US 12,260,630 B2
Methods and apparatus to implement parallel architectures for neural network classifiers
Ankit Goyal, Santa Clara, CA (US); Alexey Bochkovskiy, Podolsk (RU); and Vladlen Koltun, Santa Clara, CA (US)
Assigned to Intel Corporation, Santa Clara, CA (US)
Filed by Intel Corporation, Santa Clara, CA (US)
Filed on Jun. 25, 2021, as Appl. No. 17/359,232.
Claims priority of provisional application 63/194,627, filed on May 28, 2021.
Prior Publication US 2021/0319319 A1, Oct. 14, 2021
Int. Cl. G06K 9/00 (2022.01); G06F 18/25 (2023.01); G06N 3/045 (2023.01); G06N 3/063 (2023.01); G06N 3/08 (2023.01); G06V 10/764 (2022.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/82 (2022.01) [G06F 18/25 (2023.01); G06F 18/253 (2023.01); G06N 3/045 (2023.01); G06N 3/063 (2013.01); G06N 3/08 (2013.01); G06V 10/764 (2022.01); G06V 10/806 (2022.01)] 24 Claims
OG exemplary drawing
 
1. A non-transitory computer readable medium comprising instructions that, when executed, cause a machine to at least:
process a first stream using first neural network blocks, the first stream based on an input image;
process a second stream using second neural network blocks, the second stream based on the input image;
fuse a result of the first neural network blocks and the second neural network blocks;
perform average pooling on the result of the fuse;
process a fully connected layer based on the result of the average pooling; and
classify the image based on an output of the fully connected layer.