Abstract: Provided are a method for processing multimodal images, an apparatus, a device and a storage medium. Multiple types of vision sensors are disposed in first preset identity recognition scenario.

Abstract: An update method for a face database, and a face recognition method, an apparatus and a system, including: obtaining a face image set belonging to a same user as an obtained current face image in an original face database, where the face database includes a face image set of at least one user, and the face image set includes a stored face image; determining similarity between the current face image and the stored face image of the same user, where there is a count value for the stored face image of the same user, and the count value represents a number of consecutive unsuccessful matches or consecutive successful matches between the stored face image of the same user and a further face image of the same user; and updating the original face database according to the similarity and the count value.

Abstract: Provided are a method for processing multimodal images, an apparatus, a device and a storage medium. Multiple types of vision sensors are disposed in first preset identity recognition scenario.

Abstract: Embodiments of the present disclosure provide a method and apparatus for determining a network model pruning strategy, a device and a storage medium. The method may include: generating a BN threshold search space using configuration information of the BN threshold search space for a network model for a target hardware; generating a pruning strategy code generator using the BN threshold search space; randomly generating a BN threshold code using the pruning strategy code generator; decoding the BN threshold code to obtain a candidate BN threshold; and determining a target pruning strategy of the network model for the target hardware, based on a pruning accuracy loss of the network model corresponding to the candidate BN threshold.

Abstract: A method, and an apparatus for model distillation are provided. The method may include: obtaining a batch of teacher features corresponding to a teacher model and a batch of student features corresponding to a student model; determining a set of teacher similarities corresponding to the batch of teacher features and a set of student similarities corresponding to the batch of student features; determining weights of loss values of features of images based on difference values corresponding to the images; and weighting a loss value of a feature of each image in a batch of images, training the student model by using a weighting result. The present disclosure may use the difference values between the feature similarities of the student model and the feature similarities of the teacher model to determine the weights of the loss values.

Abstract: The present disclosure provides a method and apparatus for processing a heterogeneous cluster-oriented task. The method comprises: receiving a task request and a basic execution environment; scheduling a heterogeneous device according to the task request; compiling the basic execution environment into an execution environment corresponding to the scheduled heterogeneous device, and deploying on the scheduled heterogeneous device; triggering the scheduled heterogeneous device to execute the task request. It is only necessary for the user to provide the basic execution environment with respect to the task, and unnecessary for the user to respectively write a version of execution environment for each type of hardware platform, thereby implementing quick development of the heterogeneous device code and reducing the development and maintenance costs.

Abstract: The present disclosure provides a method and apparatus for processing a heterogeneous cluster-oriented task. The method comprises: receiving a task request and a basic execution environment; scheduling a heterogeneous device according to the task request; compiling the basic execution environment into an execution environment corresponding to the scheduled heterogeneous device, and deploying on the scheduled heterogeneous device; triggering the scheduled heterogeneous device to execute the task request. It is only necessary for the user to provide the basic execution environment with respect to the task, and unnecessary for the user to respectively write a version of execution environment for each type of hardware platform, thereby implementing quick development of the heterogeneous device code and reducing the development and maintenance costs.