Abstract: An apparatus and a method for executing a customized production line using an artificial intelligence development platform, a computing device and a computer readable storage medium are provided. The apparatus includes: a production line executor configured to generate a native form of the artificial intelligence development platform based on a file set, the native form to be sent to a client accessing the artificial intelligence development platform so as to present a native interactive page of the artificial intelligence development platform; and a standardized platform interface configured to provide an interaction channel between the production line executor and the artificial intelligence development platform. The production line executor is further configured to generate an intermediate result by executing processing logic defined in the file set and to process the intermediate result by interacting with the artificial intelligence development platform via the standardized platform interface.

Abstract: Techniques for storage testing involve: acquiring a first state of a storage system including first input/output (IO) load information; taking a first action based on the first state, the first action causing the first IO load information to be changed to second IO load information; updating the first action to be a reserved action for the first state if it is obtained based on the second IO load information that the storage system reaches a preset condition; and obtaining an action combination of a plurality of IO load information changes based on a plurality of reserved actions corresponding to a plurality of states, wherein the plurality of states include the first state. Accordingly, the most effective load combination change mode for the storage system can be found automatically and more accurately, so as to find more vulnerabilities of the storage system, thereby improving the efficiency of storage system testing.

Abstract: Provided are a streaming media processing method based on inference service, an electronic device, and a storage medium, which relates to the field of artificial intelligence, and in particular, to the field of inference service of artificial intelligence models. The method includes: detecting, in a process of processing a k-th channel of streaming media through an i-th inference service pod, the i-th inference service pod, to obtain a detection result of the i-th inference service pod, i and k being positive integers; determining a replacement object of the i-th inference service pod, in the case where it is determined that the i-th inference service pod is in an abnormal state based on the detection result of the i-th inference service pod; and processing the k-th channel of streaming media through the replacement object of the i-th inference service pod.

Abstract: Provided are a data processing method and apparatus, an electronic device, and a storage medium. The data processing method includes acquiring a target directed acyclic graph (DAG) corresponding to the service processing logic of a model self-taught learning service, where the service processing logic includes execution logic for acquiring service data generated by an online released service model, execution logic for training a to-be-trained service model based on the service data, and execution logic for releasing the trained service model online; and performing self-taught learning on the to-be-trained service model according to the target DAG.

Abstract: Provided are an inference service deployment method, a device and a storage medium, relating to the field of artificial intelligence technology, and in particular to the field of machine learning and inference service technology. The inference service deployment method includes: obtaining performance information of a runtime environment of a deployment end; selecting a target version of an inference service from a plurality of candidate versions of the inference service of a model according to the performance information of the runtime environment of the deployment end; and deploying the target version of the inference service to the deployment end.

Abstract: A method and apparatus for predicting a risk are provided. The method may include: determining an inherent risk probability of a to-be-tested object; building a relationship graph between the to-be-tested object and different associated objects; determining a primary conduction probability between any two directly associated objects in the relationship graph; determining, based on the primary conduction probability between any two directly associated objects in the relationship graph and the relationship graph, a multi-level conduction probability of the to-be-tested object; and determining a target risk probability of the to-be-tested object, based on the inherent risk probability and the multi-level conduction probability of the to-be-tested object.

Abstract: Methods, system, and non-transitory processor-readable storage medium for a tuning system are provided herein. An example method includes providing, by a tuning module, a tuning action based on a state associated with a test case, executing, by a tuning agent, the test case using the tuning action, assessing, by a tuning assessment module, the tuning action with respect to a long-term reward, and determining a similarity between a subsequent execution of the test case and the assessment of the tuning action on at least one previous execution of the test case to tune the tuning action.

Abstract: A method for model production includes acquiring a related operation for model production from a user interface layer of a model production system, and determining a software platform of the model production system; acquiring a model service corresponding to the related operation by invoking an application programming interface (API) corresponding to the related operation, wherein the API is located between the user interface layer and other layer in the model production system; performing the model service by invoking local resources of the software platform with a tool of the software platform adapted to the model service, to generate a target model; and applying the target model in a target usage scene.

Abstract: A method for running an inference service platform, includes: determining inference tasks to be allocated for the inference service platform, in which the inference service platform includes two or more inference service groups, versions of the inference service groups are different, and the inference service groups are configured to perform a same type of inference services; determining a flow weight of each of the inference service groups, in which the flow weight is configured to indicate a proportion of a number of inference tasks to which the corresponding inference service group need to be allocated in a total number of inference tasks; and allocating the corresponding number of inference tasks in the inference tasks to be allocated to each of the inference service groups based on the flow weight of each of the inference service groups; and performing the inference tasks by the inference service group.

