-
1.发明公开公开(公告)号：US20230215148A1
公开(公告)日：2023-07-06
申请号：US18183590
申请日：2023-03-14
Inventor： Shuilong DONG , Sensen HE , Shengyu WEI , Cheng CUI , Yuning DU , Tingquan GAO , Shao ZENG , Ying ZHOU , Xueying LYU , Yi LIU , Qiao ZHAO , Qiwen LIU , Ran BI , Xiaoguang HU , Dianhai YU , Yanjun MA
IPC: G06V10/774 , G06V10/40 , G06V10/74 , G06V10/764 , G06V10/776 , G06V10/778
CPC classification number: G06V10/774 , G06V10/40 , G06V10/761 , G06V10/764 , G06V10/776 , G06V10/7784
Abstract: The present disclosure provides a method for training a feature extraction model, a method for classifying an image and related apparatuses, and relates to the field of artificial intelligence technology such as deep learning and image recognition. The scheme comprises: extracting an image feature of each sample image in a sample image set using a basic feature extraction module of an initial feature extraction model, to obtain an initial feature vector set; performing normalization processing on each initial feature vector in the initial feature vector set using a normalization processing module of the initial feature extraction model, to obtain each normalized feature vector; and guiding training for the initial feature extraction model through a preset high discriminative loss function, to obtain a target feature extraction model as a training result.
-
公开(公告)号：US20230085732A1
公开(公告)日：2023-03-23
申请号：US18058543
申请日：2022-11-23
Inventor： Yuying HAO , Yi LIU , Zewu WU , Baohua LAI , Zeyu CHEN , Dianhai YU , Yanjun MA , Zhiliang YU , Xueying LV
IPC: G06T7/11
Abstract: The present disclosure provides an image processing method and apparatus, and relates to the field of image processing, and in particular to the field of image annotation. An implementation is: obtaining an image to be processed including a target region to be annotated; in response to a first click on the target region, performing a first operation to expand a predicted region for the target region based on a click position of the first click; in response to a second click in a position where the predicted region exceeds the target region, performing a second operation to reduce the predicted region based on a click position of the second click; and in response to determining that a difference between the predicted region and the target region meets a preset condition, obtaining an outline of the predicted region to annotate the target region.
-
公开(公告)号：US20220391774A1
公开(公告)日：2022-12-08
申请号：US17887951
申请日：2022-08-15
Inventor： Feng XING , Xiang LAN , Liling NIU , Xiandong LIU , Yanjun MA , Dianhai YU , Haifeng WANG
Abstract: A method and apparatus for generating an operator are provided. The method includes: constructing a group of basic application programming interfaces for providing one of the following basic functions: an access function, a storage function, and a computing function; constructing a kernel application programming interface for invoking the basic application programming interfaces to implement an operator logic; and generating a target kernel operator based on the group of basic application programming interfaces and the kernel application programming interface.
-
公开(公告)号：US20220058490A1
公开(公告)日：2022-02-24
申请号：US17519815
申请日：2021-11-05
Inventor： Haifeng WANG , Xiaoguang HU , Hongyu LIU , Dianhai YU , Yanjun MA , Tian WU
Abstract: A method and apparatus of constructing a network model for deep learning, a device, and a storage medium, which relate to artificial intelligence, and in particular to a field of deep learning. The method of constructing the network model for deep learning includes: determining an execution mode for executing codes, based on a mode parameter; executing the codes by using a first component, which is executable in a first execution mode, through a syntax element in the codes, in response to determining that the execution mode is the first execution mode; and executing the codes by using a second component, which is executable in a second execution mode, through the syntax element, in response to determining that the execution mode is the second execution mode; wherein the first component and the second component have the same component interface, and the syntax element corresponds to the component interface.
-
5.发明公开公开(公告)号：US20240070454A1
公开(公告)日：2024-02-29
申请号：US18108956
申请日：2023-02-13
Inventor： Ruoyu GUO , Yuning DU , Chenxia LI , Baohua LAI , Yanjun MA
Abstract: Provided is a lightweight model training method, an image processing method, a device and a medium. The lightweight model training method includes: acquiring first and second augmentation probabilities and a target weight adopted in an e-th iteration; performing data augmentation on a data set based on the first and second augmentation probabilities respectively, to obtain first and second data sets; obtaining a first output value of a student model and a second output value of a teacher model based on the first data set; obtaining a third output value and a fourth output value based on the second data set; determining a distillation loss function, a truth-value loss function and a target loss function; training the student model based on the target loss function; and determining a first augmentation probability or target weight to be adopted in an (e+1)-th iteration in a case of e is less than E.
