2022.11.28
Overview
An image recognition edge device is provided, which includes a memory and a processor. The processor accesses multiple instructions to perform the following operations: down-sampling an input image to generate a down-sampled image; inputting the down-sampled image to an object recognition model through multiple convolutional layers to sequentially generate multiple feature tensors; selecting a part of the feature tensors to form a first feature tensor pyramid; selecting another part of the feature tensors to form a second feature tensor pyramid; inputting the first feature tensor pyramid and the second feature tensor pyramid into a combined fully connected layer, generating a first image detection label by a first fully connected output layer based on the first feature tensor pyramid, and generating a second image detection label by the second fully connected output layer based on the second feature tensor pyramid.Category
發明
Applying
18/058,878
Filing Date
2022.11.28Notification
2023.04.27