Abstract: This application relates to the artificial intelligence field, and provides an image processing method, an apparatus, and a system. The image processing method includes: obtaining a plurality of image blocks by segmenting a to-be-analyzed pathological image; inputting the plurality of image blocks to a first analysis model to obtain a first analysis result, where the first analysis model classifies each of the plurality of image blocks based on a quantity or an area of suspicious lesion components; inputting at least one second-type image block in the first analysis result to a second analysis model to obtain a second analysis result, where the second analysis model analyzes a location of a suspicious lesion component of each input second-type image block; and obtaining a final analysis result of the pathological image based on the first analysis result and the second analysis result.

Abstract: The method includes: obtaining medical detection data to be interpreted, where the medical detection data to be interpreted includes a detection image and indicator data; performing image recognition on the detection image, to obtain image recognition data; and interpreting, by using a rule library, the indicator data and the image recognition data, to obtain an interpretation result, where an interpretation rule in the rule library is obtained by mining and analyzing a plurality of pieces of interpreted data based on a data mining algorithm, and the rule library is dynamically updated with an interpretation process. Because the interpretation rule in the rule library is obtained by mining and analyzing the plurality of pieces of interpreted data based on the data mining algorithm, a potential data law that is difficult to be discovered by human can be mined, and a more accurate interpretation rule can be extracted.

Abstract: Embodiments of the present invention disclose a data processing apparatus. The apparatus is configured to: after calculating a set of gradient information of each parameter by using a sample data subset, delete the sample data subset, read a next sample data subset, calculate another set of gradient information of each parameter by using the next sample data subset, and accumulate a plurality of sets of calculated gradient information of each parameter, to obtain an update gradient of each parameter.

Abstract: An object detection model training method performed by a computing device, includes obtaining a system parameter including at least one of a receptive field of a backbone network, a size of a training image, a size of a to-be-detected object in the training image, a training computing capability, or a complexity of the to-be-detected object, determining a configuration parameter based on the system parameter, establishing a variable convolution network based on the configuration parameter and a feature map of the backbone network, recognizing the to-be-detected object based on a feature of the variable convolution network, and training the backbone network and the variable convolution network, where a convolution core used by any variable convolution layer may be offset in any direction in a process of performing convolution.

Abstract: In an object detection model training method, a classifier that has been trained in a first phase is duplicated to at least two copies, and in a training in a second phase, each classifier obtained through duplication is configured to detect to-be-detected objects with different sizes, and train an object detection model based on a detection result.

Abstract: This application relates to the artificial intelligence field, and provides an image processing method, an apparatus, and a system. The image processing method includes: obtaining a plurality of image blocks by segmenting a to-be-analyzed pathological image; inputting the plurality of image blocks to a first analysis model to obtain a first analysis result, where the first analysis model classifies each of the plurality of image blocks based on a quantity or an area of suspicious lesion components; inputting at least one second-type image block in the first analysis result to a second analysis model to obtain a second analysis result, where the second analysis model analyzes a location of a suspicious lesion component of each input second-type image block; and obtaining a final analysis result of the pathological image based on the first analysis result and the second analysis result.

Abstract: An object detection model training method performed by a computing device, includes obtaining a system parameter including at least one of a receptive field of a backbone network, a size of a training image, a size of a to-be-detected object in the training image, a training computing capability, or a complexity of the to-be-detected object, determining a configuration parameter based on the system parameter, establishing a variable convolution network based on the configuration parameter and a feature map of the backbone network, recognizing the to-be-detected object based on a feature of the variable convolution network, and training the backbone network and the variable convolution network, where a convolution core used by any variable convolution layer may be offset in any direction in a process of performing convolution.

Abstract: In an object detection model training method, a classifier that has been trained in a first phase is duplicated to at least two copies, and in a training in a second phase, each classifier obtained through duplication is configured to detect to-be-detected objects with different sizes, and train an object detection model based on a detection result.

Abstract: The present disclosure relates to the technical field of electric light sources, particularly to a metal halide lamp and a manufacturing method thereof.

Abstract: The present disclosure relates to the technical field of electric light sources, particularly to a metal halide lamp and a manufacturing method thereof.

Abstract: A training method, apparatus, and chip for a neural network model includes determining a model training mode of each layer based on an estimated data volume in a model parameter set and an estimated data volume of output data of the layer, obtaining second output data that is obtained by m worker modules by training a (j?1)th layer, and directly obtaining by a worker module a global gradient of a model parameter by training the model parameter based on the second output data when a model parallel training mode is used for a jth layer.

Abstract: Embodiments of the present invention disclose a data processing apparatus. The apparatus is configured to: after calculating a set of gradient information of each parameter by using a sample data subset, delete the sample data subset, read a next sample data subset, calculate another set of gradient information of each parameter by using the next sample data subset, and accumulate a plurality of sets of calculated gradient information of each parameter, to obtain an update gradient of each parameter.

Abstract: A method for training a neural network model are disclosed. Each training period includes K iterations, and for an ith iteration of one of N worker modules within each training period, each worker module performs in parallel the following steps: calculating a model parameter of an (i+1)th iteration based on a local gradient of the ith iteration and a model parameter of the ith iteration, and if i is less than K, calculating a local gradient of the (i+1)th iteration based on the model parameter of the (i+1)th iteration and sample data of the (i+1)th iteration; and pulling, by the worker module, a global gradient of an rth iteration from a server module and/or pushing, by the worker module, a local gradient of an fth iteration to the server module. In this way, time windows of a calculation process and a communication process overlap, thereby reducing time delay.