An-Improved-PeleeNet-Algorithm-with-Feature-Pyramid-Networks-for-Image-Detection

I propose an effective framework based on Feature Pyramid Networks to improve the recognition accuracy of deep and shallow images while guaranteeing the recognition speed of PeleeNet structured images. Compared with PeleeNet, the accuracy of structure recognition on CIFAR-10 data set increased by 4.0%.

Thank you for your reference in the PeleeNet section of Youzhao Yang's code.（github：nnUyi） PeleeNet:https://arxiv.org/abs/1804.06882 FPN：https://arxiv.org/abs/1612.03144 data: cifar-10 download:https://pan.baidu.com/s/1eTwtvvc key:deky