资源算法yolov3-channel-pruning

yolov3-channel-pruning

2020-03-04 | |  36 |   0 |   0

yolov3-channel-pruning

Update:

补充prune_utils.py. 在自己的数据集上,剪枝30%-50%, mAP不变。

requirements:

  • numpy>=1.13

  • tensorboardX

pip install tensorboardX

or

git clone https://github.com/lanpa/tensorboardX && cd tensorboardX && python setup.py install
  • albumentations

pip install albumentations

or

conda install -c conda-forge imgaug
conda install albumentations -c albumentations
  • terminaltables

pip install terminaltables
  • tqdm

  • torch

  • random

  • matplotlib

  • .......

Run

python train.py --model_def config/yolov3.cfg

python train.py --model_def config/yolov3.cfg -sr

python test_prune.py

python train.py --model_def config/prune_yolov3.cfg -pre checkpoints/prune_yolov3_ckpt.pth

图片.png

Reference:

YOLOv3-model-pruning(感谢Lam1360给了很多帮助)

yolov3-network-slimming

PyTorch-YOLOv3


上一篇:yolov3-mxnet

下一篇: tensorflow-lite-YOLOv3

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 ...