SPPNet_Feature

用Pytorch编写以vgg16为骨干网络的sppnet提取最后一层卷积层的特征。

Requirements

• python==2.7.12
• torchvision==0.2.0
• scipy==1.0.0
• torch==0.3.1
• numpy==1.11.0
• Pillow==5.3.0

Usage

python sppnet_feature.py

References

1. He K, Zhang X, Ren S, et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition[C]// European Conference on Computer Vision. Springer International Publishing, 2014:346-361.

2. Simonyan, K. and Zisserman, A., 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.