Beijing Baidu Netcom Science and Technology Co., Ltd.

Beijing Baidu Netcom Science Technology Co., Ltd

Dianhai Yu

Yanjun Ma

Haifeng Wang

Xiaoguang Hu

Yuning Du

Qiwen Liu

Yi Liu

Daxiang Dong

Yu Sun

Tian Wu

Ruoyu Guo

Shengyu Wei

Shiqi Zhao

Xiang Lan

Ran Bi

Qiao Zhao

Ying Zhou

Hongyu Liu

Cheng Cui

Tingquan Gao

Xueying Lyu

Shuilong Dong

Liujie Zhang

Huihuang Zheng

Ke Wei Sun

Shuohuan Wang

Yukun Li

Xiao Yin Zhou

Liwei Chen

Baohua Lai

Zeyu Chen

Wenhui Zhang

Zhihua Wu

Shengxian Wan

Bin Lu

Yamei Li

Jun Zhang

Wei Zhou

Fei Guo

Weiwei Liu

Chenxia Li

Qingqing Dang

Weibao Gong

Haoshuang Wang

Guanghua Yu

Can Wen

Sensen He

Shao Zeng

Yehua Yang

Yuying Hao

Zewu Wu

Zhiliang Yu

Xueying Lv

Tianjian He

Zhiliang Tian

Xiaoting Yin

Guanzhong Wang

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.

Deep learning framework scheduling

The invention discloses a method and an apparatus for updating parameters of a multi-task model. The method includes: obtaining a training sample set, in which the training sample set comprises a plurality of samples and a task to which each sample belongs; putting each sample into a corresponding sample queue sequentially according to the task to which each sample belongs; training a shared network layer in the multi-task model and a target sub-network layer of tasks associated with the sample queue with samples in the sample queue in case that the number of the samples in the sample queue reaches a training data requirement, so as to generate a model parameter update gradient corresponding to the tasks associated with the sample queue; and updating parameters of the shared network layer and the target sub-network layer in a parameter server according to the model parameter update gradient.

Method and apparatus for updating parameter of multi-task model, and storage medium

The present application discloses a distributed training method and system, a device and a storage medium, and relates to technical fields of deep learning and cloud computing. The method includes: sending, by a task information server, a first training request and information of an available first computing server to at least a first data server; sending, by the first data server, a first batch of training data to the first computing server, according to the first training request; performing, by the first computing server, model training according to the first batch of training data, sending model parameters to the first data server so as to be stored after the training is completed, and sending identification information of the first batch of training data to the task information server so as to be recorded; wherein the model parameters are not stored at any one of the computing servers.

Distributed training method and system, device and storage medium

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.

Image processing

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.

Method for training feature extraction model, method for classifying image, and related apparatuses

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.

Method of constructing network model for deep learning, device, and storage medium

The present disclosure provides a vision processing and model training method, device, storage medium and program product. A specific implementation solution is as follows: establishing an image classification network with the same backbone network as the vision model, performing a self-monitoring training on the image classification network by using an unlabeled first data set; initializing a weight of a backbone network of the vision model according to a weight of a backbone network of the trained image classification network to obtain a pre-training model, the structure of the pre-training model being consistent with that of the vision model, and optimize the weight of the backbone network by using real data set in a current computer vision task scenario, so as to be more suitable for the current computer vision task; then, training the pre-training model by using a labeled second data set to obtain a trained vision model.

Vision processing and model training method, device, storage medium and program product

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.

Image processing method and apparatus, device, medium and program product

An imaging exposure control method and apparatus, a device and a storage medium, which relate to the field of artificial intelligence technologies, such as machine learning technologies and intelligent imaging technologies, are disclosed. An implementation includes performing semantic segmentation on a preformed image to obtain semantic segmentation images of at least two semantic regions; estimating an exposure duration of each semantic region based on the semantic segmentation image and the preformed image; and controlling exposure of each semantic region during imaging based on the exposure duration of each semantic region.

Imaging exposure control method and apparatus, device and storage medium

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.

Method and apparatus of training model, device, medium, and program product

The disclosure discloses a conversation-based recommending method. A directed graph corresponding to a current conversation is obtained. The current conversation includes clicked items, the directed graph includes nodes and directed edges between the nodes, each node corresponds to a clicked item, and each directed edge indicates relationship data between the nodes. For each node of the directed graph, an attention weight is determined for each directed edge corresponding to the node based on a feature vector of the node and the relationship data for each node of the directed graph. A new feature vector of the node is determined based on the relationship data and the attention weight of each directed edge. A feature vector of the current conversation is determined based on the new feature vector of each node. An item is recommended based on the feature vector of the current conversation.

Conversation-based recommending method, conversation-based recommending apparatus, and device

A method and an apparatus for generating a shared encoder are provided, which belongs to a field of computer technology and deep learning. The method includes: sending by a master node a shared encoder training instruction to child nodes, so that each child node obtains training samples based on a type of a target shared encoder included in the training instruction; sending an initial parameter set of the target shared encoder to be trained to each child node after obtaining a confirmation message returned by each child node; obtaining an updated parameter set of the target shared encoder returned by each child node; determining a target parameter set corresponding to the target shared encoder based on a first preset rule and the updated parameter set of the target shared encoder returned by each child node.

Method and apparatus for generating shared encoder

Provided are a text processing method, a device and a storage medium, relating to a field of computer technology, and especially to a field of artificial intelligence, such as natural language processing and deep learning. The specific implementation scheme includes: performing text processing on first text, by using a text processing acceleration operator; and processing, in parallel and faster, content after the text processing, by using the text processing acceleration operator. Text processing and parallel acceleration are carried out by the text processing acceleration operator, which can improve the speed of text processing.

Text processing method, device and storage medium

A data processing method and apparatus based on a recurrent neural network and a device are provided. The recurrent neural network includes multiple recurrent units, each recurrent unit includes multiple data processing nodes and a start node, at least one recurrent unit includes an end node, and at least one data processing node is included between the start node and the end node. During the processing of the first target processing object in a first recurrent unit, in a case that the first target processing object does not satisfy the first preset condition, the start node in the first recurrent unit is run to add a tag to the data processing nodes subsequent to the start node and stop addition of the tag in response to reaching the end node, and no processing is performed by the data processing nodes with the tag.

Data processing method and apparatus based on recurrent neural network, and device

The present application discloses a processor video memory optimization method and apparatus for deep learning training tasks, and relates to the technical field of artificial intelligence. In the method, by determining an optimal path for transferring a computing result, the computing result of a first computing unit is transferred to a second computing unit by using the optimal path. Thus, occupying the video memory is avoided, and meanwhile, a problem of low utilization rate of the computing unit of a GPU caused by video memory swaps is avoided, so that training speed of most tasks is hardly reduced.

Processor memory optimization method and apparatus for deep learning training tasks

Growing community of inventors

Beijing, China

Dianhai Yu