Inspur Suzhou Intelligent Technology Co., Ltd

Suzhou Metabrain Intelligent Technology Co., Ltd.

Hongli Liu

Feng Li

Xiaolan Zhang

Zhenzhen Zhou

Xin Liu

This disclosure discloses a network model training method and apparatus, an electronic apparatus and a computer-readable storage medium. The method includes: acquiring training data and inputting the training data into an initial model to obtain output data, wherein the initial model includes an embedding layer, the embedding layer is constructed based on preset network layer latency information, the preset network layer latency information includes network layer types and at least two types of latency data corresponding to each network layer type, and each type of latency data corresponds to different device types; inputting a current device type and a target network layer type of each target network layer in the initial model into the embedding layer to obtain target latency data corresponding to other device type; calculating a target loss value based on the target latency data, the training data and the output data, and adjusting parameters of the initial model based on the target loss value; and obtaining a target model based on the initial model in response to a training completion condition is satisfied. By means of the method, the target model has a minimum latency when running on a device corresponding to the other device type.

Network model training method and apparatus, electronic apparatus and computer-readable storage medium

An automatic modeling method for object detection model, the method includes: Ssearching for an NAS network model according to a predetermined first neural network; Straining a first object detection model by using a training set, evaluating the current first object detection model by using a validation set after a number of training times reaches a first preset number of times, and outputting an evaluation result, wherein the first object detection model is a model obtained by detection part fusion of the NAS network model and a second object detection model; Scalculating a reward corresponding to the current first object detection model; Sadjusting parameters used for searching for the NAS network model according to the reward: repeating the steps S-Sfor a second preset number of times, and determining an optimal first object detection model according to the evaluation result. Further disclosed in the present invention is an automatic modeling device. The method and device provided by the present invention can search for different models according to different tasks, and improve an object detection effect.

Automatic modeling method and device for object detection model

An image data enhancement method and apparatus, a computer device, and a storage medium are provided. The method includes: segmenting an original image to obtain segmented images and target categories of the segmented images, and obtaining, by means of the target categories, categories to be enhanced (S); binarizing the original image according to the categories to be enhanced, and obtaining instance images, according to a connected domain of the binary images, from the original image (S); performing perspective processes on the instance images to obtain first instance images, and zooming the first instance images to obtain second instance images (S); obtaining a vanishing point position from the original image, determining pasting positions of the second instance images according to the vanishing point position and the second instance images, and pasting the second instance images to the original image according to the pasting positions to obtain an enhanced image (S).

Growing community of inventors

Jiangsu, China

Hongli Liu