首页>
外国专利>
Cycle GAN is used to convert an RGB training image set to a Non-RGB training image set so that it can be used for object detection learning for objects in images with Non-RGB format to make computing load and recycled data noticeable. Learning methods and learning devices that can be reduced to, and test methods and test devices that use them.
Cycle GAN is used to convert an RGB training image set to a Non-RGB training image set so that it can be used for object detection learning for objects in images with Non-RGB format to make computing load and recycled data noticeable. Learning methods and learning devices that can be reduced to, and test methods and test devices that use them.
To provide a learning method for converting an RGB training image set to a Non-RGB training image set so as to be usable for object detection learning of an image having a Non-RGB format.SOLUTION: The learning method includes the steps of: causing a first image having an RBG format to be converted into a second image having a Non-RGB format by a first transformer 130 and causing the second image to be converted into a third image having an RGB format by a second transformer 150; causing a fourth image having a Non-RGB format to be converted into a fifth image having an RGB format by the second transformer 150 and causing the fifth image to be converted into a sixth image having a Non-RGB format by the first transformer 130; and referring to some of the first to sixth images, calculating a loss and learning some of parameters.SELECTED DRAWING: Figure 4
展开▼