资源分类
》 资源 》算法》yolov3-network-slimming

yolov3-network-slimming

2020-01-14 | |  38 |   0 |   0

yolov3-network-slimming

LICENSE

将Learning Efficient Convolutional Networks Through Network Slimming (ICCV 2017)应用在yolov3和yolov2上

环境

pytorch 0.41

window 10

如何使用

1.对原始weights文件进行稀疏化训练

python sparsity_train.py -sr --s 0.0001 --image_folder coco.data  --cfg yolov3.cfg --weights yolov3.weights

2.剪枝

python prune.py --cfg yolov3.cfg --weights checkpoints/yolov3_sparsity_100.weights --percent 0.3

3.对剪枝后的weights进行微调

python sparsity_train.py --image_folder coco.data  --cfg prune_yolov3.cfg --weights prune_yolov3.weights

关于new_prune.py

new_prune更新了算法，现在可以确保不会有某一层被减为0的情况发生，参考RETHINKING THE SMALLER-NORM-LESSINFORMATIVE ASSUMPTION IN CHANNEL PRUNING OF CONVOLUTION LAYERS(ICLR 2018)对剪枝后bn层β系数进行了保留

待完成

coco测试


上一篇：YOLOv3-complete-pruning

下一篇：YOLO_v3_tutorial_from_scratch

用户评价
全部评价

热门资源

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • shih-styletransfer

    shih-styletransfer Code from Style Transfer ...