Abstract: A color compensation method includes obtaining a target brightness, a target frame rate and a target pulse number; selecting a plurality of second gamma groups from a plurality of first gamma groups according to the target brightness and the target pulse number, wherein the plurality of first gamma groups respectively correspond to a plurality of frame rates; and calculating the compensation value to compensate the display brightness and color according to the target brightness, the target frame rate, the plurality of second gamma groups and a calculation method.

Abstract: The present disclosure discloses a method and an apparatus for adapting a deep learning model, an electronic device and a medium, which relates to technology fields of artificial intelligence, deep learning, and cloud computing. The specific implementation plan is: obtaining model information of an original deep learning model and hardware information of a target hardware to be adapted; querying a conversion path table according to the model information and the hardware information to obtain a matched target conversion path; and converting, according to the target conversion path, the original deep learning model to an intermediate deep learning model in the conversion path, and converting the intermediate deep learning model to the target deep learning model.

Abstract: A method for management of an artificial intelligence development platform is provided. The artificial intelligence development platform is deployed with instances of a plurality of model services, and each of the model services is provided with one or more instances. The method includes: acquiring calling information of at least one model service; determining the activity of the at least one model service according to the calling information; and at least deleting all instances of the at least one model service in response to that the determined activity meets a first condition.

Abstract: A resource scheduling method and apparatus, a device, and a storage medium are provided, and relates to the field of computer technology, and in particular to the field of deep learning technology. The method includes: acquiring a graphics processing unit (GPU) topology relationship of a cluster according to GPU connection information of each of computing nodes in the cluster; and in a case where a task request, for applying for a GPU resource, for a target task is received, determining a target computing node of the target task and a target GPU in the target computing node according to the task request and the GPU topology relationship, to complete GPU resource scheduling of the target task. The present disclosure can optimize the resource scheduling.

Abstract: An apparatus and a method for executing a customized production line using an artificial intelligence development platform, a computing device and a computer readable storage medium are provided. The apparatus includes: a production line executor configured to generate a native form of the artificial intelligence development platform based on a file set, the native form to be sent to a client accessing the artificial intelligence development platform so as to present a native interactive page of the artificial intelligence development platform; and a standardized platform interface configured to provide an interaction channel between the production line executor and the artificial intelligence development platform. The production line executor is further configured to generate an intermediate result by executing processing logic defined in the file set and to process the intermediate result by interacting with the artificial intelligence development platform via the standardized platform interface.

Abstract: A method includes: determining at least one typical object ratio from a first training data set by counting ratios of objects in training pictures of the first training data set; determining at least one picture scaling size based at least on the at least one typical object ratio; scaling the training pictures of the first training data set according to the at least one picture scaling size; obtaining a second training data set by slicing the scaled training pictures; training an object detection model using the second training data set; and performing object detection on a to-be-detected picture using the trained object detection model. The object detection method according to the embodiments of the present disclosure can be used to complete, without manual intervention, a task of detecting an extremely small object.

Abstract: A method and apparatus for generating a model, and a method and apparatus for recognizing information are provided. An implementation of the method for generating a model includes: acquiring a to-be-converted model, a topology description of the to-be-converted model, and device information of a target device; converting, based on the topology description and the device information, parameters and operators of the to-be-converted model to obtain a converted model applicable to the target device; and generating a deep learning prediction model based on the converted model. This embodiment enables the conversion of an existing model to a deep learning prediction model that can be applied to a target device.

Abstract: The present application discloses an image recognition method, apparatus, an electronic device and a storage medium, and relates to the field of neural networks and depth learning. An implementation solution may be as follows: loading a first image recognition model; inputting an image to be recognized into a first image recognition model; predicting the image to be recognized by using a first image recognition model to obtain an output result of a network layer of the first image recognition model; and performing post-processing on the output result of the network layer of the first image recognition model, to obtain an image recognition result.

Abstract: A method for management of an artificial intelligence development platform is provided. The artificial intelligence development platform is deployed with instances of a plurality of model services, and each of the model services is provided with one or more instances. The method includes: acquiring calling information of at least one model service; determining the activity of the at least one model service according to the calling information; and at least deleting all instances of the at least one model service in response to that the determined activity meets a first condition.

Abstract: A method and apparatus for generating a model, and a method and apparatus for recognizing information are provided. An implementation of the method for generating a model includes: acquiring a to-be-converted model, a topology description of the to-be-converted model, and device information of a target device; converting, based on the topology description and the device information, parameters and operators of the to-be-converted model to obtain a converted model applicable to the target device; and generating a deep learning prediction model based on the converted model. This embodiment enables the conversion of an existing model to a deep learning prediction model that can be applied to a target device.