Data processing method and data processing system
AssigneePanasonic Intellectual Property Corporation of America
InventorsYohei Nakata, Sotaro Tsukizawa, Yasunori Ishii
Life of this patent
Estimating the term…
Abstract
In a data processing method executed by a computer: inputting, in a third trained model, first output data corresponding to first input data for a first trained model to obtain second output data, the third trained model being acquired through training in which (i) output data of the first trained model is used as training data, and (ii) output data of a second trained model acquired by converting the first trained model is used as label data; obtaining first label data of the first input data; and retraining the first trained model using first differential data corresponding to differences between the second output data and the first label data.
Claims6
A data processing method, comprising the following executed by a computer:
- inputting, in a second trained model acquired by converting a first trained model, first input data to obtain second output data;
- obtaining first label data of the first input data;
- and
- retraining the first trained model using first differential data corresponding to differences between the second output data and the first label data.
A data processing system, comprising:
- a computer that:
- inputs in a second trained model acquired by converting a first trained model, first input data to obtain second output data;
- obtains first label data of the first input data;
- and
- retrains the first trained model using first differential data corresponding to differences between the second output data and the first label data.
A data processing method, comprising the following executed by a computer:
- inputting, in a second trained model for object detection acquired by converting a first trained model, first input image data to obtain second detection result data;
- obtaining first label data of the first input image data;
- and
- retraining the first trained model using first differential data corresponding to differences between the second detection result data and the first label data.
Dependencies are inferred from the claim text.