Abstract: Embodiments of this application provide a model training method. The system includes: A client is configured to train a first model based on unlabeled data, and is further configured to send a parameter of a first subnet in the first model to a server; the server is configured to train a second model based on the parameter of the first subnet and labeled data, to update a parameter of the second model, and the server is further configured to send an updated parameter of the first subnet and an updated parameter of a third subnet to the client; and the client is further configured to obtain a target model based on the parameter of the first subnet and the parameter of the third subnet that are from the server.

Abstract: A film layer curing apparatus includes: a support platform, configured to carry a substrate having a film layer on the substrate surface; and a light source component located above the support platform, the light source component including a light source array being arranged toward the support platform and covering the light outgoing surface of the entire film layer by projection of the light source array, the light source array including multiple point light sources evenly distributed on the light outgoing surface, light emitted by the light source array being able to uniformly irradiate the entire film layer so as to improve the thickness distribution uniformity of the film layer after curing.