-
Patent Agency Ranking
公开(公告)号：US20220222111A1
公开(公告)日：2022-07-14
申请号：US17707895
申请日：2022-03-29
Inventor： Haifeng Wang , Xiaoguang HU , Dianhai YU , Yanjun MA , Tian WU
Abstract: A scheduling method for a deep learning framework, a scheduling apparatus, an electronic device, a storage medium, and a program product is provided, and can be used in the field of artificial intelligence, especially in the fields of machine learning, deep learning, etc. The method includes: receiving a processing request for processing a plurality of tasks by using a dedicated processing unit, the processing request including scheduling requirements for the plurality of tasks, and each of the plurality of tasks being associated with execution of multi-batch data processing; and scheduling, based on the scheduling requirements for the plurality of tasks in batches of data, the dedicated processing unit to process the plurality of tasks.
-
7.发明申请公开(公告)号：US20220004930A1
公开(公告)日：2022-01-06
申请号：US17480292
申请日：2021-09-21
Inventor： Qingqing DANG , Kaipeng DENG , Lielin JIANG , Sheng GUO , Xiaoguang HU , Chunyu ZHANG , Yanjun MA , Tian WU , Haifeng WANG
Abstract: Embodiments of the present disclosure provide a method and apparatus of training a model, an electronic device, a storage medium and a development system, which relate to a field of deep learning. The method may include calling a training preparation component to set at least a loss function and an optimization function for training the model, in response to determining that a training preparation instruction is received. The method further includes calling a training component to set a first data reading component, in response to determining that a training instruction is received. The first data reading component is configured to load a training data set for training the model. In addition, the method may further include training the model based on the training data set from the first data reading component, by using the loss function and the optimization function through the training component.
-
公开(公告)号：US20220004811A1
公开(公告)日：2022-01-06
申请号：US17479061
申请日：2021-09-20
Inventor： Ruoyu GUO , Yuning DU , Weiwei LIU , Xiaoting YIN , Qiao ZHAO , Qiwen LIU , Ran BI , Xiaoguang HU , Dianhai YU , Yanjun MA
IPC: G06K9/62
Abstract: There is provided a method and apparatus of training a model, a device, and a medium, which relate to artificial intelligence, and in particular to a deep learning and image processing technology. The method may include: determining a plurality of augmented sample sets associated with a plurality of original samples; determining a first constraint according to a first model based on the plurality of augmented sample sets; determining a second constraint according to the first model and a second model based on the plurality of augmented sample sets, wherein the second constraint is associated with a difference between outputs of the first model and the second model for one augmented sample, and the first model has a complexity lower than that of the second model; training the first model based on at least the first constraint and the second constraint, so as to obtain a trained first model.
-
公开(公告)号：US20250005446A1
公开(公告)日：2025-01-02
申请号：US18547090
申请日：2022-11-02
Inventor： Weihang CHEN , Haifeng WANG , Yunfei ZHANG , Risheng YUAN , Tianyu CHEN , Hongyu LIU , Xiaoguang HU , Dianhai YU , Yanjun MA
IPC: G06N20/00
Abstract: An operator processing method of a deep learning framework an electronic device, and a storage medium are provided, which relate to a field of computer technology, especially in a field of artificial intelligence technology such as deep learning. The specific implementation scheme includes: acquiring an operator to be processed, where the operator to be processed includes a template parameter independent of the deep learning framework and an operator kernel function; parsing, in response to receiving an input information for the operator to be processed, the template parameter by using the input information to obtain a plurality of complete template parameters related to the deep learning framework; and processing the operator kernel function according to the plurality of complete template parameters, to obtain an available operator for the deep learning framework.
-
公开(公告)号：US20230186599A1
公开(公告)日：2023-06-15
申请号：US18078635
申请日：2022-12-09
Inventor： Ruoyu GUO , Yuning DU , Shengyu WEI , Shuilong DONG , Qiwen LIU , Qiao ZHAO , Ran BI , Xiaoguang HU , Dianhai YU , Yanjun MA
CPC classification number: G06V10/761 , G06V10/751
Abstract: Provided are an image processing method and apparatus, a device, a medium and a program product. The image processing method includes: performing image augmentation on an original image to obtain at least one augmented image; performing subject detection on the original image and the at least one augmented image to obtain an original detection frame in the original image and an augmented detection frame in the at least one augmented image; determining whether the original detection frame and the augmented detection frame belong to the same subject; and in response to the original detection frame and the augmented detection frame belonging to the same subject, determining a target subject frame in the original image according to the augmented detection frame.
-
-
-
-
-
-
-
-
-
Search Results
22
records
(took 0.017 seconds)
