NEURAL NETWORK PROCESSING UNIT FOR HYBRID AND MIXED PRECISION COMPUTING

    公开(公告)号:US20220156567A1

    公开(公告)日:2022-05-19

    申请号:US17505422

    申请日:2021-10-19

    Applicant: MediaTek Inc.

    Abstract: A neural network (NN) processing unit includes an operation circuit to perform tensor operations of a given layer of a neural network in one of a first number representation and a second number representation. The NN processing unit further includes a conversion circuit coupled to at least one of an input port and an output port of the operation circuit to convert between the first number representation and the second number representation. The first number representation is one of a fixed-point number representation and a floating-point number representation, and the second number representation is the other one of the fixed-point number representation and the floating-point number representation.

    DYNAMIC CONVOLUTIONS TO REFINE IMAGES WITH VARIATIONAL DEGRADATION

    公开(公告)号:US20230196526A1

    公开(公告)日:2023-06-22

    申请号:US17552912

    申请日:2021-12-16

    Applicant: MediaTek Inc.

    CPC classification number: G06T5/50 G06T5/001 G06N3/04

    Abstract: A system stores parameters of a feature extraction network and a refinement network. The system receives an input including a degraded image concatenated with a degradation estimation of the degraded image; performs operations of the feature extraction network to apply pre-trained weights to the input to generate feature maps; and performs operations of the refinement network including a sequence of dynamic blocks. One or more of the dynamic blocks dynamically generates per-grid kernels to be applied to corresponding grids of an intermediate image output from a prior dynamic block in the sequence. Each per-grid kernel is generated based on the intermediate image and the feature maps.

    Network Space Search for Pareto-Efficient Spaces

    公开(公告)号:US20230064692A1

    公开(公告)日:2023-03-02

    申请号:US17846007

    申请日:2022-06-22

    Applicant: MediaTek Inc.

    Abstract: According to a network space search method, an expanded search space is partitioned into multiple network spaces. Each network space includes a plurality of network architectures and is characterized by a first range of network depths and a second range of network widths. The performance of the network spaces is evaluated by sampling respective network architectures with respect to a multi-objective loss function. The evaluated performance is indicated as a probability associated with each network space. The method then identifies a subset of the network spaces that has the highest probabilities, and selects a target network space from the subset based on model complexity.

Patent Agency Ranking