each learner;
• obtain a plurality of detection results by detecting whether each of the plurality of product images has defects according to the plurality of reconstructed images corresponding to each learner;
• determine similar images for each learner based on a comparison result between each of the plurality of detection results corresponding to each learner and a corresponding annotation result;
• calculate a correct rate of each learner according to the similar images corresponding to each learner, and determine a learner from the plurality of learner as a multi-scale autoencoder according to the correct rate of each learner.

A non-transitory storage medium having instructions stored thereon, when the instructions are executed by a processor of an electronic device, the processor is caused to perform a multi-scale autoencoder generation method, wherein the method comprises:

• acquiring a plurality of product images and acquiring an annotation of each of the plurality of product images, an image size of each of the plurality of product images being the same and the plurality of product images comprising a plurality of non-defective images;
• constructing latent spaces of a plurality of scales;
• constructing a plurality of autoencoders according to the plurality of latent spaces and the image size of each of the plurality of product images;
• obtaining a plurality of learners by training each of the plurality of autoencoders based on the plurality of non-defective images;
• inputting the plurality of product images into each of the plurality of learners and obtaining a plurality of reconstructed images reconstructed by each learner;
• obtaining a plurality of detection results by detecting whether each of the plurality of product images has defects according to the plurality of reconstructed images corresponding to each learner;
• determining similar images for each learner based on a comparison result between each of the plurality of detection results corresponding to each learner and a corresponding annotation result;
• calculating a correct rate of each learner according to the similar images corresponding to each learner, and determining a learner from the plurality of learner as a multi-scale autoencoder according to the correct rate of each learner.